to-spec
Skill27 starsChanged 3 months agoMITView on GitHub
把当前对话转化为一份规格说明,并发布到项目工单跟踪器——无需访谈,只是综合你们已经讨论过的内容。
Files
这个技能拿当前对话上下文和对代码库的理解,产出一份规格说明。不要访谈用户——只综合你已经知道的东西。
工单跟踪器和分诊标签词汇应当已经提供给你——如果没有,运行 /setup-matt-pocock-skills。
流程
- 探索仓库以理解代码库的当前状态(如果你还没做)。在整份规格里使用项目的领域词汇表词汇,并尊重你正在触碰的区域里的任何 ADR。
- 勾画出你打算在其处测试这个功能的接缝。已有接缝应优先于新接缝。用尽可能高的接缝。如果需要新接缝,就在你能做到的最高点提出它们。跨代码库的接缝越少越好——理想数量是一个。
与用户核对这些接缝是否符合他们的预期。
- 用下面的模板写规格,然后把它发布到项目工单跟踪器。应用
ready-for-agent分诊标签——无需额外分诊。
<spec-template>Problem Statement
用户正面临的问题,从用户的视角出发。
Solution
对这个问题的解决方案,从用户的视角出发。
User Stories
一个长长的、带编号的用户故事列表。每个用户故事都应采用如下格式:
- As an
<actor>, I want a<feature>, so that<benefit>
<user-story-example>
1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending
</user-story-example>这个用户故事列表应当极其详尽,覆盖该功能的所有方面。
Implementation Decisions
一个做出的实现决策列表。它可以包括:
- 将要构建/修改的模块
- 那些模块中将被修改的接口
- 来自开发者的技术澄清
- 架构决策
- schema 变更
- API 契约
- 具体的交互
不要包含具体的文件路径或代码片段。它们可能很快就过时。
例外:如果一个原型产出了一个比散文更精确地编码了某个决策的片段(状态机、reducer、schema、类型形状),就把它内联进相关决策,并简要注明它来自一个原型。修剪到富含决策的部分——不是一个可运行的演示,只是重要的那些位。
Testing Decisions
一个做出的测试决策列表。包括:
- 一段关于什么是好测试的描述(只测外部行为,不测实现细节)
- 哪些模块将被测试
- 测试的先例(即代码库里类似类型的测试)
Out of Scope
一段关于这份规格范围之外的东西的描述。
Further Notes
关于这个功能的任何进一步说明。
</spec-template>Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- vinvcn/mattpocock-skills-zh-CN★ 5.5k16% same
- T-miracle/codex-skills-zh★ 526% same
- longfangsong/skills★ 213% same
- addie-ace/dsh-mattpocock-skills★ 012% same
Wrote their own version · 190
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
- moeru-ai/xsai★ 665same name
- DanMcInerney/architect-loop★ 626same name
- nodetool-ai/nodetool★ 603same name
- stevesolun/ctx★ 583same name
180 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 implement-spec.
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.
AWSSkillimplement-spec
Implement the result of /to-spec and /to-tickets in code.
Also in 60 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-ticketsSkill
- triageSkill
- wayfinderSkill
- wizardSkill
- claude-handoffSkill
- loop-meSkill
- setup-ts-deep-modulesSkill
- writing-beatsSkill
- writing-fragmentsSkill
- 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.

