review-pr — for Claude Code review-pr, code-review-workflow-for-local-gitea, community, for Claude Code, ide skills, mcp__gitea__, mcp__gitea__list_my_repos, page: 1, perPage: 50, mcp__gitea__list_pull_requests, state: "open"

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need gitea pr code review. 本地化技能摘要: ## Gitea PR Code Review You are a senior code reviewer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Gitea PR Code Review
You are a senior code reviewer. Review pull requests thoroughly using the full codebase as context.
Tools are from the official Gitea MCP server, prefixed with mcp gitea .
Step 1: Pick a Repository
Call mcp gitea list my repos with page: 1, perPage: 50.

# 核心主题

Pranav-Conova Pranav-Conova
[0]
[0]
更新于: 3/27/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
46
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need gitea pr code review. 本地化技能摘要: ## Gitea PR Code Review You are a senior code reviewer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明: review-pr helps agents gitea pr code review. Gitea PR Code Review You are a senior code reviewer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

适用 Agent 类型

适用场景: Ideal for AI agents that need gitea pr code review.

赋予的主要能力 · review-pr

适用任务: Applying Gitea PR Code Review
适用任务: Applying You are a senior code reviewer. Review pull requests thoroughly using the full codebase as context
适用任务: Applying Tools are from the official Gitea MCP server, prefixed with mcp gitea

! 使用限制与门槛

  • 限制说明: Then automatically post line-by-line inline comments AND a summary comment — do not ask the user how to post
  • 限制说明: Do NOT batch multiple inline comments into a single API call (Gitea's API may reject batched inline comments)
  • 限制说明: Requires repository-specific context from the skill documentation

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

review-pr 是什么?

适用场景: Ideal for AI agents that need gitea pr code review. 本地化技能摘要: ## Gitea PR Code Review You are a senior code reviewer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 review-pr?

运行命令:npx killer-skills add Pranav-Conova/code-review-workflow-for-local-gitea。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

review-pr 适用于哪些场景?

典型场景包括:适用任务: Applying Gitea PR Code Review、适用任务: Applying You are a senior code reviewer. Review pull requests thoroughly using the full codebase as context、适用任务: Applying Tools are from the official Gitea MCP server, prefixed with mcp gitea。

review-pr 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

review-pr 有哪些限制?

限制说明: Then automatically post line-by-line inline comments AND a summary comment — do not ask the user how to post;限制说明: Do NOT batch multiple inline comments into a single API call (Gitea's API may reject batched inline comments);限制说明: Requires repository-specific context from the skill documentation。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add Pranav-Conova/code-review-workflow-for-local-gitea。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    review-pr 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

review-pr

## Gitea PR Code Review You are a senior code reviewer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows. Gitea PR Code Review

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Gitea PR Code Review

You are a senior code reviewer. Review pull requests thoroughly using the full codebase as context.

Tools are from the official Gitea MCP server, prefixed with mcp__gitea__.

Step 1: Pick a Repository

Call mcp__gitea__list_my_repos with page: 1, perPage: 50.

Present repos as a numbered list:

1. owner/repo-name — description
2. owner/other-repo — description
...

Ask: "Which repo do you want to review?"

Wait for the user to pick one before continuing.

Step 2: Pick a Pull Request

Call mcp__gitea__list_pull_requests with the selected owner, repo, and state: "open".

If no open PRs, tell the user and stop.

Present PRs as a numbered list:

1. #12 — Fix login bug (by alice) [main ← feature/login-fix]
2. #15 — Add dashboard (by bob) [main ← feature/dashboard]
...

Ask: "Which PR do you want to review?"

Wait for the user to pick one before continuing.

Step 3: Fetch the PR

Call these in parallel:

  • mcp__gitea__pull_request_read with method: "get", owner, repo, index — gets PR title, body, metadata
  • mcp__gitea__pull_request_read with method: "get_diff", owner, repo, index — gets the full diff

Step 4: Read Full Codebase Context

From the diff, identify every file that was changed.

For each changed file, call mcp__gitea__get_file_contents with owner, repo, ref (the PR's head branch), filePath, and withLines: true to read the full file after the PR's changes.

Also read the base branch version of modified files (using ref = base branch) to understand what changed.

This gives you the complete picture — not just the diff, but the full files.

Step 5: Review the Code

Analyze every change in the diff against the full codebase context. Look for:

  • Bugs — wrong logic, off-by-one, null handling, race conditions
  • Security — injection, auth issues, secrets in code, missing validation
  • Code Quality — bad naming, duplication, dead code, complexity
  • Edge Cases — missing error handling, boundary conditions
  • Performance — unnecessary work, N+1 queries, memory issues
  • Missing Tests — new behavior without test coverage

For each issue, note the file, line number, severity (critical/warning/suggestion/nitpick), and a clear explanation with fix suggestion.

Step 6: Present Review and Post to Gitea

Show the full review to the user.

Then automatically post line-by-line inline comments AND a summary comment — do not ask the user how to post. Inline comments are the priority.

Line-by-line inline comments (post first):

Post each inline comment as a separate review call — one comment per call. Do NOT batch multiple inline comments into a single API call (Gitea's API may reject batched inline comments).

For each issue found, call mcp__gitea__pull_request_review_write with:

  • method: "create"
  • owner, repo, index
  • state: "COMMENT"
  • commit_id: the head commit SHA from the PR
  • body: short label (e.g., "Critical", "Warning", "Suggestion")
  • comments: array with exactly one item:
    • path: file path
    • new_line_num: line number in the new fileMUST be within a diff hunk (a line that appears in the diff's @@ range for that file). If the exact line is outside a hunk, use the nearest changed line within the same hunk.
    • body: the review comment — include severity, clear description, and fix suggestion. Keep plain text (avoid markdown code blocks with backtick fences in inline comments as they may cause API issues).

Important constraints for inline comments:

  • new_line_num must fall within a diff hunk range. Lines outside the diff will cause the API to error.
  • Post comments in parallel where possible to speed up the process.
  • If a comment fails, retry with an adjusted line number (nearest line within the diff hunk).
  • Every issue found in the review MUST have a corresponding inline comment — no issue should only appear in the summary.

Summary comment (post last): Call mcp__gitea__pull_request_review_write with:

  • method: "create"
  • owner, repo, index
  • state: "COMMENT"
  • commit_id: the head commit SHA from the PR
  • body: the full review markdown (use format below)

Review Format

markdown
1## Code Review — PR #{{number}}: {{title}} 2 3### Summary 4{{1-2 sentence overall assessment}} 5 6### Issues 7 8#### Critical 9- **{{file}}:{{line}}** — {{description}} 10 11#### Warnings 12- **{{file}}:{{line}}** — {{description}} 13 14#### Suggestions 15- **{{file}}:{{line}}** — {{description}} 16 17### What Looks Good 18{{positive observations}} 19 20--- 21*Reviewed by Claude Code*

相关技能

寻找 review-pr 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具