跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 meticulous-review

Meticulous Review

分析完成 Meticulous test run——将diffs与PR描述相提并论,以了解预期结果,然后专注于寻找并标出潜在的回归. 由本地 repo 当前的承诺(默认),或从明确的测试运行的ID或承诺SHA中决定测试运行. 当被请求审查 Meticulus 测试结果时使用, 当婴儿为牵引/相接请求的 Meticulus Tests CI 检查时使用, 或者当执行前端测试后立即改变自己 .

8825 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

分析完成 Meticulous test run——将diffs与PR描述相提并论,以了解预期结果,然后专注于寻找并标出潜在的回归. 解析从本地 Repo 当前承诺( 默认) 或从明确的测试运行 ID 或 执行 SHA 中运行的测试

何时用

要求审查 Meticulus 测试结果, 当婴儿照顾拉出/相接请求的 Meticulus Tests CI 检查, 或在进行前端修改后右侧

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Step 0 -- Establish what's expected、Step 1 -- Get the replay diff summary、CLI (infers the run from local git HEAD)、MCP (git context is never inferred — resolve the testRunId from a commit first)、Step 2 -- Get screenshot images、CLI (downloads images to ~/.meticulous/agent-images/ and prints local paths)。 其中含规范建议的小节:分步指令。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Analyze a completed Meticulous test run — compare the diffs against the PR description to see what's expected, then focus on finding and flagging potential regressions. Resolves the test run from the local repo's current commit (the default), or from an explicit test-run ID or commit SHA. Use when asked to review Meticulous test results, when babysitting a pull/merge request's Meticulous Tests CI check, or right after implementing a frontend change yourself.

Step 0 -- Establish what's expectedStep 1 -- Get the replay diff summaryCLI (infers the run from local git HEAD)MCP (git context is never inferred — resolve the testRunId from a commit first)Step 2 -- Get screenshot imagesCLI (downloads images to ~/.meticulous/agent-images/ and prints local paths)MCP (no download-to-disk tool — returns signed URLs instead; fetch them to view the images)Step 3 -- Inspect the DOM diff (for structural detail)CLIMCPStep 4 -- Get the replay timeline (optional, for diagnosing unexpected diffs)CLI

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
meticulous-review
description
Analyze a completed Meticulous test run — compare the diffs against the PR description to see what's expected, then focus on finding and flagging potential regressions. Resolves the test run from the local repo's current commit (the default), or from an explicit test-run ID or commit SHA. Use when asked to review Meticulous test results, when babysitting a pull/merge request's Meticulous Tests CI check, or right after implementing a frontend change yourself.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「meticulous-review」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-c79ee299883b8644-%E5%B1%85%E4%B8%AD%E8%AF%84%E8%AE%BA.html
请存为 .cursor/skills/meticulous-review/SKILL.md 或 .claude/skills/meticulous-review/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/alwaysmeticulous/skills' --list

npx skills add 'https://github.com/alwaysmeticulous/skills' --skill 'meticulous-review'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: meticulous-review description: Analyze a completed Meticulous test run — compare the diffs against the PR description to see what's expected, then focus on finding and flagging potential regressions. Resolves the test run from the local repo's current commit (the default), or from an explicit test-run ID or commit SHA. Use when asked to review Meticulous test results, when babysitting a pull/merge request's Meticulous Tests CI check, or right after implementing a frontend change yourself. user-invocable: true --- To review a Meticulous test run, follow the workflow below step by step, using the CLI or MCP commands as described. > Before starting, run the `meticulous-cli-update` skill to ensure the Meticulous CLI and skills are up to date — unless it has already run earlier in this conversation, in which case skip it. This skill treats you as a **reviewer, not the implementer** — even if you did write the change earlier in this conversation. Its job is to catch regressions, not to iterate on the implementation (if you're mid-implementation and want to loop against Meticulous until things look right, see the `meticulous-iterative-dev` skill for feature work with intended visual changes, or the `meticulous-zero-diff-task` skill when the UI must not change; if diffs have already been reviewed and rejected and you're just here to fix what's flagged, see the `meticulous-fix` skill). ## Step 0 -- Establish what's expected Before looking at any diff, work out what visual change this PR is _supposed_ to produce: - **If you already have full context** (same conversation that implemented the change, or the user just described the task), use that. - **Otherwise** — fetch the PR description (e.g. `gh pr view --json title,body` for GitHub, `glab mr view --output json --jq '{title,description}'` for GitLab, or `GET /2.0/repositories/{workspace}/{repo_slug}/pullrequests/{id}?fields=title,description` for Bitbucket) and pull out a brief bullet-point summary of any visual changes it calls out as expected. - If it doesn't mention any, note that explicitly — every diff below then gets extra scrutiny, since there's nothing on record it could be a known, accepted consequence of. ## Step 1 -- Get the replay diff summary Run from the local checkout to resolve the test run from the current commit's git HEAD — make sure HEAD matches the remote head CI ran on first (e.g. `git pull`), or you may review a stale or missing run: ```bash # CLI (infers the run from local git HEAD) meticulous agent test-run-diffs # MCP (git context is never inferred — resolve the testRunId from a commit first) get_test_run_for_commit(commitSha="") get_test_run_diffs(testRunId="") ``` Returns a TSV of `replayDiffId`/`screenshotName` rows — a representative, priority-ordered subset of real visual differences; work through them top to bottom. To target a run explicitly instead of resolving from HEAD, pass `--testRunId ` or `--commitSha `. The CLI blocks until the run finishes by default (pass `--dontWaitForTestRunToComplete` to instead report an in-progress run and exit immediately); MCP never blocks, so keep polling until `status` is `complete`/`failed`. Every returned row must be matched against Step 0 or flagged (see the Decision guide) before concluding the PR is good. ## Step 2 -- Get screenshot images For each representative screenshot: ```bash # CLI (downloads images to ~/.meticulous/agent-images/ and prints local paths) meticulous agent image-files --replayDiffId --screenshotName # MCP (no download-to-disk tool — returns signed URLs instead; fetch them to view the images) get_image_urls(replayDiffId="", screenshotName="") ``` Open (or fetch) `before`, `after`, and `diffImage` to inspect the change — `diffImage` is usually the most informative, highlighting exactly which pixels changed. Always inspect the images, even when the DOM diff looks clear. ## Step 3 -- Inspect the DOM diff (for structural detail) ```bash # CLI meticulous agent dom-diff --replayDiffId --screenshotName # MCP get_dom_diff(replayDiffId="", screenshotName="") ``` Optional: `--context ` (CLI) controls how many context lines surround each hunk (default 3). Output is a unified diff (`+`/`-`, indentation stripped), one `[diff N]`-headed block per independent change — for example (illustrative, not real output): ``` [diff 0]
- old label + new label
[diff 1]
    +
  • new item
``` ## Step 4 -- Get the replay timeline (optional, for diagnosing unexpected diffs) If a diff is unexpected and the images/DOM don't make it obvious why: ```bash # CLI meticulous agent timeline-diff --replayDiffId # MCP get_timeline_diff(replayDiffId="") ``` TSV columns: `diff` (` ` identical, `-` removed, `+` added, `!` changed), `timeMs`, `event` (`user`/`screenshot`/`network`/`console`/etc.), `description`. Look for failed network requests, unexpected redirects, or timing anomalies that could explain a visual change. ## Step 5 -- Decision guide For each representative screenshot, compare the diff image and DOM diff against Step 0's expectations: - **Expected** — matches one of Step 0's expected changes (or, with full implementation context, is clearly a desired outcome). Check the diff actually looks like _that_ change and nothing more — a diff can be expected in kind but still carry an extra, unrelated regression bundled into the same screenshot. Nothing to flag. - **Unintended** — not accounted for by Step 0. Use the timeline to rule out failed requests, redirects, or other anomalies, then flag it: - **Potential regression** (a real side effect, or otherwise clearly wrong) → **reject**. - **Unrelated to the change under review** — typically a flake, e.g. subpixel rendering noise or animation non-determinism → **ignore**. Either way it's flagged, not silently dropped — a human still needs to see it. **This skill reviews and flags — it does not fix.** Hand a rejected diff off to the `meticulous-fix` skill (or the person/skill implementing the change) — don't attempt code changes here. ## Step 6 -- Flag the diff ```bash # CLI meticulous agent reject-diff --replayDiffId= --screenshotName= --reason="" --x=<0..1> --y=<0..1> meticulous agent ignore-diff --replayDiffId= --screenshotName= --reason="" --x=<0..1> --y=<0..1> meticulous agent create-diff-comment --replayDiffId= --screenshotName= --text="" --x=<0..1> --y=<0..1> # MCP reject_diff(replayDiffId="", screenshotName="", reason="", x=<0..1>, y=<0..1>) ignore_diff(replayDiffId="", screenshotName="", reason="", x=<0..1>, y=<0..1>) create_diff_comment(replayDiffId="", screenshotName="", text="", x=<0..1>, y=<0..1>) ``` Call `reject-diff` or `ignore-diff` for **every** diff classified as unintended, in addition to including it in the final report. `--reason` is the succinct explanation from your classification above; `--x`/`--y` are the approximate normalized coordinates of the changed region, estimated from the diff image. `create-diff-comment` is the neutral option for anything you want on the record without a verdict. **Not symmetric:** `reject-diff` writes a real, blocking decision, same as a human rejection. `ignore-diff` decides nothing — it's a comment only, so the diff stays `unreviewed` and the check stays pending either way. Only a human can clear a diff, so don't oversell an `ignore-diff` call in your final report as having resolved anything. ## Step 7 -- Final report Cover **all significant visual changes**. 1. **Expected changes** — brief, a line or two each: what changed and which Step 0 expectation it matches. 2. **Flagged diffs** (if any) — the main point of the review, so give these the most detail: `replayDiffId`/`screenshotName` (linked: `https://app.meticulous.ai/test-runs//replay-diff/?screenshot=`), whether you rejected or ignored it, the reason you gave when flagging it (Step 6), what the change looks like, and your best assessment of the cause. The PR is only good when every diff has been matched or flagged. If any diff is flagged, the PR is not yet good: surface it clearly to the user in addition to the flag itself. ## Step 8 -- Report feedback to Meticulous **Always do this as the last step — it's part of the review itself, not something the user has to ask for.** Submit one brief note: did Meticulous catch a real problem, was anything confusing, what would have made the review easier. Positive feedback counts too — this isn't just for reporting friction. ```bash # CLI meticulous agent submit-feedback --message="" --outcome= --testRunId= --skill=meticulous-review # MCP submit_feedback(message="", outcome="", testRunId="", skill="meticulous-review") ```

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…