菜单
Standards for code documentation, comments, and artifact updates.
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 | documentation-standards |
| description | Standards for code documentation, comments, and artifact updates. |
| tier | 1 |
| version | 1.3 |
Purpose: Defines the non-negotiable standards for code comments, docstrings, and global artifacts.
STOP if you are thinking:
.AGENTS.md must follow project memory policy.All classes and functions MUST have documentation.
Use Google-style docstrings.
[!TIP] See
assets/templates/python_docstring.pyfor the format.
Use JSDoc standards.
[!TIP] See
assets/templates/jsdoc_template.tsfor the format.
# T O D O: (Python) or // T O D O: (JS/TS) for future work.[Ref](src/main.py)[.agent/skills/core.md](.agent/skills/core.md)file:///Users/username/project/src/main.py/Absolute/System/Path.AGENTS.md)Policy: keep .AGENTS.md for source-code directories under memory tracking. Missing file should not fail execution; bootstrap when needed.
[!TIP] Use the template at
assets/templates/agents_md_template.md.
| Agent Excuse | Reality / Counter-Argument |
|---|---|
| "It's a throwaway script" | Scripts evolve into products. Documenting later costs 3x more time. |
| "I don't know the types yet" | Use Any or unknown but document what the value represents. |
assets/templates/: Collections of templates.examples/good_documentation.py: Gold standard example.Use when decomposing tasks into parallel sub-tasks or spawning sub-agents. Vendor-agnostic core; load a per-vendor reference for concrete tool names, directory conventions, and invocation syntax.
Use when performing Verification-Driven Development with adversarial approach. Actively challenge assumptions and find weak spots.
Use when performing VDD adversarial review with an opt-in sarcastic, provocative delivery style — a stylistic skin over vdd-adversarial mechanics (exhaustive reporting + objective bar).
Performance critic in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing OWASP security critique in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing security vulnerability assessment (OWASP, secrets, dependencies, IaC, LLM, API, MCP/agentic) or when "thinking like a hacker" to find exploits.