writing-fragments
Skill27 starsChanged 3 months agoMITView on GitHub
Writing, explore —— 挖掘原始片段,尚无结构。
Files
<what-to-do>这是纯粹的 explore(探索):拓宽可以写的空间,而不承诺任何结构 —— 承诺是 exploit(发掘),那是另一个技能的活儿。运行一次产出片段的拷问式会话,就用户想写的任何东西不留情面地访谈他们。在这里,强加阶段、提纲或文章结构是超出范围的。
随着片段从对话的任意一方浮现出来,把它们追加到单个 markdown 文件中。
如果用户没有传入路径,就问一次文档保存到哪里,然后在本次会话余下的时间里记住它。
从用户说的第一件事起就开始捕获片段,包括最初的提示。
首次写入时,在顶部放一个单独的 H1,写上一个暂定标题(它日后可以改),除此之外别放任何东西 —— 没有元数据、没有目录、没有日期。
</what-to-do><supporting-info>什么是片段
一个片段是任何一段可能存活到最终文章里的文本。它必须是_作者可读的_ —— 作者能看出它是什么意思 —— 但它不需要定义自己的术语,也不需要让一个陌生的读者看得懂。标准是"这是一段好文字吗?",而非"这是一个自成一体的论证吗?"
片段有意地是异质的。可以成为片段的东西的例子:
- 一句你想在某处用上、但还不知道用在哪里的犀利句子。
- 一个带一行论据的主张。
- 一个小场景:发生过的一件事、一段代码片段、一个情景、一个类比。
- 一个半成形的想法:"关于 X 感觉像 Y 的某种东西,日后再把它想清楚。"
- 一句引语、一段对话、一句无意中听到的话。
- 一组凭感觉聚在一起的相关观察。
- 一句抱怨、一句坦白、一个笑点。
- 一个引导词(leading word) —— 一个整篇文章都能挂靠其上的紧凑隐喻或自造词(一个命名那个想法的术语,就像 tracer bullets 或 fog of war 命名了一整套模式)。
在这些之中,引导词是最有价值、最值得拿下的片段。它是承重的:在探索阶段命名对了那一个,它就会在日后塑造结构、过渡和标题 —— 在整个发掘阶段持续产生红利。当对话反复绕着一个想法打转时,推动着去为它铸一个词。
小说家的日记是范本:多年未加结构的观察记录,日后被挖掘为原始素材。片段就是那些观察记录。
文件格式
# Working title
A first fragment lives here.
It can be multiple paragraphs. It can include lists, code, quotes — whatever
shape the fragment naturally takes.
---
A second fragment.
---
> A quoted line that the user wants to keep around.
A reaction to it.
---
- A cluster of related observations
- That hang together by feel
- And want to be near each other片段之间用一条水平分隔线(\n---\n)分隔。正文内没有标题。没有标签。除了添加的顺序之外没有别的顺序。
写作节奏
静默追加。不要为每个片段征求许可。顺带提一下你添加了什么("把那个加进去"),但不要用保存对话框打断谈话。
在每次写入之前:从磁盘重新读取文件。用户可能在两轮之间编辑、重排或删除了片段 —— 保留他们的改动。绝不覆盖文件;只追加(或者,如果用户要求,原地编辑某个特定片段)。
用户可以在任何时候说"砍掉最后一个""把那个重写得更犀利""把那两个合并"。把这些当作一等指令来对待。
</supporting-info>Other versions76 projects use a version of this.
Word for word · 0
None found.
Edited · 61
- mattpocock/skills★ 309k10% same
- vinvcn/mattpocock-skills-zh-CN★ 5.5k22% same
- InditexTech/weavejs★ 26610% same
- loulanyue/skills★ 23110% same
- tt-a1i/matt-skills-with-to-goal★ 19210% same
- VoDaiLocz/kilo-kit-mcp★ 2810% same
- metrogg/AgentHub★ 1910% same
- George-RD/design-studio★ 1010% same
- caterpi11ar/giclaw★ 910% same
- getmodern-ai/graft★ 910% same
51 more not listed
Wrote their own version · 15
- devcxl/mattpocock-skills-zh★ 522same name
- imMamdouhaboammar/matts-skills-into-chatgpt★ 8same name
- Boom-Vitt/skills-thai★ 5same name
- malinskibeniamin/skills★ 4same name
- miptah21/skills★ 2same name
- risadams/ink-and-agency★ 2same name
- birdmanmandbir/skills★ 1same name
- eszxcvfd/skills★ 1same name
- FuSheng-MG/Pi-Agent-skills★ 1same name
- Lesani/skills★ 1same name
5 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.
Used alongsideProjects with it also use batch-grill-me, obsidian-vault and 3 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.
boyingliu01Skillbatch-grill-me
A relentless interview that asks every frontier question at once, round by round. Thin alias of `grilling` (#540) — upstream mattpocock/skills absorbed this protocol into grilling; XP-Gate keeps this name as the sprint-flow Phase 2 entry point so orchestration docs stay stable.
Also in 5 projects that use this
simo97Skillobsidian-vault
Also in 20 projects that use this
getnaoSkillchief-of-staff
Also in 9 projects that use this
AWSSkillimplement-spec
Implement the result of /to-spec and /to-tickets in code.
Also in 20 projects that use this
FabienDehopreSkilldecision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Also in 3 projects that use this
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ask-mattSkill
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grill-with-docsSkill
- implementSkill
- improve-codebase-architectureSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- setup-matt-pocock-skillsSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- wizardSkill
- claude-handoffSkill
- loop-meSkill
- setup-ts-deep-modulesSkill
- writing-beatsSkill
- writing-shapeSkill
- git-guardrails-claude-codeSkill
- migrate-to-shoehornSkill
- scaffold-exercisesSkill
- setup-pre-commitSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- teachSkill
- to-questionnaireSkill
- wait-whatSkill
- writing-for-agentsSkill
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.

