Claude Code Toolkit
The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills (+400,000 via SkillKit), 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 15 MCP configs, 26 companion apps, 53 ecosystem entries, and more.
Quick Install
Plugin marketplace (recommended):
/plugin marketplace add rohitg00/awesome-claude-code-toolkit
Manual clone:
git clone https://github.com/rohitg00/awesome-claude-code-toolkit.git ~/.claude/plugins/claude-code-toolkit
One-liner:
curl -fsSL https://raw.githubusercontent.com/rohitg00/awesome-claude-code-toolkit/main/setup/install.sh | bash
Table of Contents
- Plugins (176+)
- Agents (135)
- Skills (35 curated + 28 community)
- Commands (42)
- Hooks (20 scripts)
- Rules (15)
- Templates (7)
- MCP Configs (14)
- Contexts (5)
- Examples (3)
- Companion Apps & GUIs
- Ecosystem
- Setup
- Resources
- Related Awesome Lists
- Contributing
Plugins
Over 176 production-ready plugins that extend Claude Code with domain-specific capabilities.
Featured
| Plugin | Stars | Description |
|---|---|---|
| pro-workflow | 1,800+ | Battle-tested Claude Code workflows from power users. Self-correcting memory, parallel worktrees, wrap-up rituals, 8 hook types, 5 agents, and the 80/20 AI coding ratio. Install: /plugin marketplace add rohitg00/pro-workflow |
| gstack | 68,200+ | Garry Tan's exact Claude Code setup: 6 opinionated tools that serve as CEO, Eng Manager, Release Manager, and QA Engineer. |
All Plugins
| Plugin | Description |
|---|---|
| agento-patronum | Protects sensitive files, credentials, and shell commands from unintended AI access via Claude Code hooks. Unlike settings.json deny rules, hooks are an enforcement layer you own and can verify. Ships with defaults for .env files, SSH keys, AWS credentials, and kubeconfig. |
| skills-janitor | Audit, deduplicate, check, fix, and track usage of your Claude Code skills. 9 slash commands, zero dependencies |
| great_cto | Full SDLC pipeline plugin with 7 agents (tech-lead, senior-dev, qa-engineer, security-officer, devops, l3-support, project-auditor), 12-angle code review, 10 project archetypes, 13 compliance frameworks (SOC2/HIPAA/PCI-DSS/GDPR/ISO 27001), two-gate approval flow. Opus 4.7 advisor escalation, file-based, MIT |
| aws-cost-saver | AWS cost optimization scanner with 173 automated checks, ML-powered rightsizing, and Zero Hallucination Pricing - Real result: 60% cost reduction |
| claude-agentic-coding-playbook | Evidence-based practices for LLM-assisted development -- hooks, skills, scripts, and a best-practices guide with 58 citations. Includes 19+ guard/lifecycle hooks, investigation workflow, fleet indexing, and claude-loop for autonomous task queues. |
| claude-code-mcp | Run Claude Code as a one-shot MCP server -- an agent in your agent. Permissions bypassed automatically. By Peter Steinberger. 1,100+ stars |
| claude-code-system-prompts | Extracted system prompts from Claude Code -- 18 builtin tool descriptions, sub-agent prompts, utility prompts. Updated for each release. 5,900+ stars |
| claude-context | Semantic code search MCP server by Zilliz (Milvus creators). Hybrid BM25 + dense vector search. ~40% token reduction. 5,600+ stars |
| claude-cost-optimizer | Installable cost-mode skill (30-60% cost savings, up to 70% in strict mode) + 10 guides, 10 templates, budget hooks. Install: npx skills add Sagargupta16/claude-cost-optimizer |
| fractal | Recursive project management for Claude Code. Decomposes goals into predicates, works the riskiest piece first, and re-evaluates as it learns |
| a11y-audit | Full accessibility audit with WCAG compliance checking |
| accessibility-checker | Scan for accessibility issues and fix ARIA attributes in web applications |
| adr-writer | Architecture Decision Records authoring and management |
| AgentLint | Lint your repo for AI agent compatibility. 33 evidence-backed checks across 5 dimensions. Claude Code plugin. |
| ai-prompt-lab | Improve and test AI prompts for better Claude Code interactions |
| analytics-reporter | Generate analytics reports and dashboard configurations from project data |
| android-developer | Android and Kotlin development with Jetpack Compose |
| api-architect | API design, documentation, and testing with OpenAPI spec generation |
| api-benchmarker | API endpoint benchmarking and performance reporting |
| api-reference | API reference documentation generation from source code |
| api-tester | Test API endpoints and run load tests against services |
| aws-helper | AWS service configuration and deployment automation |
| azure-helper | Azure service configuration and deployment automation |
| backend-architect | Backend service architecture design with endpoint scaffolding |
| bug-detective | Debug issues systematically with root cause analysis and execution tracing |
| Bouncer | Independent quality gate that uses Gemini to audit Claude Code's output. Includes Stop hook (automatic), quick audit skill, and deep audit with full tool access. One-liner install. |
| brooks-lint | AI code reviews grounded in six classic engineering books (Brooks, Fowler, Martin, McConnell, Hunt & Thomas, Evans). Diagnoses code across 6 decay risk dimensions with structured findings (Symptom → Source → Consequence → Remedy). Supports PR review, architecture audit, tech debt assessment, and test quality review. v0.6 adds Mermaid dependency graphs. |
| ccmanager | Coding agent session manager supporting Claude Code, Gemini CLI, Codex, Cursor, Copilot, Cline, OpenCode, Kimi CLI. Smart auto-approval via Haiku, devcontainer support. 940+ stars |
| ccpm | Project management using GitHub Issues + Git worktrees for parallel agent execution. Issue-analyze, epic-start, epic-merge commands. 7,600+ stars |
| ccusage | CLI for analyzing Claude Code/Codex usage from local JSONL files. Daily, monthly, session, billing-window reports. Offline, zero API calls. 11,500+ stars |
| cc-cost | Single-file Python CLI that parses Claude Code transcript JSONL and reports cost, prompt-cache hit rate, tool-call distribution, top expensive turns, and actionable optimization recommendations (--diagnose, --md, --top N). MIT, no third-party deps. |
| getburnd | Local-first cost-control CLI for Claude Code. Reads ~/.claude/projects/*.jsonl, identifies 8 leak patterns (verbose context, tool loops, large file re-reads), prints savings estimates, generates a shareable report URL. MIT, zero telemetry. |
| building-multiagent-systems | Architecture patterns for multi-agent systems: orchestrator-worker, pipeline, debate, and MapReduce topologies |
| bundle-analyzer | Frontend bundle size analysis and tree-shaking optimization |
| chief | CLI that wraps Claude Code in a loop. Define a PRD, run chief, go do anything else. Commits after each task, picks up where it left off. Homebrew installable. 380+ stars |
| claudebase | Back up, restore, and sync your Claude Code config (settings, skills, agents, hooks, rules, memory, MCP) to a private GitHub repo. Named profiles, secret scanning, multi-machine conflict detection, automatic backups. 158 tests |
| changelog-gen | Generate changelogs from git history with conventional commit parsing |
| changelog-writer | Detailed changelog authoring from git history and PRs |
| ci-debugger | Debug CI/CD pipeline failures and fix configurations |
| claude-hooks-mastery | Complete mastery guide for Claude Code hooks -- UV single-file Python scripts, sub-agents, meta-agent, team-based validation, AI-generated audio feedback. 3,300+ stars |
| claude-mem | Automatically captures everything Claude does, compresses with AI, injects relevant context into future sessions. SQLite + full-text search. 35,900+ stars |
| claude-notifications-go | Cross-platform smart notifications -- 6 types, click-to-focus, context analysis, webhooks. Single Go binary, zero deps. 340+ stars |
| claude-ops | Business operating system plugin for Claude Code. Morning briefings, unified inbox, autonomous PR merge, infrastructure monitoring, and YOLO autonomous mode. |
| claude-scaffold | npx CLI that deploys CLAUDE.md, hooks, and 18 domain skills to any repository in one command. Skills auto-activate via hooks based on project context. Cross-repo sync via update --all. Install: npx claude-scaffold init |
| claude-recap | Per-topic session memory using Shell hooks — archives each conversation topic as a separate Markdown summary. Two hooks, bash + Node.js, 100% local |
| clirank-mcp-server (npm) | API discovery for agents -- scores 210+ APIs on CLI-friendliness across 11 signals. Find the right API for any task via MCP tools or REST (curl "https://clirank.dev/api/discover?q=send+emails"). No auth required |
| /cht | Chat persistence for Claude Code — 13 slash commands + hooks for saving conversations as local markdown files. Crash-proof auto-save via hooks, project-based organization, search, and management. npm: @kosoukhov/cht-cli |
| claude-rank | SEO/GEO/AEO audit plugin — tells you why AI won't cite your site, then auto-fixes robots.txt, sitemap.xml, llms.txt, and JSON-LD. 170+ rules across 10 scanners, zero config |
| claude-sounds | Audio feedback for Claude Code hooks — 10 events, 21 sounds, random rotation. macOS (afplay). |
| claude-code-hooks | 15 production-tested hooks from 160+ hours of autonomous operation. Destructive command blocker, branch guard, syntax check, context monitor, permission auto-approver. Bash, zero deps |
| claude-code-sessions | Session intelligence plugin. 11 skills for full-text search, token analytics, task management, session comparison, timeline views, and context recovery across all sessions. Includes a web dashboard. Zero runtime dependencies, read-only |
| cc-aws-keepalive | Keep Claude Code sessions alive through AWS credential expiry -- proactive expiration warnings, credential refresh bypass for Bedrock SSO/SAML, optional statusline countdown timer. 4 hook scripts, zero dependencies |
| cc-safe-setup | One command (npx cc-safe-setup) to install 6 essential safety hooks in 10 seconds. Zero dependencies |
| knowledge-graph | Built on Anthropic internal engineering practices and Karpathy's AutoResearch methodology. A zero-dependency, git-native memory layer for Claude Code that persists learned context across sessions. Pure bash, ~3ms/event, privacy-first |
| claude-supermemory | Persistent memory across sessions and projects using Supermemory. User profile injection at session start, automatic conversation capture. 2,300+ stars |
| cortex | Persistent memory for Claude Code — neuroscience-backed retrieval with thermodynamic decay, backed by 41 published papers. PostgreSQL + pgvector + sentence-transformers. 6 lifecycle hooks (SessionStart, UserPromptSubmit, PostToolUse, SessionEnd, Notification, SubagentStart), hierarchical recall, causal chains, knowledge graph navigation. Install and forget. |
| code-architect | Generate architecture diagrams and technical design documents |
| code-explainer | Explain complex code and annotate files with inline documentation |
| code-guardian | Automated code review, security scanning, and quality enforcement |
| code-review-assistant | Automated code review with severity levels and actionable feedback |
| eliniscan | AI full codebase scanner. Opens a separate Claude session for every file — reads every line, misses nothing. Finds bugs, security, performance issues and auto-fixes. |
| codebase-documenter | Auto-document entire codebase with inline comments and API docs |
| codesight | CLI token optimizer and AI context generator. Scans codebases to extract routes, schema, components, and dependencies for Claude Code, Cursor, Copilot, Codex, and Windsurf. 9x–13x token reduction. Zero runtime dependencies. npx codesight |
| color-contrast | Color contrast checking and accessible color suggestions |
| commit-commands | Advanced commit workflows with smart staging and push automation |
| complexity-reducer | Reduce cyclomatic complexity and simplify functions |
| compliance-checker | Regulatory compliance verification for GDPR, SOC2, and HIPAA |
| content-creator | Technical content generation for blog posts and social media |
| context7-docs | Fetch up-to-date library documentation via Context7 for accurate coding |
| contract-tester | API contract testing with Pact for microservice compatibility |
| cozempic | ✨ v1.2.x — Self-updating now, atomic writes, strict session guard, zero false positives on team detection. 13 pruning strategies, Agent Team protection, MCP server, JSONL doctor. Install: /plugin marketplace add Ruya-AI/cozempic |
| create-worktrees | Git worktree management for parallel development workflows |
| cron-scheduler | Cron job configuration and schedule validation |
| css-cleaner | Find unused CSS and consolidate stylesheets |
| cup | ClickUp CLI for AI agents with task management, sprints, and time tracking |
| data-privacy | Data privacy implementation with PII detection and anonymization |
| database-optimizer | Database query optimization with index recommendations and EXPLAIN analysis |
| dead-code-finder | Find and remove dead code across the codebase |
| debug-session | Interactive debugging workflow with git bisect integration |
| dig2crawl | Universal web crawler with Claude-powered CSS selector discovery. 4-level AI extraction escalation (CSS, browser actions, Claude Vision, captcha). Rust. |
| dependency-manager | Audit, update, and manage project dependencies with safety checks |
| deploy-pilot | Deployment automation with Dockerfile generation, CI/CD pipelines, and infrastructure as code |
| desktop-app | Desktop application scaffolding with Electron or Tauri |
| devops-automator | DevOps automation scripts for CI/CD, health checks, and deployments |
| discuss | Debate implementation approaches with structured pros and cons analysis |
| claw-army/claude-node | Python subprocess bridge for Claude Code CLI, giving Python code direct access to Claude Code native capabilities via stream-json |
| discoclaw | Personal AI orchestrator that bridges Discord to Claude Code with durable memory, task tracking, and cron-based automation |
| jarvis | Turns an idle Claude Max subscription into a 24/7 AI ops system — Discord bot, 76 scheduled tasks, 12 AI teams, local LanceDB RAG, 98% context compression via Nexus CIG, and 4-layer self-healing infrastructure. Uses claude -p headless mode at $0 extra cost. |
| jarvis-company-board | Real-time AI agent collaboration board built on Next.js 15 and SQLite WAL — 8 named AI board members debate decisions via SSE push, with a DEV task approval workflow and Railway deploy support. |
| dna-claude-analysis | Personal genome analysis toolkit that analyzes raw DNA data across 17 categories and generates a terminal-style HTML dashboard |
| codetape | The flight recorder for AI coding — auto-records semantic traces and syncs README, CHANGELOG, CLAUDE.md. Zero deps. npx codetape init |
| doc-forge | Documentation generation, API docs, and README maintenance |
| docker-helper | Build optimized Docker images and improve Dockerfile best practices |
| double-check | Verify code correctness with systematic second-pass analysis |
| e2e-runner | End-to-end test execution and recording for web applications |
| embedding-manager | Manage vector embeddings and similarity search |
| env-manager | Set up and validate environment configurations across environments |
| env-sync | Environment variable syncing and diff across environments |
| experiment-tracker | ML experiment tracking with metrics logging and run comparison |
| explore | Smart codebase exploration with dependency mapping and structure analysis |
| faf-skills | 31 Claude Code skills for persistent project context (.faf, application/vnd.faf+yaml). Scoring, sync, testing, publishing, MCP server creation, architecture docs. Anthropic MCP #2759. |
| feature-dev | Full feature development workflow from spec to completion |
| fractal | Recursive project management plugin. Decomposes any goal into verifiable predicates, works on the riskiest unknown first. Features /fractal:run (idempotent state machine), /fractal:init, /fractal:patch, dry run mode, and incremental decomposition with re-evaluation. |
| finance-tracker | Development cost tracking with time estimates and budget reporting |
| fix-github-issue | Auto-fix GitHub issues by analyzing issue details and implementing solutions |
| fix-pr | Fix PR review comments automatically with context-aware patches |
| flutter-mobile | Flutter app development with widget creation and platform channels |
| frontend-developer | Frontend component development with accessibility and responsive design |
| gcp-helper | Google Cloud Platform service configuration and deployment |
| gate4agent | Universal Rust transport for CLI AI agents (Claude Code, Codex, Gemini, OpenCode). Pipe/NDJSON, PTY, and ACP modes. Published on crates.io. |
| git-flow | Git workflow management with feature branches, releases, and hotfix flows |
| github-issue-manager | GitHub issue triage, creation, and management |
| harness-evolver | LangSmith-native autonomous agent optimization. Multi-agent proposers evolve prompts, routing, tools, and architecture in isolated git worktrees. Install: npx harness-evolver@latest |
| helm-charts | Helm chart generation and upgrade management |
| idle-timing | Injects hidden timing context (local time with UTC offset, idle seconds since last reply, previous-turn duration) into every user prompt so the model knows how long the conversation has been paused. Ships a statusline fragment for a live elapsed-time readout and a visible [after Xm Ys] note when you return from >10s idle. 57 tests, dual Unlicense/CC0. |
| immich-photo-manager | Turn your self-hosted Immich photo library into a conversation — natural language search, geographic album curation, duplicate detection via perceptual hashing, library health audits, and interactive HTML galleries. 22 MCP tools, 11 skills, 5 slash commands |
| import-organizer | Organize, sort, and clean import statements |
| infrastructure-maintainer | Infrastructure maintenance with security audits and update management |
| ios-developer | iOS and Swift development with SwiftUI views and models |
| k8s-helper | Generate Kubernetes manifests and debug pod issues with kubectl |
| leapfrog-mcp | Multi-session browser MCP server -- 15 parallel isolated Chromium sessions so multiple Claude Code terminals can browse simultaneously. 37 tools for navigation, extraction, interaction, network interception, and session profiles. 797 tests. Install: npx -y leapfrog-mcp |
| license-checker | License compliance checking and NOTICE file generation |
| lighthouse-runner | Run Lighthouse audits and fix performance issues |
| lightcms | AI-native CMS with 41 MCP tools for managing websites through natural language — pages, templates, assets, themes, collections, redirects, and more with full content versioning |
| linear-helper | Linear issue tracking integration and workflow management |
| load-tester | Load and stress testing for APIs and web services |
| memory-profiler | Memory leak detection and heap analysis |
| migrate-tool | Generate database migrations and code migration scripts for framework upgrades |
| migration-generator | Database migration generation and rollback management |
| model-context-protocol | MCP server development helper with tool and resource scaffolding |
| model-evaluator | Evaluate and compare ML model performance metrics |
| monitoring-setup | Monitoring and alerting configuration with dashboard generation |
| monorepo-manager | Manage monorepo packages with affected detection and version synchronization |
| mutation-tester | Mutation testing to measure test suite quality |
| myclaude | Multi-agent orchestration routing tasks to Claude Code, Codex, Gemini, and OpenCode based on complexity. OmO skill for intelligent routing. 2,400+ stars |
| nimbalyst | Visual workspace for building with Codex and Claude Code. Session and task manager. Visual editing |
| n8n-workflow | Generate n8n automation workflows from natural language descriptions |
| nexus-agents | Intelligent orchestration platform routing tasks to Claude, Gemini, Codex, and OpenCode via Budget→TOPSIS→LinUCB composite router. 30 MCP tools (orchestrate, consensus voting, research pipelines), 12 expert agents, 17 skills, plugin-native /agents + hooks. Install: /plugin marketplace add williamzujkowski/nexus-agents |
| onboarding-guide | New developer onboarding documentation generator |
| oh-my-claudecode | Teams-first multi-agent orchestration. 19 specialized agents, 28 skills. Full autonomous execution, Socratic questioning, N coordinated agents. 9,900+ stars |
| onWatch | Open-source Go CLI that tracks AI API quota usage across 7 providers (Synthetic, Z.ai, Anthropic, Codex, GitHub Copilot, MiniMax, Antigravity) with a background daemon (<50 MB RAM), zero telemetry, and a Material Design 3 web dashboard |
| obey | Rule enforcement plugin. Save rules with natural language, enforce with 17 lifecycle hooks. Three scopes (global, stack-specific, project-local), active blocking via PreToolUse, completion checklists via Stop hook, audit trail, auto-detects rule-like language. Cross-platform. |
| opcode | Tauri 2 desktop GUI and toolkit for Claude Code. Manage sessions, create custom agents with visual editor, usage analytics, MCP integration. 21,000+ stars |
| openapi-expert | OpenAPI spec generation, validation, and client code scaffolding |
| optimize | Code optimization for performance and bundle size reduction |
| ORCH | CLI runtime orchestrating Claude Code, Codex, and Cursor as typed agent teams with state machine (todo→review→done), auto-retry, inter-agent messaging, goals, and TUI dashboard |
| oss-autopilot | Open source contribution manager — tracks PRs across repos, discovers issues, diagnoses CI failures, drafts maintainer responses. 7 agents, interactive commands, MCP server. Install: /plugin marketplace add costajohnt/oss-autopilot |
| paco-framework | 1+ |
| peon-ping | Warcraft III Peon voice notifications (+ StarCraft, Portal, Zelda) for Claude Code and other agents. Desktop banners, auto-detects SSH/devcontainers. 3,900+ stars |
| perf-profiler | Performance analysis, profiling, and optimization recommendations |
| performance-monitor | Profile API endpoints and run benchmarks to identify performance bottlenecks |
| plan | Structured planning with risk assessment and time estimation |
| preflight | 24-tool MCP server that catches vague prompts before they cost 2-3x in wrong→fix cycles. 12-category scorecards, correction pattern learning, cross-service contract awareness, session history search with LanceDB vectors, and cost estimation. npx preflight-dev |
| pr-reviewer | Review pull requests with structured analysis and approve with confidence |
| product-shipper | Ship features end-to-end with launch checklists and rollout plans |
| production-grade | 14-agent autonomous pipeline — PM, Architect, Backend, Frontend, QA, Security, Code Review, DevOps, SRE, Data Scientist, Technical Writer, Skill Maker, Polymath co-pilot. Two-wave parallel execution, brownfield-safe. |
| product-org-os | 150+ skills and 12 role-based agents (CPO, VP Product, PM, PMM, BizOps, CI, and more) modeling a full product org. Two gateways: /product auto-routes to the right agent, /plt runs a multi-stakeholder leadership meeting. MIT. claude plugins install github:yohayetsion/product-org-os |
| project-scaffold | Scaffold new projects and add features with best-practice templates |
| prompt-optimizer | Analyze and optimize AI prompts for better results |
| pulse | Local Channel plugin — push notifications into Claude Code sessions via HTTP POST. No Discord/Slack needed, just curl. Three levels (info/warn/error), source tracking, dedup. |
| PUIUX Pilot | Auto-configures Claude Code hooks, MCPs, and skills for any project. Scans 95+ project types, selects from 28+ hooks, scores quality (0-100), translates configs across AI tools. Safe: dry-run, atomic writes, backup + rollback. |
| python-expert | Python-specific development with type hints and idiomatic refactoring |
| pulser | Diagnostic CLI for Claude Code SKILL.md files — scans 8 rules, auto-classifies, prescribes fixes with templates, --fix with rollback |
| query-optimizer | SQL query optimization and execution plan analysis |
| rag-builder | Build Retrieval-Augmented Generation pipelines |
| rapid-prototyper | Quick prototype scaffolding with minimal viable structure |
| reporecall | Local codebase memory for Claude Code. Tree-sitter AST indexing (22 languages), hybrid keyword + vector search, call-graph traversal, hooks + MCP. Injects relevant context in ~5ms before Claude starts thinking. npm: @proofofwork-agency/reporecall |
| react-native-dev | React Native mobile development with platform-specific optimizations |
| readme-generator | Smart README generation from project analysis |
| refactor-engine | Extract functions, simplify complex code, and reduce cognitive complexity |
| regex-builder | Build, test, and debug regular expression patterns |
| release-manager | Semantic versioning management and automated release workflows |
| responsive-designer | Responsive design implementation and testing |
| review-squad | Multi-perspective code review via dispatched subagent panels: experts, normie users, pedantic nitpickers, and real-user task runners |
| schema-designer | Database schema design and ERD generation |
| screen-reader-tester | Screen reader compatibility testing and ARIA fixes |
| security-guidance | Security best practices advisor with vulnerability detection and fixes |
| seed-generator | Database seeding script generation with realistic data |
| sitemd | Build websites from Markdown via MCP. 22 tools for creating pages, generating content, configuring settings, running SEO audits, and deploying static sites to Cloudflare Pages |
| simmer | Iterative artifact refinement using judge subagents that score against user-defined criteria across multiple rounds |
| slack-notifier | Slack integration for deployment and build notifications |
| smart-commit | Intelligent git commits with conventional format, semantic analysis, and changelog generation |
| sprint-prioritizer | Sprint planning with story prioritization and capacity estimation |
| technical-sales | Technical demo creation and POC proposal writing |
| the-pragmatic-pm | PM leadership toolkit with 43 skills, 5 agents, 4 workflows. Covers PRD generation, OKR lifecycle, pricing, AI pricing, positioning, sales enablement, and quarterly planning. |
| terraform-helper | Terraform module creation and infrastructure planning |
| test-data-generator | Generate realistic test data and seed databases |
| test-kitchen | Parallel implementation exploration using competing subagents, with structured comparison and winner selection |
| test-results-analyzer | Analyze test failures, identify patterns, and suggest targeted fixes |
| test-writer | Generate comprehensive unit and integration tests with full coverage |
| tool-evaluator | Evaluate and compare developer tools with structured scoring criteria |
| type-migrator | Migrate JavaScript files to TypeScript with proper types |
| ui-designer | Implement UI designs from specs with pixel-perfect component generation |
| ultrathink | Deep analysis mode with extended reasoning for complex problems |
| unit-test-generator | Generate comprehensive unit tests for any function or module |
| update-branch | Rebase and update feature branches with conflict resolution |
| vision-specialist | Image and visual analysis with screenshot interpretation and text extraction |
| vibe-kanban | Kanban-based orchestration for 10+ coding agents (Claude Code, Codex, Gemini CLI, Copilot, Amp). Isolated git worktrees per agent, inline diff review. 23,200+ stars |
| VibeGuard | Stop AI from hallucinating code. 88 rules + 13 hooks + 14 agents for real-time interception and static scanning across 5 languages |
| visual-regression | Visual regression testing with screenshot comparison |
| wshobson/agents | 112 specialized agents, 16 multi-agent workflow orchestrators, 146 skills, 79 tools in 72 focused plugins. 31,300+ stars |
| web-dev | Full-stack web development with app scaffolding and page generation |
| whatsapp-claude-plugin | WhatsApp channel plugin for Claude Code -- connects as a linked device via Baileys v7 with bidirectional messaging, full media support, voice transcription, permission relay, and access control |
| workflow-optimizer | Development workflow analysis and optimization recommendations |
| background-timer | Background timer with task notifications -- set delayed checks without blocking conversation |
| claude-sounds | Audio feedback for Claude Code hooks -- 10 events, 21 sounds, random rotation, customizable (macOS) |
| notch-so-good | Pixel-art crab (Chawd) lives in your Mac's notch and watches Claude Code for you. Live session timers, color-coded notifications, 13 idle animations, mouse-reactive eyes, drowsiness system. Universal binary, one-line install: npx notch-so-good. MIT, 130+ users |
| codebase-graph | Code intelligence MCP server — 42-language tree-sitter AST parsing, FalkorDB knowledge graphs, 0.944 MRR search quality. npm: @anthropic/codegraph |
| ESP32-AI-Agent-Skill | Expert ESP32 embedded systems plugin — chip selection across 9 variants, GPIO validation with anti-bricking safety, Arduino/ESP-IDF code gen, LVGL v8–v9.5 refs, 60+ Waveshare board pinouts. Install: claude /install-plugin https://github.com/ezrover/ESP32-AI-Agent-Skill |
| toprank | SEO + Google Ads plugin for Claude Code. Pulls real Search Console data and Google Ads API data, audits traffic and wasted ad spend, rewrites meta tags, generates JSON-LD schema, and ships the fixes. 9 skills across SEO, Ads, and cross-model review |
| sniff-qa | AI-powered QA tool — 8 checks in one command. Source scanning (dead links, API endpoints, debug statements, broken imports), accessibility (axe-core), visual regression (pixelmatch), performance (Lighthouse), AI exploration, source/browser cross-referencing. MCP server included. 213 tests, Apache 2.0 |
| humanizer-skill | Detects 37 AI writing patterns and rewrites text with human rhythm. 5 voice profiles (casual, professional, technical, warm, blunt). Based on burstiness/perplexity research. Zero dependencies |
| ui-ux-suite | Design audit across 12 dimensions — color contrast, typography, layout, accessibility. Scans CSS, JSX, Tailwind configs. Quantified scores (1-10) with before/after fix code. WCAG 2.1, APCA, OKLCH. Zero deps |
| claude-cybersecurity | AI-powered cybersecurity code review with 8 parallel agents. OWASP 2025, CWE Top 25, MITRE ATT&CK, 11 languages, 5 compliance frameworks, threat intelligence. Zero config. MIT |
| Clarvia MCP | MCP quality scanner — scans any MCP server, returns AEO (Agent Engine Optimization) score. Indexes 27,843+ tools for instant lookup. 24 MCP tools (search, scan, compare, leaderboard, trending). npx -y clarvia-mcp-server |
| OraClaw | Decision intelligence MCP server — 12 tools with 19 ML algorithms (multi-armed bandits, constraint solvers, forecasters, risk models, Q-learning, A*, simulated annealing). Sub-25ms responses, deterministic, 945 tests. npx @oraclaw/mcp-server |
| US Business Data MCP | MCP server for US business data — search entities across 17 state Secretary of State databases, YellowPages leads, building permits from 47 cities, 20+ federal APIs (SEC, FDA, FEMA). Built in Go, on MCP Registry |
| craft-statusline | Bash statusline plugin for Claude Code with state-aware git branch (ahead / behind / stashed / conflict / combined signals), context window with absolute-token traffic light (yellow at 400k tokens, red at 85%), 5h/7d rate limits, and optional cost. Bash 3.2 compatible, jq is the only dependency. Install: /plugin marketplace add derjochenmeyer/claude-code-craft-statusline |
| mobile-spine | Scaffold for mobile teams whose Android, iOS, and Backend live in separate repos. Coordinates 4 specialized subagents (api / pm / android / ios) with hard repo boundaries via settings.json deny rules. /mobile-spine:init runs a 6-question interview and writes the full workspace; /feat drives a 4-question interview → 4-case classification (existing endpoint / new endpoint / new domain / backend not built). 4-class codebase inventory contract surfaced in every PR (Inventory: reuse X / extend Y / new Z / remove W). MIT. |
| debian-packaging-agent-skill | Debian packaging skill covering debhelper, debian/rules, package metadata, lintian, and multi-binary packages for Ruby (gem2deb), Python (pybuild), Rust (debcargo), and Go (dh-golang). Loads language-specific reference docs on demand. Apache 2.0 |
| unslop | Removes AI writing tells (tricolons, em-dash pileups, hedging stacks, sycophancy openers, stock vocabulary). Split lint/rewrite modes — run detection-only passes on your own text without rewriting. Five intensity levels. MIT licensed |
| tailtest | Automatically generates and runs tests for every file Claude Code creates or modifies. PostToolUse hook detects changes, generates scenarios, runs them, and surfaces failures. 8 languages (Python, TypeScript, JavaScript, Go, Ruby, PHP, Java, Rust). Zero config, zero commands. |
| dodo-agent-plugin | Official Dodo Payments plugin: 8 integration skills (checkout, subscriptions, webhooks, usage-based billing, credits, license keys, BillingSDK, best practices) and 2 MCP servers (live API via browser OAuth + docs search, no auth). Multi-agent: Claude Code, Codex, Cursor, OpenCode |
| claude-time | Live local time + timezone injected into every prompt via UserPromptSubmit hook. Stops Claude from saying "tonight" at 9 AM. Also stamps every response with [HH:MM AM/PM TZ] so you can see when each message landed (useful when tasks stall). Zero config, zero deps beyond jq. MIT |
| ejentum-mcp | Reasoning Harness for agentic AI: 4 MCP tools (reasoning, code, anti-deception, memory) over 679 engineered cognitive operations. Each call returns a structured scaffold the calling LLM ingests before its first token. Catches sycophancy, hallucination, and reasoning decay before they emerge. Companion skills/ directory ships SKILL.md files for autonomous routing in Claude Code. MIT, free tier 100 calls. |
| claude-forge | "oh-my-zsh for Claude Code". Complete toolkit: 11 agents, 33 commands, 24 skills, 15 hooks (covering 21 lifecycle events) + 9 opt-in examples, 9 rules, 4 MCP servers (playwright, context7, jina-reader, chrome-devtools@0.23.0), statusLine. One install via curl ... install.sh or /plugin marketplace add sangrokjung/claude-forge. Includes TDD workflow, multi-reviewer pipeline (codex/gemini/security/architect), Chrome DevTools Lighthouse audits, 4-way independent skeptical review. Submitted to anthropics/claude-plugins-official. MIT. |
| repo-visuals | Designs bespoke GitHub README hero visuals — animated GIF or static PNG — through a structured discovery dialog. Retina capture via Puppeteer + ffmpeg. Heroes merged into HTMLHint, Terminal.Gui, ast-graph. |
| weft | Deterministic workflow tracking with event-sourced state — templates with skill chains, bounded loops, and per-step tool guards. Hooks block out-of-order tool calls; state survives compaction via an append-only event log. Stdlib-only Python core, 191 tests, MIT. Install: /plugin marketplace add dioptx/weft |
| magic-cc-codex-worker | Turns OpenAI Codex into a pool of parallel agent workers for Claude Code. Each worker runs in its own git worktree to isolate concurrent edits. Resumable sessions, dual-model PR review (PR materialized in a detached worktree for the reviewer), role-based specialization (implementer/reviewer/planner), delegation-level knob (minimal/balance/max), bundled single-file MCP server. 9 slash commands, 3 subagents, 62 unit tests, CI on Node 20/22. Install: /plugin marketplace add wenqingyu/magic-cc-codex-worker then /plugin install magic-codex@magic-codex. License: PolyForm Noncommercial 1.0.0 (free for independent devs / research / nonprofits; commercial use requires separate license) |
| notify | Cross-platform system notifications for Claude Code hooks — macOS (terminal-notifier) and Linux (notify-send). Duration filtering to suppress noisy short events, git context extraction (repo + branch), and contextual messages per hook type. MIT |
| claude-snapshot | Portable Claude Code setup snapshots — export your settings, plugins, hooks, CLAUDE.md, and MCP configs as a .tar.gz, diff before applying, and restore on another machine in under 2 minutes. No network, no daemon, .bak safety on every apply. Node.js 18+, cross-platform (macOS + Linux). Install: /plugin marketplace add adhenawer/claude-snapshot |
| ashlr-plugin | Open-source Claude Code plugin replacing the built-in Read/Grep/Edit/Bash tools with token-efficient versions backed by @ashlr/core-efficiency. Independently benchmarked at 57% token reduction on real codebases. 70+ tools across glob, grep, structural diff/edit, and an opt-in genome (LSP-style codebase index). Install: curl -fsSL plugin.ashlr.ai/install.sh \| bash |
| temporal-core | Make Claude Code agents feel time pass — research-backed temporal awareness via 3 hooks (SessionStart + UserPromptSubmit + PreToolUse) that inject session elapsed and since last action signals into context. Bundled skill teaches pacing/deadline reasoning. Aher et al. 2026: explicit time surfacing → 6× deadline performance. Apache-2.0, zero runtime deps. |
| nirecom/agents | Self-driving Claude Code + GitHub Copilot framework with hook-enforced workflow state machine (research → plan → tests → code → security-review → docs), private-info scanning (AWS/Anthropic keys, PEM certs, RFC 1918 IPs), three-stage planning with adversarial Codex review, OWASP-backed test categories, and cross-machine session sync. Windows-native (PowerShell-first) with Linux/macOS support. |
| claude-channel-instagram | Instagram Graph API bridge for Claude Code -- comments, DMs, comment-to-DM bootstrap, audio transcription, pluggable extensions system. Official Meta API (no scraping). Apache-2.0, by RIA Systems (verified Meta Tech Provider). Landing: claude-plugins.riasistemas.com.br/instagram. Install: /plugin marketplace add riasistemas/claude-plugins then /plugin install instagram@riasistemas |
| claude-channel-whatsapp | Official WhatsApp Business Cloud API bridge for Claude Code -- webhooks, OGG Opus audio, allowlist + permission relay scrubbing secrets. NOT Baileys/scraping -- uses Meta's official API with WABA tokens. Apache-2.0, by RIA Systems (verified Meta Tech Provider). Landing: claude-plugins.riasistemas.com.br/whatsapp. Install: /plugin marketplace add riasistemas/claude-plugins then /plugin install whatsapp@riasistemas |
| axme-code | Persistent project memory across sessions, architectural decisions with enforce levels, and pre-execution safety hooks that block dangerous commands at the harness level (not via prompts). Local-only storage, multi-repo workspace support, automatic knowledge extraction via background auditor. 100% on ToolEmu safety, 89% on LongMemEval at ~10x fewer tokens than competitors. |
| logic-lens | Logic-first code review plugin for Claude Code — detects behavioral bugs via semi-formal execution tracing. Finds logic errors linters and type checkers miss. Structured findings: Premises → Trace → Divergence → Remedy with L1–L6 risk codes. Six skills: logic-review, logic-explain, logic-diff, logic-locate, logic-health, logic-fix-all. |
Installing a Plugin
/plugin install claude-code-toolkit@smart-commit
Or install all plugins at once:
/plugin install claude-code-toolkit
Agents
One hundred thirty-five specialized agents organized into ten categories. Each agent defines a persona, system instructions, and tool access patterns.
Core Development (13 agents)
| Agent | File | Purpose |
|---|---|---|
| Fullstack Engineer | fullstack-engineer.md | End-to-end feature delivery across frontend, backend, and database |
| API Designer | api-designer.md | RESTful API design with OpenAPI, versioning, and pagination |
| Frontend Architect | frontend-architect.md | Component architecture, state management, performance |
| Mobile Developer | mobile-developer.md | Cross-platform mobile with React Native and Flutter |
| Backend Developer | backend-developer.md | Node.js/Express/Fastify backend services |
| GraphQL Architect | graphql-architect.md | Schema design, resolvers, federation, DataLoader |
| Microservices Architect | microservices-architect.md | Distributed systems, event-driven, saga patterns |
| WebSocket Engineer | websocket-engineer.md | Real-time communication, Socket.io, scaling |
| UI Designer | ui-designer.md | UI/UX implementation, design systems, Figma-to-code |
| Electron Developer | electron-developer.md | Electron desktop apps, IPC, native OS integration |
| API Gateway Engineer | api-gateway-engineer.md | API gateway patterns, rate limiting, auth proxies |
| Monorepo Architect | monorepo-architect.md | Turborepo/Nx workspace strategies, dependency graphs |
| Event-Driven Architect | event-driven-architect.md | Event sourcing, CQRS, message queues, distributed events |
Language Experts (25 agents)
| Agent | File | Purpose |
|---|---|---|
| TypeScript | typescript-specialist.md | Type-safe patterns, generics, module design |
| Python | python-engineer.md | Pythonic patterns, packaging, async |
| Rust | rust-systems.md | Ownership, lifetimes, trait design |
| Go | golang-developer.md | Interfaces, goroutines, error handling |
| Next.js | nextjs-developer.md | App Router, RSC, ISR, server actions |
| React | react-specialist.md | React 19, hooks, state management |
| Django | django-developer.md | Django 5+, DRF, ORM optimization |
| Rails | rails-expert.md | Rails 7+, Hotwire, ActiveRecord |
| Java | java-architect.md | Spring Boot 3+, JPA, microservices |
| Kotlin | kotlin-specialist.md | Coroutines, Ktor, multiplatform |
| Flutter | flutter-expert.md | Flutter 3+, Dart, Riverpod |
| C# | csharp-developer.md | .NET 8+, ASP.NET Core, EF Core |
| PHP | php-developer.md | PHP 8.3+, Laravel 11, Eloquent |
| Elixir | elixir-expert.md | OTP, Phoenix LiveView, Ecto |
| Angular | angular-architect.md | Angular 17+, signals, standalone components |
| Vue | vue-specialist.md | Vue 3, Composition API, Pinia, Nuxt |
| Svelte | svelte-developer.md | SvelteKit, runes, form actions |
| Swift | swift-developer.md | SwiftUI, iOS 17+, Combine, structured concurrency |
| Scala | scala-developer.md | Akka actors, Play Framework, Cats Effect |
| Haskell | haskell-developer.md | Pure FP, monads, type classes, GHC extensions |
| Lua | lua-developer.md | Game scripting, Neovim plugins, LuaJIT |
| Zig | zig-developer.md | Systems programming, comptime, allocator strategies |
| Clojure | clojure-developer.md | REPL-driven development, Ring/Compojure, ClojureScript |
| OCaml | ocaml-developer.md | Type inference, pattern matching, Dream framework |
| Nim | nim-developer.md | Metaprogramming, GC strategies, C/C++ interop |
Infrastructure (11 agents)
| Agent | File | Purpose |
|---|---|---|
| Cloud Architect | cloud-architect.md | AWS, GCP, Azure provisioning and IaC |
| DevOps Engineer | devops-engineer.md | CI/CD, containerization, monitoring |
| Database Admin | database-admin.md | Schema design, query tuning, replication |
| Platform Engineer | platform-engineer.md | Internal developer platforms, service catalogs |
| Kubernetes Specialist | kubernetes-specialist.md | Operators, CRDs, service mesh, Istio |
| Terraform Engineer | terraform-engineer.md | IaC, module design, state management, multi-cloud |
| Network Engineer | network-engineer.md | DNS, load balancers, CDN, firewall rules |
| SRE Engineer | sre-engineer.md | SLOs, error budgets, incident response, postmortems |
| Deployment Engineer | deployment-engineer.md | Blue-green, canary releases, rolling updates |
| Security Engineer | security-engineer.md | IAM policies, mTLS, secrets management, Vault |
| Incident Responder | incident-responder.md | Incident triage, runbooks, communication, recovery |
Quality Assurance (10 agents)
| Agent | File | Purpose |
|---|---|---|
| Code Reviewer | code-reviewer.md | PR review with security and performance focus |
| Test Architect | test-architect.md | Test strategy, pyramid, coverage targets |
| Security Auditor | security-auditor.md | Vulnerability scanning, OWASP compliance |
| Performance Engineer | performance-engineer.md | Load testing, profiling, optimization |
| Accessibility Specialist | accessibility-specialist.md | WCAG compliance, ARIA, screen readers |
| Chaos Engineer | chaos-engineer.md | Chaos testing, fault injection, resilience validation |
| Penetration Tester | penetration-tester.md | OWASP Top 10 assessment, vulnerability reporting |
| QA Automation | qa-automation.md | Test automation frameworks, CI integration |
| Compliance Auditor | compliance-auditor.md | SOC 2, GDPR, HIPAA compliance checking |
| Error Detective | error-detective.md | Error tracking, stack trace analysis, root cause ID |
Data & AI (15 agents)
| Agent | File | Purpose |
|---|---|---|
| AI Engineer | ai-engineer.md | AI application integration, RAG, agents |
| ML Engineer | ml-engineer.md | ML pipelines, training, evaluation |
| Data Scientist | data-scientist.md | Statistical analysis, visualization |
| Data Engineer | data-engineer.md | ETL pipelines, Spark, data warehousing |
| LLM Architect | llm-architect.md | Fine-tuning, model selection, serving |
| Prompt Engineer | prompt-engineer.md | Prompt optimization, structured outputs |
| MLOps Engineer | mlops-engineer.md | Model serving, monitoring, A/B testing |
| NLP Engineer | nlp-engineer.md | NLP pipelines, embeddings, classification |
| Database Optimizer | database-optimizer.md | Query optimization, indexing, partitioning |
| Computer Vision | computer-vision-engineer.md | Image classification, object detection, PyTorch |
| Recommendation Engine | recommendation-engine.md | Collaborative filtering, content-based, hybrid |
| ETL Specialist | etl-specialist.md | Data pipelines, schema evolution, data quality |
| Vector DB Engineer | vector-database-engineer.md | FAISS, Pinecone, Qdrant, Weaviate, embeddings |
| Data Visualization | data-visualization.md | D3.js, Chart.js, Matplotlib, Plotly dashboards |
| Feature Engineer | feature-engineer.md | Feature stores, pipelines, encoding strategies |
| AutoResearch Agent | autoresearch-agent.md | ML experiment automation via tree search, code optimization |
Developer Experience (15 agents)
| Agent | File | Purpose |
|---|---|---|
| CLI Developer | cli-developer.md | CLI tools with Commander, yargs, clap |
| DX Optimizer | dx-optimizer.md | Developer experience, tooling, ergonomics |
| Documentation Engineer | documentation-engineer.md | Technical writing, API docs, guides |
| Build Engineer | build-engineer.md | Build systems, bundlers, compilation |
| Dependency Manager | dependency-manager.md | Dependency audit, updates, lockfiles |
| Refactoring Specialist | refactoring-specialist.md | Code restructuring, dead code removal |
| Legacy Modernizer | legacy-modernizer.md | Legacy codebase migration strategies |
| MCP Developer | mcp-developer.md | MCP server and tool development |
| Tooling Engineer | tooling-engineer.md | ESLint, Prettier, custom tooling |
| Git Workflow Manager | git-workflow-manager.md | Branching strategies, CI, CODEOWNERS |
| API Documentation | api-documentation.md | OpenAPI/Swagger, Redoc, interactive examples |
| Monorepo Tooling | monorepo-tooling.md | Changesets, workspace deps, version management |
| VS Code Extension | vscode-extension.md | LSP integration, custom editors, webview panels |
| Testing Infrastructure | testing-infrastructure.md | Test runners, CI splitting, flaky test management |
| Developer Portal | developer-portal.md | Backstage, service catalogs, self-service infra |
Specialized Domains (15 agents)
| Agent | File | Purpose |
|---|---|---|
| Blockchain Developer | blockchain-developer.md | Smart contracts, Solidity, Web3 |
| Game Developer | game-developer.md | Game logic, ECS, state machines |
| Embedded Systems | embedded-systems.md | Firmware, RTOS, hardware interfaces |
| Fintech Engineer | fintech-engineer.md | Financial systems, compliance, precision |
| IoT Engineer | iot-engineer.md | MQTT, edge computing, digital twins |
| Payment Integration | payment-integration.md | Stripe, PCI DSS, 3D Secure |
| SEO Specialist | seo-specialist.md | Structured data, Core Web Vitals |
| E-Commerce Engineer | e-commerce-engineer.md | Cart, inventory, order management |
| Healthcare Engineer | healthcare-engineer.md | HIPAA, HL7 FHIR, medical data pipelines |
| Real Estate Tech | real-estate-tech.md | MLS integration, geospatial search, valuations |
| Education Tech | education-tech.md | LMS, SCORM/xAPI, adaptive learning, assessments |
| Media Streaming | media-streaming.md | HLS/DASH, transcoding, CDN, adaptive bitrate |
| Geospatial Engineer | geospatial-engineer.md | PostGIS, spatial queries, mapping APIs, tiles |
| Robotics Engineer | robotics-engineer.md | ROS2, sensor fusion, motion planning, SLAM |
| Voice Assistant | voice-assistant.md | STT, TTS, dialog management, Alexa/Google |
Business & Product (12 agents)
| Agent | File | Purpose |
|---|---|---|
| Product Manager | product-manager.md | PRDs, user stories, RICE prioritization |
| Technical Writer | technical-writer.md | Documentation, style guides |
| UX Researcher | ux-researcher.md | Usability testing, survey design |
| Project Manager | project-manager.md | Sprint planning, Agile, task tracking |
| Scrum Master | scrum-master.md | Ceremonies, velocity, retrospectives |
| Business Analyst | business-analyst.md | Requirements analysis, process mapping |
| Content Strategist | content-strategist.md | SEO content, editorial calendars, topic clustering |
| Growth Engineer | growth-engineer.md | A/B testing, analytics, funnel optimization |
| Customer Success | customer-success.md | Ticket triage, knowledge base, health scoring |
| Sales Engineer | sales-engineer.md | Technical demos, POCs, integration guides |
| Legal Advisor | legal-advisor.md | ToS, privacy policies, software licenses |
| Marketing Analyst | marketing-analyst.md | Campaign analysis, attribution, ROI tracking |
Orchestration (8 agents)
| Agent | File | Purpose |
|---|---|---|
| Task Coordinator | task-coordinator.md | Routes work between agents, manages handoffs |
| Context Manager | context-manager.md | Context compression, session summaries |
| Workflow Director | workflow-director.md | Multi-agent pipeline orchestration |
| Agent Installer | agent-installer.md | Install and configure agent collections |
| Knowledge Synthesizer | knowledge-synthesizer.md | Compress info, build knowledge graphs |
| Performance Monitor | performance-monitor.md | Track token usage, measure response quality |
| Error Coordinator | error-coordinator.md | Handle errors across multi-agent workflows |
| Multi-Agent Coordinator | multi-agent-coordinator.md | Parallel agent execution, merge outputs |
Research & Analysis (11 agents)
| Agent | File | Purpose |
|---|---|---|
| Research Analyst | research-analyst.md | Technical research, evidence synthesis |
| Competitive Analyst | competitive-analyst.md | Market positioning, feature comparison |
| Trend Analyst | trend-analyst.md | Technology trend forecasting |
| Data Researcher | data-researcher.md | Data analysis, pattern recognition |
| Search Specialist | search-specialist.md | Information retrieval, source evaluation |
| Patent Analyst | patent-analyst.md | Patent searches, prior art, IP landscape |
| Academic Researcher | academic-researcher.md | Literature reviews, citation analysis, methodology |
| Market Researcher | market-researcher.md | Market sizing, TAM/SAM/SOM, competitive intel |
| Security Researcher | security-researcher.md | CVE analysis, threat modeling, attack surface |
| Benchmarking Specialist | benchmarking-specialist.md | Performance benchmarks, comparative evals |
| Technology Scout | technology-scout.md | Emerging tech evaluation, build-vs-buy analysis |
| agntk | npx agntk | Zero-config AI agent CLI with 20+ tools, persistent memory, Ollama auto-detection, and free tier |
| qa-orchestra | Multi-agent QA toolkit with 10 specialized agents — orchestrator, environment-manager, functional-reviewer, test-scenario-designer, browser-validator, automation-writer, manual-validator, bug-reporter, release-analyzer, smart-test-selector. Stack-agnostic, output-chained, live validation via Chrome MCP |
Using Agents
Reference an agent in your CLAUDE.md:
## Agents
- Use `agents/core-development/fullstack-engineer.md` for feature development
- Use `agents/quality-assurance/code-reviewer.md` for PR reviews
- Use `agents/data-ai/prompt-engineer.md` for prompt optimization
Skills
Thirty-five curated skill modules included in this repo, with access to 400,000+ additional skills via the SkillKit marketplace. Each included skill teaches Claude Code domain-specific patterns with code examples, anti-patterns, and checklists.
| Skill | Directory | What It Teaches |
|---|---|---|
| TDD Mastery | skills/tdd-mastery/ | Red-green-refactor, test-first design, coverage targets |
| API Design Patterns | skills/api-design-patterns/ | RESTful conventions, versioning, pagination, error responses |
| Database Optimization | skills/database-optimization/ | Query planning, indexing, N+1 prevention, connection pooling |
| Frontend Excellence | skills/frontend-excellence/ | Component architecture, state management, performance budgets |
| Security Hardening | skills/security-hardening/ | Input validation, auth patterns, secrets management, CSP |
| Prism Scanner | pip install prism-scanner | Agent skill/plugin/MCP security scanner — 39+ rules, AST taint tracking, A-F grading |
| DevOps Automation | skills/devops-automation/ | Infrastructure as code, GitOps, monitoring, incident response |
| Continuous Learning | skills/continuous-learning/ | Session summaries, learning logs, pattern extraction |
| React Patterns | skills/react-patterns/ | Hooks, server components, suspense, error boundaries |
| Python Best Practices | skills/python-best-practices/ | Type hints, dataclasses, async/await, packaging |
| Go Idioms | skills/golang-idioms/ | Error handling, interfaces, concurrency, project layout |
| Django Patterns | skills/django-patterns/ | DRF, ORM optimization, signals, middleware |
| Spring Boot Patterns | skills/springboot-patterns/ | JPA, REST controllers, layered architecture |
| Next.js Mastery | skills/nextjs-mastery/ | App Router, RSC, ISR, server actions, middleware |
| GraphQL Design | skills/graphql-design/ | Schema design, DataLoader, subscriptions, pagination |
| Kubernetes Operations | skills/kubernetes-operations/ | Deployments, Helm charts, HPA, troubleshooting |
| Docker Best Practices | skills/docker-best-practices/ | Multi-stage builds, compose, image optimization |
| AWS Cloud Patterns | skills/aws-cloud-patterns/ | Lambda, DynamoDB, CDK, S3 event processing |
| CI/CD Pipelines | skills/ci-cd-pipelines/ | GitHub Actions, GitLab CI, matrix builds |
| Microservices Design | skills/microservices-design/ | Event-driven architecture, saga pattern, service mesh |
| TypeScript Advanced | skills/typescript-advanced/ | Generics, conditional types, mapped types, discriminated unions |
| Rust Systems | skills/rust-systems/ | Ownership, traits, async patterns, error handling |
| Prompt Engineering | skills/prompt-engineering/ | Chain-of-thought, few-shot, structured outputs |
| MCP Development | skills/mcp-development/ | MCP server tools, resources, transport setup |
| PostgreSQL Optimization | skills/postgres-optimization/ | EXPLAIN ANALYZE, indexes, partitioning, JSONB |
| Redis Patterns | skills/redis-patterns/ | Caching, rate limiting, pub/sub, streams, Lua scripts |
| Monitoring & Observability | skills/monitoring-observability/ | OpenTelemetry, Prometheus, structured logging |
| Authentication Patterns | skills/authentication-patterns/ | JWT, OAuth2 PKCE, RBAC, session management |
| WebSocket & Realtime | skills/websocket-realtime/ | Socket.io, SSE, reconnection, scaling |
| Testing Strategies | skills/testing-strategies/ | Contract testing, snapshot testing, property-based testing |
| Git Advanced | skills/git-advanced/ | Worktrees, bisect, interactive rebase, hooks |
| Accessibility (WCAG) | skills/accessibility-wcag/ | ARIA patterns, keyboard navigation, color contrast |
| Performance Optimization | skills/performance-optimization/ | Code splitting, image optimization, Core Web Vitals |
| Mobile Development | skills/mobile-development/ | React Native, Flutter, responsive layouts |
| Data Engineering | skills/data-engineering/ | ETL pipelines, Spark, star schema, data quality |
| LLM Integration | skills/llm-integration/ | Streaming, function calling, RAG, cost optimization |
Community Skills
| Skill | Install | What It Teaches |
|---|---|---|
| deep-dive | git clone https://github.com/kimsb2429/deep-dive-skill && cp -r deep-dive-skill/deep-dive ~/.claude/skills/ | DAG-based deep research — breaks questions into a dependency graph, runs parallel subagents, identifies gaps, writes a sourced report. Single markdown file, no external APIs or MCP servers. |
| Reepl - LinkedIn Content Creation | npx skillkit@latest install reepl-io/skills | 18 tools for LinkedIn content management: drafts, publishing, scheduling, voice profiles, contacts, collections, templates, and AI image generation |
| avoid-ai-writing | git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.claude/skills/avoid-ai-writing | AI writing pattern detection and rewriting (21 categories, 43 replacements) |
| CCM | npx skills add dr5hn/ccm@ccm | Multi-account management, session cleanup, health checks, environment snapshots, permissions audit for Claude Code |
| cc-inspect | git clone https://github.com/howardpen9/cc-inspect ~/.claude/skills/cc-inspect | Inspect all installed Claude Code skills, plugins, MCP servers, commands, and hooks in a browser dashboard. Scope-aware (user/project/local), zero dependencies (pure bash + python3), generates self-contained HTML |
| Edison | git clone https://github.com/kilnside/edison ~/.claude/skills/edison | Design decision skill — the phase between brainstorming and building. Research-first progressive deepening with self-executing specs. Three modes: Check, Explore, Audit |
| claude-handoff | git clone https://github.com/REMvisual/claude-handoff ~/.claude/skills/handoff | Cross-session handoff system with chain tracking, context summaries, and structured work continuity between Claude Code sessions |
| html-anything | npx skills add clockless-org/html-anything | Turn any file, folder, URL, or service export (Amazon orders, Kindle highlights, Spotify history, WhatsApp/WeChat, Google Photos Takeout, LinkedIn connections, CSV, PDF, DOCX, logs, GPX, …) into a polished single-file HTML page. Auto picks one of 18 design styles (teaching, timeline-story, map-atlas, developer, living-essay, editorial-carousel, terminal-cli, …). Self-contained — inline CSS/JS, no CDN, works offline. Live gallery |
| ClawSec | Visit clawsec.cc | Security audit platform for AI agent skills — automated 5-tier assessments, vulnerability detection, and configuration auditing for 33,000+ skills |
| ClawSearch | npm install -g clawsearch | Security-first skill discovery engine with Trust Score ratings, knowledge graph, and pre-install guard (clawsearch-guard) to vet skills before installation |
| MUSE | git clone + ./scripts/install.sh --tool claude | Pure-Markdown memory OS with 48 skills, cross-conversation memory, 8 roles with permission isolation. Works with 6 AI coding tools. |
| PM Pilot | git clone https://github.com/mshadmanrahman/pm-pilot ~/.claude/skills/pm-pilot | Claude Code for PMs: 25 skills for meeting prep, PRDs, stakeholder intel, user story mapping, customer journey maps, and product discovery |
| Product Manager Skills | clawhub install product-manager-skills | Senior PM agent with 6 knowledge domains, 12 templates, and 30+ frameworks covering discovery, strategy, delivery, SaaS metrics, PM career coaching (IC to CPO), and AI product craft |
| OpenDivination | pipx install opendivination && npx skills add amenti-labs/opendivination --skill divination | Tarot and I Ching skill with auditable entropy provenance, guided source setup across computer RNG, QRNG APIs, and local hardware, plus optional resonance mode |
| pumpclaw | git clone https://github.com/chainstacklabs/pumpclaw ~/.claude/skills/pumpclaw | Agent skill for pump.fun token trading on Solana — buy, sell, launch tokens, wallet management, dry-run simulation, slippage checks, and PumpSwap AMM migrations via pumpfun-cli |
| x-twitter-scraper | npx skills add Xquik-dev/x-twitter-scraper | X API & Twitter scraper skill for AI coding agents -- tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, trending topics, account monitoring, and 19 extraction tools |
| claude-code-marketing-skills | git clone https://github.com/cognyai/claude-code-marketing-skills ~/.claude/skills/claude-code-marketing-skills | AI-powered marketing skills — SEO Audit, Landing Page Review, Competitor Analysis, Ad Copy Writer, Lead Qualification. Free, no account required. Works with Claude Code, Cursor, Windsurf |
| claude-skills | git clone | 192 production-ready skills across 9 domains (engineering, marketing, product, compliance, C-level advisory) with 254 Python automation tools. 5,300+ stars |
| faf-skills | git clone | 31 Claude Code skills for persistent project context (.faf, application/vnd.faf+yaml). Scoring, sync, testing, publishing, MCP server creation, architecture docs. Anthropic MCP #2759. |
| floom | git clone https://github.com/floomhq/floom.git ~/.claude/skills/floom-repo && ~/.claude/skills/floom-repo/scripts/setup | Deploy Python scripts as cloud automations. /floom adapts code, tests in sandbox, deploys with auto-generated web UI, REST API, and MCP endpoint |
| n8n-skills | git clone | 7 complementary skills for building production-ready n8n workflows. Covers 525+ nodes, 2,653+ templates. 3,400+ stars |
| nv:context | npx skills add johnnichev/nv-context -g -y | State-of-the-art context engineering for AI agents. Auto-discovers tools, audits code for landmines, scores 6 leverage layers (repo structure, tool integration, memory, hooks, sessions, persona), generates production-ready CLAUDE.md/AGENTS.md configs |
| claude-code-best-practice | git clone | Comprehensive reference implementation for Claude Code configuration -- skills, subagents, hooks, commands with practical examples. 17,400+ stars |
| ADHX | /plugin marketplace add itsmemeworks/adhx or curl -sL https://raw.githubusercontent.com/itsmemeworks/adhx/main/skills/adhx/SKILL.md -o ~/.claude/skills/adhx/SKILL.md | Fetch any X/Twitter post as clean LLM-friendly JSON — no scraping, works with tweets and full X Articles |
| SkillNav | clawhub install HuiW86/skillnav | Search 3,900+ MCP servers with install commands, get daily AI brief, query arXiv papers, and discover trending tools -- all in Chinese. Curated by skillnav.dev editorial team |
| moyu | claude skill install --url https://github.com/uucz/moyu --skill moyu | Anti-over-engineering skill that teaches AI restraint. 5 variants (standard/lite/strict/en/ja), 10 platforms. Benchmarked: 66% code reduction vs baseline |
| naming | git clone https://github.com/glacierphonk/naming ~/.claude/skills/naming | Metaphor-driven naming for products, SaaS, brands, bots, and open source projects. Produces memorable, meaningful names |
| Obsidian Theme Designer | git clone https://github.com/XiangyuSu611/obsidian-theme-designer ~/.claude/skills/obsidian-theme-designer | Design Obsidian themes visually in the browser — style direction, color palette, font showcase, dual light/dark mode preview, and automated font installation. No CSS knowledge needed |
| Claudify | npx create-claudify | Complete operating system for Claude Code with 1,727 skills across 31 categories, 9 specialist agents with persistent memory, 21 slash commands, and automated quality checks |
| Axiom | npx skills add Guipetris/axiom | Contract-enforced autonomous pipeline: 8 stages from idea to PR with EARS requirements, ATDD (tests before implementation), RALPLAN-DR deliberation with ADR, 3 independent parallel reviewers, classified self-correction (SYNTAX/LOGIC/ARCH/AMBIGUOUS), cross-run project memory, and stage rollback. Zero dependencies beyond git and gh. |
| AuraKit | npx @smorky85/aurakit | All-in-one fullstack skill: 46 modes (BUILD/FIX/CLEAN/DEPLOY/REVIEW/TDD/QA/DEBUG/PAYMENT + more), 23 sub-agents, 6-layer OWASP+ security (bash-guard, secret scanning), 10 hooks, 8 languages, ~55% token savings. Cross-platform: Claude Code, Codex CLI, Cursor, Windsurf, Manus. |
| StitchFlow | git clone https://github.com/yshishenya/stitchflow && cd stitchflow && bash install.sh --target all | Cross-agent Stitch UI design bundle for turning briefs and mockups into screens, variants, Tailwind-friendly HTML, and screenshots |
| claude-skills | npx skills add ckorhonen/claude-skills | Broader collection of 45+ Claude Code skills spanning engineering, code hygiene, design, marketing, AI, security, and infrastructure. Hub at cdd.dev/skills. |
| swe-skills | npx skills add ckorhonen/swe-skills | 15 swe: skills for engineering analysis and judgment: PR risk review, repo introspection, performance/security audits, incident follow-up, ownership maps, refactor opportunities, test gap hunts. Hub at cdd.dev/skills/swe. |
| hone-skills | npx skills add ckorhonen/hone-skills | 8 hone: skills that run on a cadence (daily/weekly/per-PR) to fight code entropy: method brevity, naming clarity, duplication, magic numbers, broken-windows, naming specificity, test naming, automation opportunities. Hub at cdd.dev/skills/hone. |
| iterationlayer/skills | git clone https://github.com/iterationlayer/skills ~/.claude/skills/iterationlayer-skills | Document extraction, image transformation, image generation, document generation, and sheet generation via Iteration Layer APIs |
| Cost Optimizer | git clone https://github.com/fullstackcrew-alpha/skill-cost-optimizer | Save 60-80% on AI token costs with smart model routing, context compression, heartbeat tuning, usage reports, and config generation |
| linkedin-skills | /plugin marketplace add sergebulaev/linkedin-skills | 10 LinkedIn marketing skills: viral hook formulas, comment drafting, pre-publish algorithm audit, AI-tell humanizer, profile optimizer, content planner, thread engagement |
| Overnight Worker | git clone https://github.com/fullstackcrew-alpha/skill-overnight-worker | Autonomous overnight work agent — assign tasks before sleep, get structured results by morning with smart task decomposition, web research, and push notifications |
| Smart PR Review | git clone https://github.com/fullstackcrew-alpha/skill-smart-pr-review | Opinionated AI code reviewer with 6-layer deep review, Devil's Advocate mode, and standardized MUST FIX / SHOULD FIX / SUGGESTION output for TS/JS, Python, Go, Rust |
| DevOps Agent | git clone https://github.com/fullstackcrew-alpha/skill-devops-agent | One-click deploy, monitoring setup (Prometheus+Grafana), scheduled backups, and fault diagnosis with safety-first design including confirmation prompts, dry-run, and snapshot rollback |
| CN Content Matrix | git clone https://github.com/fullstackcrew-alpha/skill-cn-content-matrix | Chinese multi-platform content generator for Xiaohongshu, WeChat, Douyin, and Bilibili with true style transfer, compliance review, and sensitive word detection |
| D3.js Visualization | git clone | Generate interactive D3.js data visualizations from Claude Code |
| Google Drive – Memyard | git clone https://github.com/zagmoai/public-google-drive ~/.claude/skills/public-google-drive | Create and edit Google Docs and Sheets without sign-in. Documents hosted on Memyard with shareable links. No API keys or OAuth required |
| iOS Simulator | git clone | Interact with iOS Simulator for mobile testing and screenshot capture |
| Playwright Automation | git clone | Browser automation skill for end-to-end testing and web interaction |
| threat-hunting-with-sigma-rules | git clone | Sigma-rule-based threat detection and security log analysis |
| FFUF Web Fuzzing | git clone | Web vulnerability fuzzing and security testing via FFUF |
| Markdown to EPUB | git clone | Convert markdown files into EPUB ebooks |
| CSV Data Summarizer | git clone | Generate insights and summaries from CSV data files |
| tapestry | git clone | Knowledge networks, iterative learning, article extraction, and YouTube transcript processing |
| j4rk0r/claude-skills | npx skills add j4rk0r/claude-skills --yes --global | 3 expert-grade skills: skill-guard (9-layer security auditor), skill-advisor (smart routing with gap analysis), skill-learner (persistent error correction). All A+ 120/120 on skill-judge |
| deployhq-cli | brew install deployhq/tap/dhq && dhq setup claude | Deploy, rollback, and manage servers via DeployHQ CLI with --json output and breadcrumbs |
| SciAgent-Skills | git clone https://github.com/jaechang-hits/SciAgent-Skills | 197 life science skills for Claude Code covering genomics, proteomics, drug discovery, and more. BixBench 92.0% accuracy. |
| manage-skills | cp -r skills/manage-skills ~/.claude/skills/manage-skills | Discover, create, edit, toggle, copy, move, and delete agent skills across 11 tools (Cursor, Claude, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment) from the terminal |
| SuperSEO Skills | /plugin marketplace add inhouseseo/superseo-skills | 11 SEO skills for page audits, content briefs, article writing, E-E-A-T audits, semantic gap analysis, featured snippets, topic clusters, and link building. Each skill fetches pages and reads top-ranking competitors itself, so no keyword exports are needed. |
| buyer-eval | git clone https://github.com/salespeak-ai/buyer-eval-skill ~/.claude/skills/buyer-eval-skill | Structured, evidence-based B2B software vendor evaluation — researches your company, asks domain-expert questions, engages vendor AI agents via the Salespeak Frontdoor API, scores vendors across 7 dimensions with evidence transparency, produces comparative scorecards with demo prep questions |
| memory-bank | npx skills add Nagendhra-web/memory-bank | Persistent memory system — cuts token waste 60-80%, sessions last 3-5x longer. 3-tier layered architecture with progressive loading, branch-aware context, smart compression, session continuation protocol, session diffing, memory health scoring. Apache 2.0 |
| claude-seo | git clone https://github.com/AgriciDaniel/claude-seo | Comprehensive SEO suite — 30+ skills, 10 agents, site audits, E-E-A-T, GEO, schema, local SEO. MIT |
| claude-ads | git clone https://github.com/AgriciDaniel/claude-ads | Multi-platform ad audit — Google/Meta/LinkedIn/TikTok/Microsoft, 225+ checks, 18 skills. MIT |
| claude-blog | git clone https://github.com/AgriciDaniel/claude-blog | Blog engine — 17 commands, 12 templates, 100-point scoring, E-E-A-T, CMS integration. MIT |
| Coware | npx skills add shitianfang/coware-skills | Syncs shared API specs across AI coding agents — prevents merge conflicts from mismatched interfaces, field names, or return types. Auto-pulls latest specs, walks agents through setup for new projects |
| humanize-chinese | clawhub install humanize-chinese | Detects and rewrites AI-generated Chinese text. Two-layer detection (20+ rule dimensions + N-gram perplexity), 0-100 scoring, 7 style transforms, academic paper AIGC reduction. 4 slash commands: /detect, /humanize, /academic, /style |
| BeHuman | clawhub install behuman | Adds inner dialogue to AI responses via Self-Mirror consciousness loop — Self generates instinctive response, Mirror exposes filler/performative empathy, Self revises into real human reply. Based on Lacan's Mirror Stage, Kahneman's Dual Process Theory. MIT |
| readme-demo-recorder | git clone https://github.com/cjcsecurity/readme-demo-recorder ~/.claude/skills/readme-demo-recorder | Scripted-flow browser demo recorder for README hero assets — YAML demo-script in, polished MP4 + GIF out. Visible fake cursor + click pulse, three cursor styles (pulse/minimal/crosshair), timed caption overlays via ffmpeg drawtext, and automatic 7-step GIF size-cap ladder so output lands under GitHub's 10 MB inline cap. Built on Playwright + ffmpeg. Apache-2.0 |
| Karpathy Guidelines | npx @swarmclawai/andrej-karpathy-skills --agent claude --dest . | Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, OpenClaw, Windsurf, Aider, Copilot, and AGENTS.md-compatible agents |
| claude-tabletop | git clone https://github.com/cjcsecurity/claude-tabletop ~/.claude/skills/claude-tabletop | Two paired skills for project-aware technical tabletop exercises. /tabletop-exercise surveys the project (README, manifests, IaC, CI/CD), proposes 3 scenarios that match the stack, and generates a facilitator runbook (Markdown + interactive HTML with live exercise timer, per-inject reveal overlays, decision-log auto-timestamping, JSON export), participant packet, timed inject deck, and fillable forms. /tabletop-aar ingests the filled forms and drafts a structured After-Action Report. Covers 9 domains (cybersec, prodsec, devops/sre, privacy, data/ml, platform, mobile, ai-safety, business-continuity), 54 scenarios, 38 inject archetypes, 28 NPC personas, 7 compliance frameworks. Live demo. Apache-2.0 |
| paul-graham-skills | git clone https://github.com/WinterDDo/paul-graham-skills && cp -r paul-graham-skills/skills/* ~/.claude/skills/ | Five behavioral disciplines distilled from ~37 Paul Graham essays as Claude Code execution skills: plain-output-not-polished (decoration covers seams), discover-not-persuade (don't switch modes under pressure), distrust-the-surface (clean answer is a hypothesis), change-method-not-goal (failed method is the problem), mark-what-you-don't-know (distinguish evidence from pattern-match). Each is a comprehensive SKILL.md with triggers, failure modes, push-back guidance, and self-tests. MIT |
| rtlify-ai | npx rtlify-ai init | RTL (Right-to-Left) architecture rules for AI coding agents. Teaches logical CSS properties, Tailwind logical classes, bidi text, icon flipping, React Native RTL APIs. Works with Claude Code, Cursor, Copilot, Windsurf, Cline, Gemini CLI, Codex CLI. Zero dependencies. npx rtlify-ai check audits violations |
| calm-design | git clone https://github.com/calmtiger86/calm-design ~/.claude/skills/calm-design | Premium UI designs that don't look AI-generated — 50+ anti-slop patterns blocked, 33 brand references (Toss, Linear, Vercel), Korean-first with Pretendard. 5 modes: Generate, Upgrade, Match-Reference, Multi-Variant, JSON Spec |
| Emdash Skills | git clone https://github.com/megabytespace/claude-skills ~/.claude/skills/emdash-skills | 14-category autonomous product-building OS for AI coding tools. 94 reference docs, 18 agents. One-line prompts to deployed products on Cloudflare Workers |
| sober-coding | npx skills add https://github.com/voidborne-d/sober-coding.git | Hangover cure for vibe coding — language-agnostic code quality analyzer targeting AI-generated code smells. 27 checks across 7 dimensions (security, architecture, duplication, error handling, dependencies, testing, dead code), 0–100 sobriety score, actionable fix instructions via sober fix <ID>, CI mode with --fail-on critical. MIT |
| qovery-deploy | curl -fsSL https://skill.qovery.com/install.sh \| bash | Deploy any app to Kubernetes (AWS EKS, GCP GKE, Azure AKS, Scaleway). Analyzes codebases, creates Dockerfiles for 12+ frameworks, provisions databases, deploys via CLI+API or Terraform, auto-fixes failures. Also has MCP Server. |
| planmysaas | git clone https://github.com/creationskiro/planmysaas-claude-skill ~/.claude/skills/planmysaas | Turns idea to a complete 8-stage SaaS blueprint — idea, research, analysis, architecture, features, frontend, phases, build playbook. Stage 8 ships a decision-grade, rubric-graded build playbook with dependency-ordered steps. Plain markdown, MIT, v1.0.0. |
| agentkit-seo | npx agentkit-seo install --provider claude-code | AI agent skill for auditing and optimizing GitHub profiles and repositories. Covers bio, pinned repos, README structure, topics, Copilot instructions, and language stats. |
| active-listening | /plugin marketplace add https://github.com/josharsh/active-listening | Detect developer preferences during conversation ("never push without asking", "always use const") and remember them across sessions. Auto-saves to disk and re-applies in every future conversation |
| StyleSeed | skills/styleseed/ | Design judgment: 69 visual rules, brand skins, professional UI |
| SwarmClaw | git clone https://github.com/swarmclawai/swarmclaw && cp -r swarmclaw/skills/swarmclaw.md ~/.claude/skills/swarmclaw.md | Self-hosted runtime for autonomous AI agents. Multi-provider, MCP-native, with memory, runtime skills, delegation, schedules, and reviewed conversation-to-skill learning across OpenClaw gateways and other providers |
| SwarmVault | `/plugin marketplace add swarmclawai/swarmvault &