Local Diff Review Skill for Claude
基于本地 git diff 的代码审查技能。用于在提交 PR 前先做自检评审，严格复用 pr-review 的三维度标准（代码质量标准、FastGPT 风格规范、常见问题清单），支持审查未暂存改动、已暂存改动、某次提交、或当前分支相对基线分支的全部改动。
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/YYH211/Claude-meta-skill --skill local-diff-reviewThe instruction itself
4 sections, as written by the authorLocal Diff Review（提交前本地评审）
核心原则
- 审查标准必须与
pr-review保持一致，不允许自定义弱化标准。 - 先审查再改代码：默认先输出问题清单，只有用户明确要求才改代码。
- 结论必须可执行：每个问题都要给出文件路径、行号、风险说明、修复建议。
审查标准来源（必须遵循）
- 代码质量标准：
./code-quality-standards.md - 常见问题清单：
./common-issues-checklist.md
> 说明：本 skill 的“评审准则”以 pr-review 当前版本为准，以上链接即唯一标准来源。
使用场景
- 用户希望“先本地 review，再提 PR”。
- 用户给出“review 我当前改动/本地 diff/暂存区改动/分支差异”。
- 用户希望获得与 PR review 同等级别的风险分级反馈。
信息收集流程
先收集仓库状态：
git status --short
git branch --show-current
git remote -v
再根据用户意图选择 diff 范围（默认优先问清楚范围）：
# 1) 未暂存改动
git diff
# 2) 已暂存改动
git diff --staged
# 3) 工作区全部改动（含暂存+未暂存）
git diff HEAD
# 4) 当前分支相对基线分支（推荐用于“准备提 PR”）
git diff upstream/<base-branch>...HEAD
# 5) 指定提交
git show <commit>
审查步骤
- 阅读 diff，按文件分组梳理改动目的。
- 依次执行三维度审查（严格按上面 3 份标准文档）。
- 标注问题等级：
- 🔴 严重问题（必须修复）
- 🟡 建议改进（建议本次修）
- 🟢 可选优化（可后续处理）
- 汇总回归风险：i18n、类型安全、边界行为、兼容性、性能影响。
- 给出审查结论：可合并 / 需修改后再审。
输出格式（建议）
1) 变更概览
- 审查范围（哪一种 diff）
- 涉及文件数、核心模块
2) 问题清单
每个问题都包含：
- 文件路径 + 行号
- 风险等级（🔴/🟡/🟢）
- 问题描述（为什么是问题）
- 修复建议（给出可落地方案）
3) 总体结论
- 是否建议现在提 PR
- 提 PR 前建议补做的最小验证（如 lint / typecheck / 相关测试）
评审时的行为约束
- 不凭空猜测业务意图；证据不足时明确“需用户确认”。
- 不把“个人偏好”当成阻塞项。
- 不为不存在的调用路径添加过度防御性建议。
- 与用户沟通时优先中文、结论清晰、步骤可执行。
常用触发语句（示例）
- “请按 PR 标准 review 我本地当前改动。”
- “请 review 我的
git diff --staged，只给问题清单。” - “请按 FastGPT 规范审查我当前分支相对
upstream/v4.14.7-dev的改动。”
Other skills for the same job
different authors, same section of the catalogue
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
How to use it
Take yyh211/local-diff-review from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.