小白指挥AI干活之复审只挑真毛病

SKILL开发
开发 未标注权限 许可证不明确
安装这个技能

在让 AI 复审任何东西(代码、方案、文档、合同)、收到复审意见要判断哪些该改、或发现多个会话互相修改格式措辞而正事不动(一直在搞文档治理不推进正事)时使用。强制实质性标准:每条意见必须答得上"不改会坏什么",措辞找茬不算发现,"没有问题"是合法结论;连续两轮交付物零变化必须报警。/ Use when asking an AI to review anything (code, plan, doc, contract), receiving findings, or when sessions churn meta-work (format fixes, review-of-review) while the deliverable sits untouched. Findings must name what breaks or gets rebuilt; nitpicks rejected; zero-findings is a legitimate verdict; every round must move the deliverable, not the paperwork about it.

一句话选型结论

按资料字段整理

小白指挥AI干活之复审只挑真毛病是开发类的 Agent Skill,安装方式未标注,权限级别未标注,许可证不明确,有可直接复制的安装命令。技能本质是给模型读的说明书,效果取决于模型与客户端;装完先用一个小任务验证,再放进正式流程。

分类开发 安装方式未标注 权限级别未标注权限 许可证许可证不明确
累计安装 未标注 本周 未标注
GitHub 星标 未标注 仓库 未标注
下载量 未标注 技能市场下载数
权限级别 未标注权限 安装前请确认风险范围
许可证 许可证不明确 未说明

安装

未标注
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
skillhub install user_f274b691/reviewing-for-substance
  1. 1
    确认客户端支持

    确认你的客户端支持 Skills(Claude、Codex、Cursor 等),并升级到较新的版本。

  2. 2
    拿到技能文件

    执行上面的命令安装;也可以把仓库里的 SKILL.md 手动放进客户端的 skills 目录。

  3. 3
    刷新技能列表

    重新打开客户端,或刷新技能列表,让新放进来的技能被加载。

  4. 4
    验证是否生效

    问一句「你有哪些技能」,确认列表里出现它,再拿一个小任务试跑。

技能档案

开发
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方user_f274b691仓库 未标注 · 版本 未标注
宿主客户端未标注技能可被这些客户端加载
安装方式未标注安装包 community
权限级别未标注权限安装前请确认风险范围
许可证未说明许可证不明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验未标注上游最后核验时间 · 数据更新 1791621972
正文体量8.6 KBSKILL.md 原文大小,越大说明说明书写得越细

典型使用场景

3 类
按分类整理的常见用法,具体以 SKILL.md 为准
写代码与改 bug

按需求补代码、定位并修掉报错。

读仓库与生成改动

让模型读懂项目结构,再给出可落地的改动。

跑测试与排查故障

按现象排查问题,补测试用例并复跑。

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有可直接复制的安装命令,不用自己翻文档找入口。

先想清楚的地方

  • 没有标注权限级别,实际能做什么要装好后确认。
  • 许可证不明确,商用或二次分发前先到仓库确认条款。
  • 没有做站内核验,内容以作者仓库为准。
  • 技能只是说明书,实际效果取决于模型与客户端,装完先用小任务试一遍。

更适合

  • 需要在开发场景里给模型补一套做法的人。
  • 愿意先读一遍 SKILL.md、确认它会让模型做什么的人。

不太适合

  • 对许可证要求很严、必须明确可商用的人。
  • 只想装完就自动变强、不打算看说明书的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
技能权限级别安装方式累计安装宿主客户端安装命令
小白指挥AI干活之复审只挑真毛病当前 未标注权限 未标注 未标注 未标注 有
技能审查员 浏览器控制 ClawHub 市场 877.9 万 OpenClaw 有
Vercel React 最佳实践 浏览器控制 GitHub 仓库 849.1 万 Codex、Claude、Cursor 有
GitHub 代码协作 联网访问 ClawHub 市场 763.3 万 OpenClaw 有
网页设计指南 联网访问 GitHub 仓库 668.6 万 Codex、Claude、Cursor 有
本体论 只读 ClawHub 市场 663.7 万 OpenClaw 有

SKILL.md 全文

8.6 KB
模型实际读到的说明书原文,来自技能仓库

Reviewing for Substance

Core Rule

Progress is measured on the deliverable, never on the documents about the deliverable. Two tests, applied relentlessly:

  • For any review finding: 这条不改,什么会坏、什么会返工? No answer → not a finding.
  • For any round of work: 这一轮结束,交付物本身前进了什么? No answer → not progress, whatever got edited.

AI has two ways of looking busy without being useful: manufacturing review findings to seem thorough, and polishing meta-artifacts (formats, structures, phrasings, documents about documents) to seem productive. Both produce motion without movement. This skill bans both.

Finding Triage

Every review finding lands in exactly one class:

Class Definition Handling
Blocking Wrong behavior, broken contract, missed requirement, data loss — rework guaranteed if shipped Must close before proceeding
Material Works, but creates real cost later: unhandled state, a field an implementer must guess at, silent assumption Close, or consciously defer with a note
Polish Style, phrasing, structure taste Author's discretion; never blocking; may be omitted entirely

The Nitpick Ban

Rejected as findings, regardless of how they're phrased: synonym preferences, formatting taste, 「我会换个说法」, restating content in the reviewer's own voice, heading-level opinions, 总分总 structure advice. The reviewer unsure whether something qualifies runs the test: what breaks, or what gets rebuilt, if this ships exactly as-is?

Three companion rules:

  1. Zero findings is a legitimate verdict. 「未发现实质性问题」 stated plainly is a completed review — better than three manufactured nitpicks. Review quality is the severity of what it catches, never the count of what it lists.
  2. Steelman first. Attack the strongest reading of the artifact; if two readings exist, the ambiguity itself is the finding, not the dumber reading's consequences.
  3. Asymmetry. One located, reproducible substantive flaw outranks any breadth of approval — but approval honestly reached is success, not dereliction.

Review Output Format

Verdict first: 通过 / 需修改(列 Blocking+Material)/ 阻断。Then findings, each carrying its class and its "what breaks" one-liner. Polish items, if listed at all, go in a clearly separated non-blocking tail. A review that buries its verdict under twelve undifferentiated suggestions has not been delivered.

The Busywork Alarm

The generalized disease: sessions exchanging work that only touches documents about the work — unifying formats, renaming sections, revising each other's phrasing, reviewing the review — while the thing being built does not move. It feels like collaboration; it is a treadmill (推来推去搞文档治理,不推进正事).

Alarm rules:

  1. End of every round, name the deliverable delta: what can the user now see, run, or decide that they couldn't before? 「文档更规范了」 is not a delta unless the document IS the deliverable.
  2. Two consecutive rounds with zero deliverable delta → stop and report to the user — 「我们在空转,卡点是X」 — instead of opening the next meta-round. Escalating honesty beats simulated momentum.
  3. Meta-work is legitimate only in direct service of an imminent deliverable change (e.g., fixing a contract doc an implementer is blocked on). Meta-work with no downstream consumer waiting is theater.
  4. Review chains don't nest: no reviews of reviews. A disputed finding resolves by evidence or by the owner's call — not by a third session reviewing the dispute.

Both Sides Are Bound

  • The author must not solicit rubber stamps (「快速看一眼说个没问题就行」) — corrupting the reviewer corrupts the loop.
  • The reviewed answers every Blocking/Material finding with a fix or a reasoned rebuttal; silence is not a response. Rebuttal is legitimate — reviews are input, not commands.
  • The requester (the human) gets verdicts in plain language: what's actually wrong, what it costs, what's taste.

Edge Handling

  • Nothing to review (empty/missing artifact): say so and ask for the artifact — never manufacture a review of nothing.
  • Ambiguous target (which file? which version?): pin the review object first (path + version/coordinate); reviewing an unpinned target produces findings nobody can act on.
  • Polish explicitly requested: legitimate — switch to polish mode, deliver it labeled 「润色(非复审发现)」, and keep it out of any review verdict.
  • Author disputes a Blocking finding: one evidence-backed restatement maximum, then escalate to the owner for a call — no repeated argument rounds (that is the review-chain treadmill by another door).
  • Reviewer cannot execute/verify (no environment, no data): deliver findings labeled static-analysis-grade and name exactly what remains unverified — never present unrun checks as run.

More worked examples per review type (code / requirements / busywork / polish-request) are in references/examples.md.

Example

Reviewing an export-feature contract, done right:

> 结论:需修改。
> Blocking:status 枚举只有 pending/done,没有失败态——实现者只能自造错误处理,联调必返工。
> Material:空结果集行为未定义(空文件还是报错?)。
> 未发现其他实质性问题。

Done wrong (rejected): 「建议 taskId 改名 exportTaskId 更语义化;第二节建议换个说法;建议整体结构调整为总分总。」——零实质,三找茬。

Busywork alarm firing, real pattern: 会话 A 建议会话 B 统一文档标题层级;B 回赠 A 把「完成」改为「已完成」的修订;两轮过去,要交付的功能一行未动 → 停,报告:「过去两轮交付物零变化,我们在空转;真正的卡点是接口失败态没人拍板。」

Common Rationalizations

Rationalization Required response
"The reviewer listed 12 issues — thorough review." Run each through "what breaks?"; often zero survive. Count is not rigor.
"I was asked to review; I have to find something." You were asked to find what's broken, not to prove you looked. 「未发现实质性问题」 is the honest deliverable.
"Cleaner documents are progress too." Documents serve the deliverable; a doc-only round with an untouched deliverable is a zero-delta round.
"Let's align the formatting first, then push the real work." Format alignment with no waiting consumer is theater; the real work is the queue.
"More review rounds show rigor." Rounds that surface new substantive findings show rigor; rounds that recycle taste show a treadmill.
"The other session's review of my review seems off — I'll review it back." Review chains don't nest; resolve by evidence or owner's call.

Guardrails

  • This skill kills fake findings and fake progress, not review itself: substantive review of real changes remains mandatory, and one located flaw still outranks broad approval.
  • Polish has its place: when explicitly requested, or as a clearly-labeled non-blocking tail after substance is settled.
  • When the deliverable IS a document (a spec, a report), "正事" means its semantic content — the busywork alarm then targets format-and-phrasing loops that leave the meaning untouched.
  • Escalating 「我们在空转」 is a success behavior, never an admission to hide.

常见问题

5 问
答案由本站依据条目字段整理
小白指挥AI干活之复审只挑真毛病怎么安装?

在支持 Skills 的客户端里执行:skillhub install user_f274b691/reviewing-for-substance。安装方式为未标注。装完刷新技能列表或重开客户端。

小白指挥AI干活之复审只挑真毛病支持哪些客户端?

资料没有标注宿主客户端,但只要客户端支持 Skills(Claude、Codex、Cursor 等),一般都能加载。

小白指挥AI干活之复审只挑真毛病权限高吗,安全吗?

权限级别为未标注权限。安装前先看它会读取或写入哪些内容。

小白指挥AI干活之复审只挑真毛病收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于技能本身和所用的模型或客户端,正式使用前按作者说明确认。

小白指挥AI干活之复审只挑真毛病用什么许可证?

许可证标注为 未说明(许可证不明确)。商用或二次分发前请到仓库确认条款原文。

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 未标注。