weekly-rpg-retro

作者 Pavelgq已验证

AI skill for personal weekly rpg-style retrospectives where you choose the story

0
Stars
0
Forks
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/Pavelgq/weekly-rpg-retro

快速入门

使用 weekly-rpg-retro 等 Skills 的指南。

安全报告

已验证

上次扫描:—

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

README.md

Weekly RPG Retro 🎲

A Claude skill that turns weekly reflection into an RPG campaign: you are the character, Claude is the Game Master. Under the hood — the classic agile retrospective structure (five stages, checking last week's action items, experiments against recurring problems). On top — lore, stats, bosses, and achievements, so the ritual is one you want to repeat instead of abandoning after a month.

The GM speaks whatever language you speak.

What it looks like

Once a week you tell Claude "let's run my weekly session". The Game Master:

  1. opens your character sheet and tells you itself what worries it — sagging stats, bosses growing stronger, the fate of last week's quests;
  2. asks questions one at a time (what was valuable, what drained you, what you learned, what got done for the main quests, when you felt proud) and reacts to each answer in two layers: narrative + an honest observation about the pattern;
  3. proposes its own interpretation of the week: stat deltas, achievements, bosses moving between stages;
  4. helps you pick 1–3 small quests for the coming week;
  5. closes with a "GM's observation" and writes everything to files.

Core mechanics

Personal stats. No fixed set — during onboarding the Game Master derives 4–6 stats from your goals and values. The starting value comes from a 1–100 self-assessment; after that, weekly deltas of ±1…3. No silent minuses: the GM must voice and discuss every decline.

Bosses. A recurring difficulty is a boss with a stage and a level. The cycle mirrors a retrospective loop: Spotted → Studied (a hypothesis about the trigger) → Fighting (a one-week experiment quest) → Retreating → Defeated. If a boss sits without an experiment for three weeks, or returns after a victory, it grows stronger: its level rises and the GM raises it at the start of the session. A conscious "not fighting this one right now" is recorded in the decision register and freezes the level.

Closing the loop. Every session starts with the fate of last week's quests. "Not done" is material for observation, not for guilt: the campaign's Prime Directive is that the character acted in the best way they could given what they knew, the resources they had, and the state they were in.

Quarterly review. Every ~12 weeks — the view from above: progress on the main quests, how fast bosses get defeated, the rating trend, the shift in how the character speaks about themselves, and next quarter's goals.

Installation

A skill is a folder with a SKILL.md. Put it where your Claude looks for skills:

  • Claude Code: .claude/skills/weekly-rpg-retro/ inside the campaign repository (or ~/.claude/skills/ for all projects);
  • Claude.ai / Cowork: upload SKILL.md to a chat and click "Save skill", or add it via Settings → Capabilities → Skills.

Important: the campaign needs a folder

The skill describes the process, but the state (profile, character sheet, week logs) lives in files. Create a dedicated directory or repository for the campaign — and run sessions where Claude can reach it: Claude Code, Cowork, or a chat with a connected GitHub repository. In a plain chat with no file system, the campaign won't survive between conversations.

The structure the skill maintains on its own:

my-campaign/
├── profile.md            # setting, goals, values, your stat set
├── character_sheet.md    # current state: stats, bosses, achievements
├── week1_log.md          # one log per week
├── week2_log.md
└── quarter1_review.md    # quarter summaries

See examples/ for a fictional sample profile and week log that show the intended tone and format.

Quick start

  1. Create an empty campaign folder/repository and install the skill.
  2. Tell Claude: "Let's set up my campaign" — the Game Master runs onboarding (~20 minutes): a setting to your taste, main quests for the quarter, your values, known adversaries, your personal stats.
  3. A week later: "Let's run my weekly session." Full format ~30 minutes, short ~15.

The skill never launches itself — only when you ask.

Philosophy

  • A retrospective that never checks past decisions is an empty ritual.
  • Bosses describe a recurring difficulty, not a character flaw.
  • Lore is packaging: every GM line must carry a real observation, not just atmosphere.
  • A small quest doable under any shape of week beats a big plan.

License

MIT — take it, adapt it, play it.

常见问题

What is weekly-rpg-retro?

weekly-rpg-retro is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Pavelgq. AI skill for personal weekly rpg-style retrospectives where you choose the story. It has 0 GitHub stars.

Is weekly-rpg-retro safe to use?

Yes. weekly-rpg-retro 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 weekly-rpg-retro?

Clone the repository with "git clone https://github.com/Pavelgq/weekly-rpg-retro" and add it to your Claude Code skills directory (see the Installation section above). weekly-rpg-retro ships a SKILL.md manifest, so compatible agents can discover and load it automatically.

Are there alternatives to weekly-rpg-retro?

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 weekly-rpg-retro 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