writing-for-agents
Skill13 starsChanged yesterdayMITView on GitHub
只要是写、改或审查 agent 读的文字时使用
192 other projects use a version of this.
Adopted by
Most recently taken up by
- philoserf/claude-code-configtheir own version, first seen Nov 15, 2026
- niki914/zafirotheir own version, first seen Nov 15, 2026
- Kealman/cland-v0their own version, first seen Nov 15, 2026
- incredible404-rgb/zstacktheir own version, first seen Nov 15, 2026
- hanjiang-215/ticket-index-skillstheir own version, first seen Nov 15, 2026
- Gjl1u9/watch-lesstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use wait-what, to-questionnaire and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AWSSkillwait-what
Stop. That last message did not land: re-pitch it.
Also in 115 projects that use this
AWSSkillto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Also in 83 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 34 projects that use this
openchamberSkillclack-cli-patterns
Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.
Also in 3 projects that use this
MicrosoftSkillcloud-architecture-diagram
Create, edit, or review Azure and Microsoft ecosystem architecture, GitHub CI/CD, and auth/API diagrams as editable draw.io files; resolve Microsoft and GitHub icons. Use for architecture visualization, diagram critique, or missing icons. Azure DevOps only when explicitly requested. Not for competing-cloud architecture, deployment, live discovery, security certification, or unrelated charts.
Also in 3 projects that use this
openchamberSkilldrag-to-reorder
Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.
Also in 3 projects that use this
- +1 more from aws
- +4 more from openchamber
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 192
- mattpocock/skills★ 325ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- formbricks/formbricks★ 13ksame name
- openchamber/openchamber★ 13ksame name
- btriapitsyn/openchamber★ 13ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
182 more not listed
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 repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- gpt-imageSkill
- postSkill
- promoSkill
- videoSkill
- writing-for-humansSkill
- architecture-auditSkill
- better-testSkill
- eli5Skill
- project-setupSkill
- prototypeSkill
- prSkill
- write-swiftSkill
- find-refsSkill
- ui-craftSkill
- ui-picksSkill
- browserSkill
- desktopSkill
- session-dataSkill
- sshSkill
- web-searchSkill
- fan-outSkill
- grillingSkill
- hillclimbSkill
- researchSkill
- retroSkill
The file
Files
给 agent 写文档
适用于一切会被 agent 读到的文档。目标是让每次运行走同样的过程,用最少的字。
检验
每句话默认删。留下的要同时满足:
- 有出处:一次观察到的失败(agent 这样错过,或用户这样纠正过;“模型可能会犯”不算),或环境里查不到、重新摸清代价高的事实(未写明的约定、某个选择的理由、只能在第三方控制台上做的步骤)。几分钟能试出来的坑不算:踩到时修成报错、lint 或代码旁的一句注释。脚本、配置、目录结构、
--help查得到的不重述。 - 删掉会变差:当前模型没有它就做错。
不满足的整句删掉,不只删几个字。常见的:
- 模型默认就会做的步骤:理解需求、自查、"要彻底"。
- 为旧模型写的验证与复查指令。当前模型会自行验证,这类指令只造成过度验证;删掉,不改写。
- 全大写和"必须""务必"式强调。新模型对系统提示更敏感,强调会让它过度触发;写成平实的"在……时做……"。
清理
新写、被要求精简或审查时过整份文档;只改一处时过它所在的那一节。每句定一个去向:
- 过不了检验的,删。
- 能机器检查的(格式、禁词、命名、依赖方向),做成 lint、hook 或测试,修复指引写进报错信息,然后从文档删掉;这次做不了就留着,在回复里提出。
- 其他层(全局系统提示、插件提示词、项目 AGENTS.md、skill)已有同义的,合并到一处:各层各写一遍“要验证”,agent 就验证三遍。
- 只有部分情形用到的,按「结构」移出正文。
要加规则时先找能改写的现有句子;确需新增,同一次改动里找一句可删的。
完成标准:留下的每一句都过了检验,且同一含义只在一处出现。
常驻文档(系统提示、AGENTS.md、skill 的 description)新写或大改后,有子代理工具时派一个新上下文的子代理,只给它文档和本 skill,让它列出过不了检验的句子,属实的删掉。起草者带着整段对话的上下文,看不出哪些句子多余。
指针
AGENTS.md 里指向某份文件的一行、skill 的 description,都是指针:说明材料是什么,以及什么情形去读。
- 触发词放最前;每种情形只留一个触发词,同义改写合并掉。
- 该读的材料没被读到,先加强指针措辞、写清触发情形("等合并与发布只用
make land"),加强无效才把内容内联。 - 指针每轮都在上下文里,比正文裁剪得更狠;正文已说明的身份信息不在指针里重复。
AGENTS.md 是地图:命令入口、代码看不出的约束、"遇到某种情形去读某份文件"的条件指针。架构概述、目录树、rg 一下就能找到的东西不写。
结构
文档由两种内容组成:agent 按顺序做的步骤,和按需查的参考。
- 每条路径都用到的内容写在正文;只有部分情形用到的移到单独文件,正文留指针。步骤被参考资料埋住时,agent 注意不注意到全看运气。
- 同一概念的定义、规则、注意事项放在同一标题下,不散在各处。
- 只在某个事件或某次工具调用时才用得上的说明,写进那条事件消息或工具说明,不放进每轮常驻的提示词。
- 每个步骤以完成标准结尾:可检查(分得清做完没做完),且要求穷尽("每个被改的调用点都已核对",而不是"列出改动")。标准含糊,agent 会提前收工。
措辞
- 写目标行为("写单行注释"),不写笼统禁令("别啰嗦"):禁令会把被禁的东西带进上下文。硬性护栏才直接禁止。
- 规则有例外就写进同一句(“……时先确认,其余直接开工”),不另起一条去抵消它:两条规则相互拉扯时,哪条占上风没有保证。
- 观察到具体失败模式时逐项点名("奶油色背景、标题里的斜体强调词、01/02/03 编号标签"),同时写出要什么。
- 用模型预训练里已有的常用词(tracer bullet、expand–contract),不自造术语;一串形容能收成一个这样的词就收(“快、确定、开销低”收成 tight)。自造词要花字定义,还会被 agent 带进给用户的回复,变成用户看不懂的黑话。
Skill
- description 每轮常驻上下文,按「指针」写;模型需要自己发现时才开放自动触发。
- 只靠手动命令或其他 skill 明确指向的,加
disable-model-invocation: true,它就不进自动列表。 - 正文超过 500 行就按情形拆出参考文件,引用只走一层。
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.

