agentleFS
Sign inStart free
devcxldevcxl/mattpocock-skills-zh/skills/engineering/implement-spec/SKILL.md

implement-spec

Skill522 starsChanged 36 days agoMITView on GitHub

在代码中实现 /to-spec 与 /to-tickets 的产物。

107 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use implement-spec-with-codex, close-spec and 10 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.
  • dzhngSkill

    implement-spec-with-codex

    Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.

    Also in 4 projects that use this

  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 4 projects that use this

  • wolverin0Skill

    audit-decisions

    Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

    Also in 4 projects that use this

  • saffron-healthSkill

    get-pr-reviews

    Get nicely formatted output of the last review comments on a PR. Used internally by other skills.

    Also in 3 projects that use this

  • saffron-healthSkill

    push-everything

    Stage ALL changes in the repository (not just session changes), commit, and push. Use when you need to commit all pending changes.

    Also in 3 projects that use this

  • transitive-bullshitSkill

    compare-screenshots

    Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

    Also in 4 projects that use this

  • +5 more from dzhng

The file

Create a free account to mount
Files
SKILL.md

你已被提供一份 spec。该 spec 应关联若干 ticket，用以描述如何实现该 spec。

应该已经为你提供了 issue 跟踪器。如果没有，请告诉用户运行 /setup-matt-pocock-skills。

目标是整份 spec 在一条集成分支上实现完成，每张 ticket 都按 issue 跟踪器关闭工作的方式解决。

这些 ticket 不是一份步骤清单。它们是一张任务图，彼此之间存在阻塞关系。这意味着始终存在一个前沿（frontier）：可立即被领走的 ticket。

每个子智能体都应从一个全新的上下文窗口开始。

与子智能体之间的通信应保持精简。通信主要通过上下文指针：指向 spec、ticket、研究笔记与历史 commit。无需重复指针已经能触达的信息。

实施者子智能体应尽可能在后台运行，以获得最大并发。

步骤

  1. 阅读 spec 与 ticket，理解任务图。
  2. （可选）使用一个探查子智能体完成 ticket 所需的探查工作：相关的代码库文件或外部文档。确保该探查子智能体能够保存文件：它应把 Markdown 笔记保存在仓库之外、所有后续子智能体都能访问的目录中。这让实施者子智能体可以专心实现，而非探查。
  3. 创建集成分支。如果 issue 跟踪器通过 PR 关闭工作，或者用户要求一个 PR，则在步骤 5 的第一次合并之后开一个 draft PR（一个在 main 之上没有 commit 的分支开不了 PR），并标记为关闭对应的 spec 与 ticket。
  4. 每张 ticket 都使用一个全新的实施者子智能体来实现，每个都在自己的 worktree、自有的分支上工作。每个实施者子智能体：
    • 开始前先确认其 worktree 基于集成分支，如果不是则重置到该分支；
    • 调用 Skill 工具并传入 tdd 来构建 ticket；
    • 在报告完成之前，把集成分支的顶部合并进自己的分支。
  5. 一旦某个实施者子智能体完成，使用一个合并子智能体将其工作合并进集成分支。
  6. 如果这改变了可领取 ticket 的前沿，立刻启动更多实施者子智能体去处理新出现的 ticket。这保证了最大并发。
  7. 所有 ticket 完成后，对集成分支调用 Skill 工具并传入 code-review。用一个全新的实施者子智能体一次性修复 code review 提出的全部问题。
  8. 如果存在 draft PR，将它标记为 ready for review。否则，按 issue 跟踪器关闭工作的方式逐张解决 ticket，并报告集成分支。
  9. 清理所有实施者子智能体的 worktree。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free