self-edit
Skill1 starsChanged 2 months agoMITView on GitHub
AI 产出物的自动审查与修复。当需要检查并修复 AI 生成的文字/代码/内容中的问题时使用。适用于任何 AI 产出后的质量检查。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mike22890/opencode-skills-enword for word, first seen Oct 15, 2026
Other versions1 project uses a version of this.
Word for word · 1
- mike22890/opencode-skills-en★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository40 other files it gives its agents.
- aestheticsSkill
- applying-ui-design-systemSkill
- avoid-ai-writingSkill
- clonedepsSkill
- codemapSkill
- code-masterySkill
- code-refactor-astSkill
- copywritingSkill
- croSkill
- db-schema-designerSkill
- frontend-designSkill
- github-workflowSkill
- git-workflowSkill
- humanize-fictionSkill
- human-voiceSkill
- life-planningSkill
- literary-craftSkill
- long-taskSkill
- marketing-psychologySkill
- masterpiece-writingSkill
- mcp-builderSkill
- mermaid-diagram-generatorSkill
- orchestrating-adversarial-reviewsSkill
- pandocSkill
- persuasion-craftSkill
- pptxSkill
- pricingSkill
- privacy-guardSkill
- product-strategySkill
- property-based-testingSkill
- psychology-masterySkill
- research-masterySkill
- shopping-advisorSkill
- simplifySkill
- skill-creatorSkill
- story-endingsSkill
- system-designSkill
- thinking-craftSkill
- wealth-masterySkill
- wisdom-philosophySkill
The file
Files
Self-Edit(自动审查修复)
何时触发
关键词:检查一下、审查、有没有问题、AI味、重复、无聊、不自然、修一下、改得像人写的。
文字审查(写完必跑)
1. 重复检查
- 词频检查:同一段里同一个词出现 2 次以上 → 换掉
- 句式检查:连续 3 句以上结构相同 → 打破
- 段落检查:段落长度方差 → 长短交替
2. 情绪检查
- 搜索:"很X"、"非常X"、"特别X" → 改成身体反应
- 搜索:"觉得"、"感到"、"认为"(高频)→ 删掉,直接写行为
3. 对话检查
- 搜索:完整句子对话 → 改成省略/断句
- 搜索:"X说。""Y说。"连续出现 → 加动作/沉默
4. 节奏检查
- 段落长度是否一致?→ 打破
- 是否每段都有总结句?→ 删掉一半
- 标题是否戏剧化?→ 改平实
5. 隐私检查
- 搜索:邮箱、手机号、身份证号、API key、token → 删掉
- 搜索:公司名、人名(非公开)→ 匿名化
代码审查(写完必跑)
1. 安全检查
- 搜索:硬编码密码/token → 改成 env 变量
- 搜索:SQL 拼接 → 改成参数化查询
- 搜索:eval/exec → 删掉
2. 质量检查
- 搜索:重复代码块 → 提取函数
- 搜索:>3 层 if 嵌套 → 用早返回
- 搜索:万能 helper/utils → 拆成具体模块
3. AI 味检查
- 搜索:过度注释(解释"是什么")→ 改成解释"为什么"
- 搜索:万能变量名(data/info/item)→ 改成意图明确的名字
使用方式
写完任何东西后,跑一遍:
1. 复制产出内容
2. 对照上面清单逐项检查
3. 发现问题立即修复
4. 修复后再读一遍不需要用户手动触发——AI 每次产出后自动跑。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

