Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问许可证需确认审计提醒

github-review-prGitHub 审查 PR

Agent Skill

用于围绕 GitHub 仓库、Issue、Pull Request、分支、提交和代码协作流程提供辅助能力。它适合让 Agent 查询项目状态、整理变更、辅助创建或检查协作事项,并把仓库中的信息转成可执行的下一步。使用时需要区分只读查询和写入操作;涉及创建 PR、修改 Issue、推送分支或访问私有仓库时,应确认 token 权限、目标仓库范围和用户授权。

总安装

1,552

周安装

66

GitHub Stars

1,507

下载量

544
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:github-review-pr(GitHub 审查 PR)
来源仓库:https://github.com/feiskyer/claude-code-settings
仓库路径:skills/github-review-pr
安装命令:
npx skills add https://github.com/feiskyer/claude-code-settings --skill github-review-pr
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/feiskyer/claude-code-settings --skill github-review-pr

简介

协助审查 GitHub Pull Request 内容的技术辅助工具。

  • 支持代码变更分析与问题点识别。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。
  • 适用于多人协作开发的质量控制环节。
  • 修改评论或状态需具备相应仓库贡献者权限。
  • github-review-pr 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Review GitHub Pull Request

A structured, multi-agent workflow for thorough code reviews on GitHub PRs. The approach uses parallel specialized reviewers, confidence scoring, and false positive filtering to produce high-signal, actionable feedback.

Use gh for all GitHub interactions. Do not use web fetch or attempt to build/typecheck the app — CI handles that separately.

Workflow

1. Eligibility Check

Use a subagent to verify the PR is eligible for review. Skip the review if any of these are true:

  • The PR is closed or merged
  • The PR is a draft
  • The PR doesn't need review (e.g., automated/bot PR, or trivially simple)
  • You've already left a code review comment on it

If no PR number is provided, run gh pr list to show open PRs and ask which one to review.

2. Gather Context (parallel)

Launch two subagents in parallel:

Subagent A — Project guidance discovery: Find all relevant CLAUDE.md and AGENTS.md files — check the repo root and any directories whose files the PR modified. Return a list of file paths (not contents).

Subagent B — PR summary: View the PR with gh pr view and gh pr diff, then return a concise summary of what changed.

3. Parallel Code Review (5 specialized agents)

Launch 5 parallel subagents, each reviewing the PR from a different angle. Each agent should return a list of issues found, with a reason tag for why it was flagged (e.g., "CLAUDE.md adherence", "bug", "historical git context", "past PR feedback", "code comment violation").

AgentFocusApproach
#1 CLAUDE.md / AGENTS.md complianceCheck changes against project guidanceRead the CLAUDE.md and AGENTS.md files from step 2. Note that these files are guidance for AI agents as they write code, so not all instructions apply during code review.
#2 Shallow bug scanObvious bugs in the diffRead only the changed lines (avoid extra context beyond the diff). Focus on significant bugs, not nitpicks. Ignore likely false positives.
#3 Git history contextBugs visible through historical contextRead git blame and history of modified code. Identify issues that become apparent in light of how the code evolved.
#4 Past PR feedbackRecurring issuesFind previous PRs that touched these files. Check their comments for feedback that may also apply here.
#5 Code comment complianceRespect inline guidanceRead code comments in modified files. Verify the PR changes comply with any guidance expressed in those comments.

4. Confidence Scoring

For each issue found in step 3, launch a parallel subagent that receives the PR context, the issue description, and the CLAUDE.md/AGENTS.md file list. The subagent scores the issue on a 0-100 confidence scale:

ScoreMeaning
0False positive that doesn't stand up to light scrutiny, or a pre-existing issue.
25Might be real, but could be a false positive. Couldn't verify. If stylistic, not explicitly called out in CLAUDE.md or AGENTS.md.
50Verified as real, but may be a nitpick or unlikely to hit in practice. Not very important relative to the rest of the PR.
75Double-checked and very likely real. Will be hit in practice. The existing approach is insufficient. Important for functionality, or directly mentioned in CLAUDE.md/AGENTS.md.
100Definitely real and confirmed. Will happen frequently. Evidence directly confirms the issue.

For issues flagged due to CLAUDE.md/AGENTS.md instructions, the scoring agent should double-check that the relevant file actually calls out that issue specifically.

5. Filter

Discard any issues scoring below 80. If no issues meet this threshold, skip to posting the "no issues found" comment.

6. Re-check Eligibility

Before posting, use a subagent to repeat the eligibility check from step 1. PRs can be closed or updated while the review runs.

7. Post Review Comment

Use gh to comment on the PR with findings. Follow these rules:

  • Keep output brief
  • No emojis
  • Link and cite relevant code, files, and URLs
  • You must provide the full git SHA in links (not $(git rev-parse HEAD) — the comment renders as Markdown)
  • Provide at least 1 line of context before and after the issue line in link ranges

Comment format — issues found

### Code review

Found 3 issues:

1. <brief description> (CLAUDE.md says "<quote>")

https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ts#L12-L16

2. <brief description> (AGENTS.md says "<quote>")

https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ts#L30-L35

3. <brief description> (bug due to <file and code snippet>)

https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ts#L50-L55

<sub>- If this code review was useful, please react with a thumbs up. Otherwise, react with a thumbs down.</sub>

Comment format — no issues found

### Code review

No issues found. Checked for bugs, CLAUDE.md, and AGENTS.md compliance.

Link format

Links must follow this exact format for Markdown rendering to work:

https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.ext#L[start]-L[end]
  • Full 40-character git SHA (no shell expansion)
  • Repo name must match the repo being reviewed
  • # after the file name
  • Line range as L[start]-L[end]
  • Include at least 1 line of context before/after (e.g., commenting on lines 5-6 should link L4-L7)

False Positive Examples

These should be filtered out during steps 3-5. Share this context with the review and scoring agents:

  • Pre-existing issues (not introduced by this PR)
  • Something that looks like a bug but isn't actually one
  • Pedantic nitpicks a senior engineer wouldn't flag
  • Issues a linter, typechecker, or compiler would catch (imports, types, formatting, test failures)
  • General code quality concerns (test coverage, docs, broad security) unless explicitly required in CLAUDE.md or AGENTS.md
  • Issues called out in CLAUDE.md/AGENTS.md but explicitly silenced in code (e.g., lint ignore comments)
  • Intentional functionality changes directly related to the PR's purpose
  • Real issues on lines the author did not modify

gh Command Reference

# List open PRs
gh pr list

# View PR description and metadata
gh pr view 78

# View PR code changes
gh pr diff 78

# Get repo owner/name
gh repo view --json nameWithOwner --jq '.nameWithOwner'

# Get PR head commit SHA (full 40-char)
gh api repos/OWNER/REPO/pulls/78 --jq '.head.sha'

# Post a comment on the PR
gh pr comment 78 --body "### Code review ..."

# Post inline review comment on a specific file/line
gh api repos/OWNER/REPO/pulls/78/comments \
    --method POST \
    --field body="[your-comment]" \
    --field commit_id="[full-sha]" \
    --field path="path/to/file" \
    --field line=42 \
    --field side="RIGHT"

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.17%
按下载量换算197

Claude

27.69%
按下载量换算151

Cursor

19.72%
按下载量换算107

Gemini CLI

8.64%
按下载量换算47

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/feiskyer/claude-code-settings --skill github-review-pr 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills