agentleFS
YorkWong1995YorkWong1995/OPC-Harness/.claude/skills/review/SKILL.md

review

Skill4 starsChanged 6 months agoMITView on GitHub

Read pending diff, PRs, task results, or selected files and produce a structured review without modifying code.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, daily-arxiv 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

  • 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

  • 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

    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

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

The file

Files
SKILL.md

review

对 pending diff、PR、任务结果或指定文件做只读评审,识别阻塞问题、非阻塞建议和风险结论;该 skill 只输出评审意见,不直接修改代码或执行修复。

用法

/review <pending diff、PR、任务结果或文件范围>

目标

  • 找出会影响正确性、安全性、可维护性或验收结论的阻塞问题
  • 区分 blocking 与 non-blocking 建议,避免把风格偏好当作阻塞项
  • 用文件路径、行号、命令或 diff 片段支撑每条结论
  • 给出 pass / needs-work / needs-info 的明确评审结论

适用场景

  • 提交前需要检查 pending diff 是否满足任务目标
  • PR 或补丁需要独立只读评审
  • 任务结果需要核对范围、风险和验证证据
  • 指定文件需要检查潜在缺陷或文档漂移

不适用场景

  • 直接修改代码或文档
  • 代替 /bugfix 执行修复
  • 代替 /acceptance-check 给出最终 QA 验收
  • 在没有 diff、文件或任务结果的情况下猜测问题

输出分类规则

Blocking 问题

满足任一条件时列为 blocking,并使结论变为 needs-work:

  • 破坏任务验收标准、核心功能或已有回归测试
  • 引入安全风险、数据损坏、权限越界或高风险副作用
  • 缺少必要验证,导致关键路径无法判断是否可用
  • 改动范围明显超出任务目标,且可能影响无关模块
  • 文档、配置或入口变更会误导用户执行危险操作

每条 blocking 必须包含:问题描述、影响范围、证据引用、建议修正方向。

Non-blocking 建议

满足以下条件时列为 non-blocking,不单独阻止通过:

  • 命名、排版、重复代码或文档表达可改进,但不影响验收
  • 可读性、可维护性或测试覆盖可以增强,但当前实现仍满足目标
  • 后续优化项不属于本次任务范围
  • 风险较低且有明确原因说明可延后处理

每条 non-blocking 必须说明为什么不是 blocking。

风险判断

至少覆盖以下维度,并为每项给出 未发现 / 有风险 / 信息不足:

  • 正确性:逻辑、边界条件、状态流转是否匹配任务
  • 安全:输入、权限、命令、文件路径、敏感信息是否安全
  • 兼容性:旧配置、旧 artifacts、旧入口或用户工作流是否受影响
  • 测试:验证命令、测试数据和证据是否覆盖关键路径
  • 发布:是否涉及部署、迁移、回滚或外部系统副作用

结论规则

  • pass:未发现 blocking,且信息足以判断目标满足。
  • needs-work:存在至少一个 blocking,必须先修正再进入下一阶段。
  • needs-info:缺少任务目标、diff、文件内容或验证证据,无法可靠判断。

执行规则

  1. 先确认评审对象和任务目标;缺少目标时只做通用风险评审并标记 needs-info。
  2. 只读评审,不写入文件、不自动修复、不触发发布或外部副作用。
  3. 每条 blocking 问题必须说明影响、证据和建议修正方向。
  4. non-blocking 建议不得阻止通过,除非它会破坏验收标准或安全边界。
  5. 评审结论必须与问题分类一致:存在 blocking 时为 needs-work;信息不足时为 needs-info;无 blocking 时可为 pass。

示例

  • /review pending diff for tasks-p8.md review skill,检查是否只读且输出分类完整
  • /review PR #123,重点检查配置兼容性、测试证据和是否存在 blocking 问题
  • /review src/opc/workflow.py tests/test_metrics.py,判断 run_metrics cost 汇总是否满足任务验收

输出骨架

[示例:pass]
[评审对象] .claude/skills/review/SKILL.md pending diff
[任务目标/验收标准] 增加只读 review skill,包含分类规则、输出骨架和验收标准
[Blocking 问题]
- 未发现
[Non-blocking 建议]
- 可在后续索引文档中补充该 skill 的入口说明;不阻塞,因为当前任务只要求 SKILL.md
[风险判断]
- 正确性:未发现(证据:...)
- 安全:未发现(证据:...)
- 兼容性:未发现(证据:...)
- 测试:未发现(证据:...)
- 发布:未发现
[结论] pass
[后续动作] 可进入 QA 或下一任务

[示例:needs-work]
[评审对象] pending diff
[任务目标/验收标准] 增加只读 review skill,不应修改代码
[Blocking 问题]
- 问题:实现中修改了 runtime 代码但任务只要求 skill 文档
  影响:超出范围,可能引入未验证行为
  证据:src/opc/workflow.py:...
  建议修正方向:移出无关代码改动,单独建任务处理
[Non-blocking 建议]
- 未发现
[风险判断]
- 正确性:信息不足,runtime 改动无对应验收
- 安全:未发现
- 兼容性:有风险,改动范围超出任务
- 测试:信息不足,缺少对应测试
- 发布:未发现
[结论] needs-work
[后续动作] 退回 Engineer 拆分无关改动并补验证

验收标准

  • 示例覆盖 pass 和 needs-work 两种结论
  • 输出骨架包含评审对象、任务目标、blocking、non-blocking、风险判断、结论和后续动作
  • blocking 问题必须包含影响、证据和建议修正方向
  • pass 结论不得包含未处理 blocking

验收

  • 明确 review 是只读评审,不直接修改代码
  • 输入覆盖 pending diff、PR、指定文件和任务结果
  • 输出包含 blocking、non-blocking、风险判断和明确结论
  • 每条问题或建议都要求引用文件路径、行号、命令或 diff 证据

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.