agentleFS
popsiclelmlmpopsiclelmlm/skills-cn/skills/in-progress/review/SKILL.md

review

Skill0 starsChanged 6 months agoMITView on GitHub

沿两个轴 review 从固定点(commit、branch、tag 或 merge-base)以来的变更:Standards(code 是否遵循此 repo 已记录的 coding standards?)和 Spec(code 是否匹配来源 issue/PRD 的要求?)。在并行 sub-agents 中运行两个 reviews,并并排报告。当用户想 review branch、PR、work-in-progress changes,或要求 "review since X" 时使用。

192 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images 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

    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 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Commit messages 中的 issue references(#123、Closes #45、GitLab !67 等)— 通过 docs/agents/issue-tracker.md 中的 workflow 获取。

    line 29

“Common” is measured: kept by at least 6 in 10 of the 157 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review

对 HEAD 和用户提供的固定点之间的 diff 做双轴 review:

  • Standards — code 是否符合此 repo 已记录的 coding standards?
  • Spec — code 是否忠实实现了来源 issue / PRD / spec?

两个轴都作为 parallel sub-agents 运行,避免彼此污染 context,然后此 skill 聚合它们的 findings。

Issue tracker 应该已经提供给你;如果缺少 docs/agents/issue-tracker.md,运行 /setup-matt-pocock-skills。

Process

1. Pin the fixed point

用户说的任何东西都是 fixed point:commit SHA、branch name、tag、main、HEAD~5 等。不要有自己的偏好,直接传递。如果他们没有指定,询问:"Review against what — a branch, a commit, or main?" 拿到 fixed point 前不要继续。

记录一次 diff command:git diff <fixed-point>...HEAD(three-dot,所以比较对象是 merge-base)。同时用 git log <fixed-point>..HEAD --oneline 记录 commits list。

2. Identify the spec source

按以下顺序寻找 originating spec:

  1. Commit messages 中的 issue references(#123、Closes #45、GitLab !67 等)— 通过 docs/agents/issue-tracker.md 中的 workflow 获取。
  2. 用户作为 argument 传入的 path。
  3. docs/、specs/ 或 .scratch/ 下匹配 branch name 或 feature 的 PRD/spec file。
  4. 如果什么都没找到,询问用户 spec 在哪里。如果他们说没有,Spec sub-agent 会跳过并报告 "no spec available"。

3. Identify the standards sources

Repo 中任何记录 code 应如何编写的东西。常见位置:

  • CLAUDE.md、AGENTS.md
  • CONTRIBUTING.md
  • CONTEXT.md、CONTEXT-MAP.md、per-context CONTEXT.md files
  • docs/adr/(architectural decisions 也是 standards)
  • .editorconfig、eslint.config.*、biome.json、prettier.config.*、tsconfig.json(machine-enforced standards:记录它们,但不要重复检查 tooling 已检查的内容)
  • repo root 或 docs/ 下任何 STYLE.md、STANDARDS.md、STYLEGUIDE.md 或类似文件

收集 files list。Standards sub-agent 会读取它们。

4. Spawn both sub-agents in parallel

发送一条包含两个 Agent tool calls 的 message。两者都使用 general-purpose subagent。

Standards sub-agent prompt — 包含:

  • 完整 diff command 和 commit list。
  • Step 3 找到的 standards-source files list。
  • Brief:"Read the standards docs. Then read the diff. Report — per file/hunk where relevant — every place the diff violates a documented standard. Cite the standard (file + the rule). Distinguish hard violations from judgement calls. Skip anything tooling enforces. Under 400 words."

Spec sub-agent prompt — 包含:

  • Diff command 和 commit list。
  • Spec 的 path 或 fetched contents。
  • Brief:"Read the spec. Then read the diff. Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line for each finding. Under 400 words."

如果 spec 缺失,跳过 Spec sub-agent,并在 final report 中说明。

5. Aggregate

在 ## Standards 和 ## Spec headings 下展示两个 reports,逐字或轻微清理。不要 merge 或 rerank findings:两个轴刻意分开,方便用户独立查看。

以一句 summary 收尾:每个轴的 findings 总数,以及最严重的单个 issue(如有)。

Why two axes

一个 change 可能通过一个轴而失败在另一个轴:

  • Code 遵循所有 standards,但实现了错误东西 → Standards pass, Spec fail.
  • Code 准确完成 issue 要求,但破坏了项目 conventions → Spec pass, Standards fail.

分开报告能防止一个轴遮蔽另一个轴。

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.