to-tickets
Skill5 starsChanged 3 months agoMITView on GitHub
将 plan、spec 或当前对话按用户选择的场景拆分或垂直切片模式组织为 tickets,声明 blocking edges 与验收验证要求,并发布到已配置 tracker。
192 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- anorth/agent-skillstheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
- 5thlayer/skillworkstheir own version, first seen Nov 8, 2026
- dfirmin/compasstheir own version, first seen Nov 8, 2026
- zhikedan/mattpocock-skills-dshtheir own version, first seen Nov 8, 2026
- dhruvsaxena1998/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use setup-ts-deep-modules, to-questionnaire and 8 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.
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 43 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 89 projects that use this
ryotaroh180105Skillclaude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
Also in 40 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 47 projects that use this
AWSSkillwizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Also in 108 projects that use this
sponge-b0bSkillto-specs
Project decision-complete planning into implementation Specs from exact Canonical Contract Ledger semantics while preserving Independent Specs and existing Spec identity.
Also in 3 projects that use this
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- WenWuZhiDao/mattpocock-skills-zh★ 2720% same
- addie-ace/dsh-mattpocock-skills★ 019% same
Wrote their own version · 190
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
- moeru-ai/xsai★ 667same name
- nodetool-ai/nodetool★ 615same 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.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- documenting-codeSkill
- implementSkill
- implement-specSkill
- integrating-frontend-apisSkill
- organizing-frontend-componentsSkill
- prototypeSkill
- tddSkill
- writing-vue-componentsSkill
- researchSkill
- teachSkill
- writing-for-agentsSkill
- codebase-designSkill
- domain-modelingSkill
- grill-with-docsSkill
- to-specSkill
- code-reviewSkill
- diagnosing-bugsSkill
- improve-codebase-architectureSkill
- retroSkill
- ask-mattSkill
- execute-planSkill
- git-commitSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- prSkill
- setup-matt-pocock-skillsSkill
- triageSkill
- usage-disclosureSkill
- wait-whatSkill
- wayfinderSkill
The file
Files
转换为工单(To Tickets)
将计划、规格或对话组织为工单(tickets),由用户选择场景拆分(user scenarios)或垂直切片(tracer-bullet vertical slices)。两种模式共用验收、测试和依赖规则,均保留关键行为、异常路径和回归覆盖。
你应当已经获得议题跟踪器和分诊标签词汇;如果没有,提醒用户运行 /setup-matt-pocock-skills。
流程
1. 确认模式与收集上下文
用户在本次请求中已明确指定模式,或本次规划已有明确选择时,直接沿用。否则先使用可用的询问窗(如 request_user_input_async)提供两个选项,并等待用户选择:
| 模式 | 拆单单位与取舍 |
| 场景拆分 | 一个完整用户场景包含多个紧密相关的行为,减少重复上下文和调度成本 |
| 垂直切片 | 一条狭窄但完整的端到端路径独立成单,便于细粒度交付和验证 |
没有询问窗时用文字询问。预选项、未回复或超时均不算选择,不自动采用默认模式。等待期间可以收集上下文和探索代码库,收到选择前不进入工单起草或发布。
选择仅在本次规划内有效,多轮修改沿用;用户明确切换时,按新模式重新组织草案并保留全部需求与验证要求。新的规划重新确认模式,不从上一次规划继承。
以对话上下文中已有的内容为基础开展工作。如果用户通过参数传入引用(规格路径、议题编号或 URL),就获取该引用并阅读其完整正文和评论。
2. 探索代码库(可选)
如果尚未探索代码库,就先了解代码的当前状态。工单标题和描述应当使用项目领域词汇表(domain glossary)中的词汇,并遵守所涉及区域的 ADR。
识别实现当前需求所必需的预重构(prefactor),结合共享代码、现有测试和受影响的调用方判断工单边界。
3. 按所选模式起草工单
仅应用所选模式的粒度规则,再应用下方共用规则。小需求可以只有一张工单,不设置固定工单数量。
场景拆分
每张工单围绕一个完整用户场景,可以包含多个紧密相关的操作,覆盖实现该场景所需的相关层(模式、API、UI、测试),完成后可端到端演示或验证。共享实现和上下文、共同验收的行为优先合并。
只有以下理由支持继续拆分;在方案中说明具体依据:
- 存在真实前置依赖,需要分阶段推进。
- 存在明确的独立交付或并行实施价值,收益超过重复上下文、调度和集成成本。
- 场景过大,单个智能体难以在一个全新的上下文窗口中可靠完成实现和验证;以需同时理解的业务规则、共享模块或验证范围等具体证据说明容量风险。
多个按钮、接口、技术层、异常分支或测试用例本身均不构成拆单理由。没有上述依据时停止拆分。
垂直切片
- 每张工单沿相关层(模式、API、UI、测试)打通一条狭窄但完整的端到端路径,以可独立交付的行为为边界。
- 每个切片完成后本身可以演示或验证,规模能装入一个全新的上下文窗口。
- 同一用户场景中的不同端到端行为可以分别成单,无需满足场景模式的合并优先及三项继续拆分条件;仍不能按技术层或单个测试用例机械拆单。
共用的预重构与依赖规则
工单内仍可小步实现和测试,测试粒度不决定工单粒度。仅服务于当前工单的小范围预重构并入该工单,在依赖它的实现前完成;多张工单共同依赖的必要重构才单独作为前置工单。两种模式均不要求所有预重构统一先完成。
为每个工单指定其阻塞边(blocking edges):只列开始前必须完成的其他工单,不把建议顺序写成硬依赖。没有阻塞项的工单可以立即开始。
**广域重构(wide refactors)是两种模式共用的例外。重命名列、重新定义共享符号类型等机械变更,如果其爆炸半径(blast radius)使端到端切片无法独立保持 CI 通过,就按扩展—收缩(expand–contract)**排序:先添加与旧形式兼容的新形式;再按包或目录分批迁移调用方,每批依赖扩展工单,并保持 CI 通过;最后删除旧形式,该工单依赖所有迁移批次。若单独批次仍无法保持 CI 通过,则共用集成分支,保留该顺序,并让所有批次及收缩工单阻塞最终的“集成并验证”工单,仅在该处承诺 CI 通过。
共用的验收与验证
- 给验收标准编号,逐项写明可观察的预期结果和验证方式。合并工单时保留所有行为要求,适合自动化的行为使用自动化测试;需人工验证时说明操作与预期结果。
- 按风险覆盖关键行为、异常与边界路径,以及受影响的已有行为和共享调用方的回归。可复用现有测试,并让同一测试覆盖多个验收项,但须明确对应关系。
- 每张工单完成时运行受影响范围的检查并记录结果。多工单功能在承担集成交付的工单中指定跨工单验证及其阻塞项;只有存在独立集成门槛时才另建验证工单。
- 在仓库和执行技能允许的范围内合并重复验证,不为每个小行为重复启动整套测试。全量测试服从现有仓库及执行技能门禁;本技能的规划不能豁免这些要求。
完成标准:工单粒度符合用户所选模式,所有需求均有工单承接,所有验收项均有验证方式,拆分理由和真实阻塞关系明确,整体交付的验证责任已落实。
4. 询问用户
先标明当前所选模式,再以编号列表呈现建议的拆分方案。每个工单都要显示:
- 标题(Title):简短的描述性名称
- 阻塞项(Blocked by):必须先完成哪些其他工单(如果有)
- 交付内容(What it delivers):该工单实现的端到端行为
- 拆分依据(Why separate):多工单时说明独立成单的理由
- 验收与验证(Acceptance and verification):验收项与验证方式、风险覆盖及整体验证归属
询问用户:
- 粒度是否合适?(过粗或过细)
- 阻塞边是否正确:每个工单是否只依赖真正构成其门槛的工单?
- 是否应当合并某些工单或进一步拆分?
- 关键行为、异常路径和回归验证是否完整?
持续迭代,直到用户批准拆分方案。
5. 将工单发布到已配置的跟踪器
发布已经批准的工单。具体方式取决于 /setup-matt-pocock-skills 配置的跟踪器:无论哪种方式,工单本身都相同,只有阻塞边的表现形式不同:
- 本地文件(Local files) → 在
.scratch/<feature-slug>/issues/<NN>-<slug>.md下为每个工单写一个文件,并从01开始按依赖顺序编号(阻塞项优先)。每个文件的 “Blocked by” 列出它所依赖工单的编号和标题。使用下方逐工单文件模板:每个文件只放一个工单,绝不要写成单一合并文件。 - 真实议题跟踪器(GitHub、Linear 等) → 按依赖顺序(阻塞项优先)为每个工单发布一项议题,使每个工单的阻塞边能够引用真实标识符。平台支持时使用原生阻塞关系;否则将每个工单的 “Blocked by” 设置为阻塞议题。如果输入来自已有议题,按跟踪器文档中的操作将每个工单关联为它的子议题。除非另有指示,否则应用
ready-for-agent分诊标签:这些工单按设计就可以由智能体领取。
处理前沿(frontier):即所有阻塞项都已完成的任何工单。对于纯线性链,这意味着从上到下处理。
除上述子议题关联外,不要关闭或修改任何父议题。
<local-ticket-template><NN>: <Ticket title>
What to build: the end-to-end behaviour delivered by this ticket at the chosen granularity: a complete user scenario or a narrow vertical slice.
Blocked by: the numbers/titles of the tickets that gate this one, or "None (can start immediately)".
Status: ready-for-agent
- AC1: observable behaviour and expected result
- AC2: observable behaviour and expected result
Verification: map every AC to an automated test or a manual check with expected results; include risk-based error, boundary and regression coverage. State the affected checks and any assigned cross-ticket integration checks. Record results when completing the ticket; preserve repository and execution-skill test gates.
</local-ticket-template><issue-template>Parent
A reference to the parent issue on the tracker (if the source was an existing issue, otherwise omit this section).
What to build
The end-to-end behaviour delivered by this ticket at the chosen granularity: a complete user scenario or a narrow vertical slice.
Acceptance criteria
- AC1: observable behaviour and expected result
- AC2: observable behaviour and expected result
Verification
Map every AC to an automated test or a manual check with expected results; include risk-based error, boundary and regression coverage. State the affected checks and any assigned cross-ticket integration checks. Record results when completing the ticket; preserve repository and execution-skill test gates.
Blocked by
- A reference to each blocking ticket, or "None (can start immediately)". Omit this section when blockers were set as native edges.
</issue-template>无论采用哪种形式,都要避免具体文件路径或代码片段:它们很快就会过时。例外:如果原型生成的片段能够比文字更精确地表达某项决策(状态机、reducer、模式、类型形状),就将其内联,并简要注明它来自原型。只保留承载决策的部分:不要放入可运行演示,只保留重要内容。
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.

