rylai-codex-hermes-skills

作者 Rylaispirit已验证

35 portable Agent Skills for Codex, Hermes, and Claude, maintained by Rylai with Vietnamese documentation and upstream attribution.

54
Stars
40
Forks
Python
语言
2026/8/24
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/Rylaispirit/rylai-codex-hermes-skills

快速入门

使用 rylai-codex-hermes-skills 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

Rylai Codex-Hermes-Claude Skills

A personal collection of portable Agent Skills curated, adapted, and maintained by Rylai for Codex, Hermes, and Claude.

The bundle contains 35 independent skills for writing, research, data, documents, presentations, design, media, finance, deployment, and skill creation. The skills can be installed together or copied individually.

Every skill is a plain SKILL.md folder with no runtime lock-in, so the same files load in Codex, Hermes, and Claude. Only the install location differs.

Ownership And Sources

  • Rylai authors the bundle structure, installers, validators, Vietnamese guide, clean-room replacements, compatibility notes, and original helper scripts.
  • Skills adapted from public GitHub projects retain their upstream repository, revision, author, and license information.
  • An upstream credit means the corresponding author owns their original work. Rylai is the maintainer and adapter of this Codex-Hermes-Claude edition.
  • No private workstation paths, credentials, proprietary vendor schemas, remote placeholder images, or marketplace control skills are included.

See THIRD_PARTY_NOTICES.md and PROVENANCE.yml for the release provenance.

Vietnamese Guide

See GIAI_THICH_SKILLS_VI.md for a Vietnamese description of every skill, including its purpose, expected inputs and outputs, runtime requirements, and example requests.

Installation

Codex

.\install-codex.ps1

Use -Force to replace existing skills. Existing folders are backed up first.

Hermes

bash install-hermes.sh

Use --force to replace existing skills. Existing folders are backed up first.

Claude

bash install-claude.sh
.\install-claude.ps1

Use --force (-Force in PowerShell) to replace existing skills. Existing folders are backed up first.

The default target is the personal skill directory, so the skills load in every Claude session. Pass --project (-Project) to install into .claude/skills next to the current project instead, or --target <dir> (-Target <dir>) to choose the directory yourself. Skills are discovered when a session starts, so start a new Claude session after installing.

Claude reads the same SKILL.md frontmatter as the other runtimes. The extra agents/openai.yaml file in each skill is ignored there and is kept only so one checkout serves all three agents.

Prebuilt Claude ZIP Files

packages/ holds one .zip archive per skill, built from skills/ by build_claude_packages.py. Each ZIP has the skill folder at its root, including that folder's SKILL.md and bundled resources.

Use these with Claude.ai or Cowork through the skill-management interface. Claude Code should use the unpacked folders through install-claude.sh, install-claude.ps1, or a manual copy into a Claude skill directory.

Rebuild them after editing any skill:

python build_claude_packages.py --clean

Archives are reproducible, so an unchanged skill keeps its checksum. Per-archive hashes are written to packages/checksums.sha256.

Install One Skill

Copy one directory from skills/ into the skill directory used by your agent:

Codex:  ~/.agents/skills/<skill-name>
Hermes: ~/.hermes/skills/<skill-name>
Claude: ~/.claude/skills/<skill-name>          personal, every session
        <project>/.claude/skills/<skill-name>  one project only

Status Meanings

  • ready: instruction workflow is usable without a special proprietary runtime.
  • conditional: requires an optional package, binary, login, API, or renderer.
  • adapted-core: the portable core is available; advanced integrations may be intentionally omitted.

Runtime requirements are described in each SKILL.md and in manifest.json.

Verification

python -m pip install -r requirements-verify.txt
python verify_bundle.py

The verifier checks skill structure, UI metadata, Rylai maintainer metadata, provenance, manifest consistency, Markdown fences and inline code spans, private paths, banned vendor residue, third-party notices, and whether all 35 Claude ZIP packages are still in sync with skills/.

checksums.sha256 covers the source files in this repository. The generated archives are covered separately by packages/checksums.sha256. Both are plain sha256 manifests:

sha256sum -c checksums.sha256
cd packages && sha256sum -c checksums.sha256

The archive manifest lists bare file names, so check it from inside packages/.

Get-FileHash -Algorithm SHA256 <file>

Regenerate the release checksum file after changing any source file:

python build_claude_packages.py --release-checksums

Repository Layout

skills/
  <skill-name>/
    SKILL.md
    agents/openai.yaml
    scripts/ references/ assets/ ... when required
manifest.json
PROVENANCE.yml
THIRD_PARTY_NOTICES.md
packages/
  <skill-name>.zip
  checksums.sha256
GIAI_THICH_SKILLS_VI.md
install-codex.ps1
install-hermes.sh
install-claude.ps1
install-claude.sh
build_claude_packages.py
verify_bundle.py

License

Rylai-authored material is released under the MIT License. Third-party material keeps its original license; see the notices and provenance files.

This is a community project and is not endorsed by the agent platforms or the upstream repositories listed in the notices.

常见问题

What is rylai-codex-hermes-skills?

rylai-codex-hermes-skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Rylaispirit. 35 portable Agent Skills for Codex, Hermes, and Claude, maintained by Rylai with Vietnamese documentation and upstream attribution. It has 54 GitHub stars.

Is rylai-codex-hermes-skills safe to use?

Yes. rylai-codex-hermes-skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install rylai-codex-hermes-skills?

Clone the repository with "git clone https://github.com/Rylaispirit/rylai-codex-hermes-skills" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is rylai-codex-hermes-skills written in?

rylai-codex-hermes-skills is primarily written in Python. It is open-source under Rylaispirit on GitHub, so you can review or fork the full source.

Are there alternatives to rylai-codex-hermes-skills?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh rylai-codex-hermes-skills against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情