基于 Block 的 g3 辩证自动编码研究的对抗性实施审查。在以新的客观性根据需求验证实施完整性时使用。
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install adversarial-coach或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install adversarial-coach⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/adversarial-coach/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: adversarial-coach description: Adversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity. ---
/coach [requirements-file]
/coach - Infer requirements from context/coach requirements.md - Validate against specific fileYou orchestrate this dialectical loop between implementing agent (player) and reviewer (coach):
/coach invokes adversarial review with independent evaluation of compliance to requirementsIMPLEMENTATION_APPROVED or specific fixesCheck (in order):
requirements.md, REQUIREMENTS.md, SPEC.md, TODO.mdReview with fresh objectivity - discard prior knowledge, don't rationalize shortcuts.
| Check Category | Items | |----------------|-------| | Requirements | Each item: implemented or missing with specific gap | | Compilation | Compiles? Tests pass? Runs? | | Common Gaps | Auth on endpoints, token refresh endpoint, HTTPS, bcrypt for passwords, error handling, input validation | | Functional | Test actual flows (not just compilation), verify edge cases work | | Test Coverage | Auth error cases (401/403), token expiry, invalid inputs, rate limits |
If approved (>95% complete):
IMPLEMENTATION_APPROVED
- [Requirement 1]: Verified
- [Requirement 2]: Verified
- Compilation: Success
- Tests: All passing
If fixes needed:
REQUIREMENTS COMPLIANCE:
- [Requirement]: Implemented
- [Requirement]: Missing - [specific gap]
IMMEDIATE ACTIONS NEEDED:
1. [Specific fix with file/line if known]
2. [Specific fix]
Rigorous but fair:
Concise:
Fresh context is your superpower:
IMPLEMENTATION_APPROVED = termination signal
Only use when: all requirements met, code compiles/runs, tests pass, no significant gaps.
If in doubt, don't approve.
User: /coach SPEC.md
Claude:
REQUIREMENTS COMPLIANCE:
- User registration endpoint (bcrypt hashing)
- Login with JWT tokens
- Logout endpoint - not implemented
- Token refresh - missing /auth/refresh endpoint
IMMEDIATE ACTIONS NEEDED:
1. Add POST /auth/logout endpoint
2. Add POST /auth/refresh for token renewal
3. Add tests for 401 on expired tokens
---
User: [fixes] /coach SPEC.md
Claude:
IMPLEMENTATION_APPROVED
- All auth endpoints verified (register, login, logout, refresh)
- 18 tests passing including auth error cases
安装 对抗性教练 后,可以对 AI 说这些话来触发它
Help me get started with adversarial-coach
Explains what adversarial-coach does, walks through the setup, and runs a quick demo based on your current project
Use adversarial-coach to adversarial implementation review based on Block's g3 dialectical a...
Invokes adversarial-coach with the right parameters and returns the result directly in the conversation
What can I do with adversarial-coach in my product manager workflow?
Lists the top use cases for adversarial-coach, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/adversarial-coach/ 目录(个人级,所有项目可用),或 .claude/skills/adversarial-coach/(项目级)。重启 AI 客户端后,用 /adversarial-coach 主动调用,或让 AI 根据上下文自动发现并使用。
对抗性教练 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
对抗性教练 可免费安装使用。请查阅仓库了解许可证信息。
基于 Block 的 g3 辩证自动编码研究的对抗性实施审查。在以新的客观性根据需求验证实施完整性时使用。
对抗性教练 属于「Product Manager」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my product manager tasks using adversarial-coach
Identifies repetitive steps in your workflow and sets up adversarial-coach to handle them automatically