Token导航 LogoToken导航

Agent Skill · 研究检索

wtf.pr-review(WTF 公关评论)

wtf.pr-review 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

wtf.pr-review 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 70,176。

总安装 212周安装 9GitHub Stars 3下载 74核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:wtf.pr-review(WTF 公关评论)
来源仓库:https://github.com/xiduzo/wtf
仓库路径:skills/wtf.pr-review
安装命令:
npx skills add https://github.com/xiduzo/wtf --skill wtf.pr-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/xiduzo/wtf --skill wtf.pr-review

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

wtf.pr-review 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。它支持基于关键词、任务场景或来源线索进行信息聚合与过滤,适用于 Pull Request 评审相关研究。

通过 npx skills add 命令从 GitHub 仓库安装,具体用法需结合原始 README 进一步确认。安装前请核实权限范围、维护状态,并注意是否涉及联网、命令执行或文件读写操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/wtf.pr-review

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/xiduzo/wtf --skill wtf.pr-review;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

wtf.pr-review 怎么安装?

在终端执行 npx skills add https://github.com/xiduzo/wtf --skill wtf.pr-review。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

wtf.pr-review 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

wtf.pr-review 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

wtf.pr-review 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

wtf.pr-review 用的人多吗?

公开数据是累计安装 212 次,近一周安装 9 次,下载 74 次,GitHub 3 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

wtf.pr-review 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 要求有安全扫描结论才肯安装的团队。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
wtf.pr-review

WTF 公关评论 · 本页

2123需要联网未明确未收录

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

PR Review

Review a pull request as a tech lead. Core value: reads the diff against the linked Task spec (Gherkin, Contracts, Impacted Areas) to catch spec drift, missing test coverage, and contract violations before merge — not by running the software, but by reading the code.

Distinct from wtf.verify-task: wtf.verify-task is a QA engineer running the implemented behavior against Gherkin scenarios (does the software do what it says?). This skill is a developer reviewing the code itself (is the code written correctly against the spec?).

Process

0. GitHub CLI setup

Run steps 1–2 of ../references/gh-setup.md. Stop if gh is not installed or not authenticated.

1. Identify the PR

If a PR number was passed in, use it directly. Otherwise:

gh pr list --state open --json number,title,headRefName --limit 20

Call AskUserQuestion with question: "Which PR are you reviewing?", header: "PR", and options pre-filled from open PRs.

Fetch the PR:

gh pr view <pr_number> --json number,title,body,headRefName,baseRefName,additions,deletions,changedFiles

2. Fetch the spec hierarchy

Try to extract a Task number from the PR body (Closes #<n> or Fixes #<n>). If found, fetch the full spec hierarchy:

gh issue view <task_number>    # Gherkin, Contracts, Impacted Areas, DoD
# Extract feature and epic numbers, then in parallel:
gh issue view <feature_number> # ACs, user stories
gh issue view <epic_number>    # Goal, constraints

If no Task number is found, call AskUserQuestion with question: "Is there a Task issue linked to this PR?", header: "Linked task", and options: [{label: "No linked task", description: "Review from diff only"}, {label: "Yes — I'll provide the number", description: "Enter the task issue number"}].

If there is no linked Task, the review proceeds from diff context alone (step 4 will note the absence of a spec as a finding).

3. Load the technical steering document

Use the Read tool to attempt reading docs/steering/TECH.md. Apply its patterns, constraints, and conventions as the baseline for code quality judgements throughout this review.

4. Inspect the diff

git diff <base_branch>...<pr_branch> --stat
git diff <base_branch>...<pr_branch>

Read the full diff. Note:

  • Which files changed and which layers they touch
  • What was added vs. removed vs. moved
  • Whether the changes stay within the Impacted Areas listed in the Task

5. Run the review checklist

Evaluate each dimension. Record findings as PASS / FAIL / WARN per item.

a. Spec adherence

For each Gherkin scenario in the Task:

  • Is there a test that covers this scenario? (search test files for scenario name or equivalent describe/it block)
  • Does the implementation match the Given/When/Then behavior — not just passing the test, but structurally doing what the scenario describes?

Flag: missing test for a scenario, test present but testing the wrong behavior, implementation that bypasses the scenario entirely.

b. Contract compliance

For each entry in the Task's Contracts & Interfaces section:

  • Does the code implement exactly the specified shape? (field names, types, optionality)
  • Are there any added fields not in the spec (scope creep)?
  • Are any specified fields missing from the implementation?

Flag: schema drift, extra fields, missing fields, wrong types.

c. Impacted Areas

Cross-reference the Task's Impacted Areas list against the actual changed files:

  • Unexpected files changed outside the listed areas (scope creep signal)
  • Listed areas with no changes (may indicate incomplete implementation)

d. Code quality against TECH.md

Review changed code against the patterns and constraints in docs/steering/TECH.md:

  • Naming conventions (domain language vs. generic names)
  • Layer separation (e.g. business logic in wrong layer)
  • Error handling patterns
  • Function length and nesting (flag >40 lines or deep nesting as a warning, not a blocker)

e. Test coverage

  • Are there tests for the happy path AND at least one error/edge path per public function changed?
  • Does the test file pattern match the project convention (from TECH.md)?
  • Are there any skip, todo, or commented-out assertions in the new tests?

f. Definition of Done

Check the Task's DoD checklist against the diff:

  • Are all DoD items evidenced in the diff or existing code?

6. Summarise findings

Produce a structured review summary:

PR Review — #<pr_number>: <title>
───────────────────────────────────────────────
Linked task: #<n> | Spec coverage: [n/n scenarios covered]

PASS  Spec adherence     — all [n] scenarios have matching tests
WARN  Contract compliance — `paymentId` field missing from response shape (Task spec: required)
PASS  Impacted Areas     — changes within declared scope
WARN  Code quality       — `processSettlement()` is 58 lines (threshold: 40)
PASS  Test coverage      — happy path + 2 error paths
FAIL  DoD                — "Observability: metrics emitted" not evidenced in diff

Verdict: REQUEST CHANGES
───────────────────────────────────────────────
Required (blocking merge):
  1. [Contract] Add `paymentId` to settlement response — Task spec requires it (Contracts §2)
  2. [DoD] Emit the `settlement_processed` metric — listed as required in Task DoD

Suggested (non-blocking):
  3. [Quality] Extract `processSettlement()` into smaller functions — currently 58 lines

Verdicts:

  • APPROVE — no blocking findings
  • APPROVE WITH COMMENTS — suggestions only, nothing blocking
  • REQUEST CHANGES — one or more FAIL items that must be resolved before merge

7. Review with user

Show the summary. Then call AskUserQuestion with:

  • question: "Does this look right? Should I post this as a GitHub PR review?"
  • header: "Post review"
  • options: [{label: "Post it", description: "Submit as a GitHub PR review comment"}, {label: "I have edits", description: "I want to adjust before posting"}, {label: "Don't post — just the summary", description: "Keep it in the conversation"}]

Apply any edits, then proceed.

8. Post the review

gh pr review <pr_number> \
  --<approve|request-changes|comment> \
  --body-file /tmp/wtf.pr-review-<pr_number>-body.md

Use:

  • --approve for APPROVE or APPROVE WITH COMMENTS
  • --request-changes for REQUEST CHANGES
  • --comment if the user chose "Don't post — just the summary" but then changed their mind

Print the PR URL.

平台分布

Codex

37.09%
按下载量换算27

Claude

28.76%
按下载量换算21

Cursor

16.11%
按下载量换算12

Gemini CLI

8.68%
按下载量换算6

安全审计

暂无安全审计结果可展示。

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills