菜单
Scaffold per-repo configuration for all other skills. Run once per project before using any other skill. Configures issue tracker, triage labels, doc paths, test framework, and creates CONTEXT.md and initial ADR. Supports Claude Code, Cursor, Windsurf, Cline, GitHub Copilot, Codex, Aider, and any AI tool.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | setup |
| description | Scaffold per-repo configuration for all other skills. Run once per project before using any other skill. Configures issue tracker, triage labels, doc paths, test framework, and creates CONTEXT.md and initial ADR. Supports Claude Code, Cursor, Windsurf, Cline, GitHub Copilot, Codex, Aider, and any AI tool. |
| argument-hint | [project path, defaults to current directory] |
"Start as you mean to go on."
All other skills depend on shared configuration and context. This skill creates that foundation. Run once per project. Takes 2 minutes.
Use defaults if user doesn't want to decide:
bug, feature, enhancement, tech-debt, questiondocs/ (default), docs/adr/, docs/handoff/CONTEXT.md at project root (default)Always create:
CONTEXT.md — Domain context and shared languagedocs/adr/0001-initial-setup.md — Initial ADRTool-specific (based on Step 1):
| Tool | File |
|---|---|
| Claude Code | CLAUDE.md |
| Cursor | .cursor/rules/integrated-guidelines.mdc |
| Windsurf | .windsurfrules |
| Cline | .clinerules |
| GitHub Copilot | .github/copilot-instructions.md |
| Codex | AGENTS.md |
| Aider | .aider.conf.yml |
| Gemini CLI | GEMINI.md |
| OpenCode | .opencode/instructions.md |
| Copilot CLI | .copilot-cli/instructions.md |
| Codex CLI | .codex/instructions.md |
| Other | SYSTEM_PROMPT.md (copy content to tool's custom instructions) |
# Project Context
## Domain Language
- [Term 1]: [definition]
- [Term 2]: [definition]
## Module Map
- [Module A]: [responsibility]
- [Module B]: [responsibility]
## Architecture Decisions
- See `docs/adr/` for all decisions
## Code Style
- [Rule 1]
- [Rule 2]
# ADR 0001: Initial Project Setup
## Status
Accepted
## Context
Setting up AI Engineering Mastery skills for this project.
## Decision
- Issue tracker: [choice]
- AI tools: [choices]
- Test framework: [choice]
## Consequences
- All skills will use this configuration
- CONTEXT.md is the source of truth for domain language
Setup Complete!
Configuration:
- Issue Tracker: [choice]
- AI Tools: [choices]
- Docs Path: [path]
- Test Framework: [choice]
Files Created:
- CONTEXT.md
- docs/adr/0001-initial-setup.md
- [tool-specific files]
Available Skills:
/brainstorm — Design exploration with HARD-GATE
/grill — Deep alignment before coding
/tdd — Test-driven development
/diagnose — Systematic debugging
/architect — Architecture improvement
/zoom-out — System-level context
/to-prd — Create PRD
/to-issues — Break plan into issues
/caveman — Compressed communication
/handoff — Session handoff
/verify — Evidence-based completion verification
/review — Code review (request + receive)
Quick Start:
1. Start with /grill to align on your first task
2. Use /tdd to implement with confidence
3. End with /handoff to save your progress
/setup before any other skillFind deepening opportunities in a codebase — refactors that turn shallow modules into deep ones. Use when the codebase feels hard to change, bugs cluster in certain modules, adding features requires touching many files, or proactively every few days as a health check.
Collaborative design exploration before implementation. Use when starting a new feature or project, when the approach is unclear, or when multiple design directions exist. Unlike /grill (which aligns on a given plan), /brainstorm explores and creates the plan. Enforces a HARD-GATE: no code until design is approved.
Systematic debugging loop for hard bugs and performance regressions. Use when something is broken and you don't know why, when behavior is inconsistent, or when error messages are unclear. Follows reproduce → minimise → hypothesise → instrument → fix → regression-test.
Deep alignment session before coding. Use when starting a non-trivial feature, when requirements are ambiguous, before refactoring, or when the user's request could be interpreted multiple ways. Surfaces assumptions, presents tradeoffs, and produces a verified implementation plan.
Request and handle code reviews with technical rigor. Use after completing a feature or task, before merging. Covers both requesting reviews and responding to feedback — verify before implementing, push back when wrong, no performative agreement.
Test-driven development with red-green-refactor loop. Use when building features, fixing bugs, refactoring code, or when the user mentions TDD, test-first, or red-green-refactor. Builds one vertical slice at a time.