local-diff-review SKILL.md skillA

local-diff-review from bg-szy/top-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bg-szy/top-skills/local-diff-review@git:20260522.3711c9f

Pins git:20260522.3711c9f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bg-szy/top-skills
Path
skills/Claude-meta-skill/local-diff-review/SKILL.md
Versions recorded
1
Latest version
git:20260522.3711c9f, committed May 22, 2026
Size
3,191 bytes
Repository stars
6
License
a license file GitHub does not identify

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。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Local Diff Review(提交前本地评审)

## 核心原则

1. 审查标准必须与 `pr-review` 保持一致,不允许自定义弱化标准。
2. 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。
3. 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`](code-quality-standards.md)
- 常见问题清单:[`./common-issues-checklist.md`](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:

```bash
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):

```bash
# 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

1. 阅读 diff,按文件分组梳理改动目的。
2. 依次执行三维度审查(严格按上面 3 份标准文档)。
3. 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)
4. 汇总回归风险:i18n、类型安全、边界行为、兼容性、性能影响。
5. 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)
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_gie32olkley75gd5/90244ba0e78c47ad917a785083e31a9016c911a9667e7b3e6cbbc8d0da44acd4.json

Then /plugin install local-diff-review@markdownregistry-gie32olkley75gd5 in Claude Code. It installs git:20260522.3711c9f, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add bg-szy/top-skills/local-diff-review@sha256:90244ba0e78c47ad

The line at the top of this page pins the label git:20260522.3711c9f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gie32olkley75gd5.svg)](https://markdownregistry.com/a/art_gie32olkley75gd5)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in bg-szy/top-skills/local-diff-review since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of local-diff-review from somewhere else? Ask it: where did my local-diff-review come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on May 22, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260522.3711c9f latest2026-05-22 3711c9f 3,191 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3191 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

bg-szy/top-skills · 6 stars · license a license file GitHub does not identify · pushed 2026-11-15 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_gie32olkley75gd5
GET https://markdownregistry.com/api/v1/resolve?ref=bg-szy/top-skills/local-diff-review
GET https://markdownregistry.com/api/v1/blob/90244ba0e78c47ad917a785083e31a9016c911a9667e7b3e6cbbc8d0da44acd4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from bg-szy/top-skills

create-skill-file SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/create-skill-file/SKILL.md · Guides Claude in creating well-structured SKILL.md files following best practices. Provides clear guidelines for…
git:20260522.3711c9f · audit A · 6 stars
create-skill-file SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/create-skill-file__create-skill-file/SKILL.md · Guides Claude in creating well-structured SKILL.md files following best practices. Provides clear guidelines for…
git:20260530.b083023 · audit A · 6 stars
daily-ai-news SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/daily-ai-news/SKILL.md · Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides…
git:20260522.3711c9f · audit A · 6 stars
deep-reading-analyst SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/deep-reading-analyst/SKILL.md · Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA…
git:20260522.3711c9f · audit A · 6 stars
dry-refactoring SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/dry-refactoring/SKILL.md · Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate…
git:20260522.3711c9f · audit A · 6 stars
fastgpt-workflow-generator SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/fastgpt-workflow-generator/SKILL.md · Generates production-ready FastGPT workflow JSON from natural language requirements. Uses AI-powered semantic template…
git:20260522.3711c9f · audit A · 6 stars
frontend-design SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/frontend-design/SKILL.md · Creates unique, production-grade frontend interfaces with exceptional design quality. Use when user asks to build web…
git:20260522.3711c9f · audit A · 6 stars
mcp-builder SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/mcp-builder/SKILL.md · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
git:20260522.3711c9f · audit A · 6 stars
planning-with-files SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/planning-with-files/SKILL.md · Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge…
git:20260522.3711c9f · audit A · 6 stars
prompt-optimize SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/prompt-optimize/SKILL.md · Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who…
git:20260522.3711c9f · audit A · 6 stars
software-copyright-writer SKILL.md skill
bg-szy/top-skills · skills/Claude-meta-skill/software-copyright-writer/SKILL.md · 根据真实代码仓库、官网页面、运行界面、模块范围和目标软著数量,分析软件著作权(软著)申报方向,拆分可申报主题,检查 Logo、版权、备案、截图和源码等材料约束,生成 3w-4w 字正文、局部代码片段、源码原文、网页截图证据和 .docx…
git:20260522.3711c9f · audit A · 6 stars
accelerated-computing-cudf SKILL.md skill
bg-szy/top-skills · skills/agent-skills/accelerated-computing-cudf/SKILL.md · Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby…
v2.0 · audit A · 6 stars

Every file in bg-szy/top-skills

Browse by kind, by grade A, or by owner.