メニュー
Project documentation structure — standard proj-[name]/ layout with ADRs, stories, and operations guides. Use when: initializing docs for a new project, recording architecture decisions, or maintaining project knowledge bases.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | project-docs |
| description | Project documentation structure — standard proj-[name]/ layout with ADRs, stories, and operations guides. Use when: initializing docs for a new project, recording architecture decisions, or maintaining project knowledge bases. |
Each project gets a proj-[name]/ directory:
proj-[name]/
├── SKILL.md # Project entry point (concise summary)
└── references/
├── _index.md # Navigation guide
├── product/
│ ├── vision.md # What problem this project solves
│ └── principles.md # Core development principles
├── system/
│ └── overview.md # System architecture overview
├── decisions/
│ ├── _index.md # Decision index
│ ├── adr/ # Architecture Decision Records
│ └── stories/ # Feature stories
└── operations/
├── quick-nav.md # Quick navigation
└── troubleshooting.md # Common issues & solutions
product/vision.md — What problem does this project solve?product/principles.md — What are the core development principles?system/overview.md — What does the system look like now?decisions/adr/ — Record important technical choices already madeSee doc-standards.md for ADR format, story format, and naming conventions.
| File | Content |
|---|---|
| doc-standards.md | Document formats and templates |
Use when writing, reviewing, or deciding what to post on Threads. Also triggers when planning post-viral strategy or checking posting timing. Runs pre-publish checks based on Meta algorithm patents.
Use when predicting Threads post performance, analyzing post history patterns, estimating engagement ceiling for a draft, or deciding what content type to write next. Works with or without personal data — uses darkseoking benchmark as fallback.
Claude Code 專案配置審計。觸發：review/優化 CLAUDE.md、skills、settings、定期清洗累積內容、新專案上線前檢查。
Agent 配置設計指南 — 基於 Claude Code 6 個 built-in agent 的逆向分析。Use when: 設計新 agent、優化現有 agent prompt、決定工具/模型配置、撰寫 dispatch prompt。
AI Agent 成本工程 — 基於 Claude Code 的成本追蹤、prompt cache 最佳化、token 預算控制逆向分析。Use when: 優化 token 消耗、設計成本控制機制、分析 cache 效率、選擇模型配置。
Harness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理策略、建構 agent loop。