skill Claude Code CX Codex Cursor GitHub Copilot
Open on GitHub
pr-review — Claude Code skill: what it does, how to install
Two-phase pull request review for skill repositories, combining automated schema checks with content audits.
Install into Claude Code · Skills CLI (Vercel)
All methods and platforms ↓
npx skills add MiniMax-AI/skills --skill pr-review -a claude-codeWhat pr-review does
The skill handles pull request reviews in two distinct phases: automated validation followed by content evaluation. First, it runs python .claude/skills/pr-review/scripts/validate_skills.py to verify that SKILL.md exists, required YAML fields are present, and no plaintext secrets are committed.
The second phase inspects skill trigger conditions, environment variable usage for API keys, and documentation updates across README.md and README_zh.md. The workflow is tied directly to the MiniMax repository structure, so running it outside this layout will fail during the script execution stage.
What it helps with
- validate SKILL.md structure and YAML frontmatter
- catch hardcoded credentials and secrets before merge
- verify environment variable handling for external APIs
- ensure documentation parity across README and README_zh
Example prompts for the agent
- Review this pull request against repository standards
- Validate the new skill submission with pr-review
- Check this skill PR for compliance
How to install pr-review
1Skills CLI (Vercel)
npx skills add MiniMax-AI/skills --skill pr-review -a claude-code2Manually: put the files in place
~/.claude/skills/pr-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pr-review/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/skills --skill pr-review -a codex2Manually: put the files in place
.agents/skills/pr-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/skills --skill pr-review -a cursor2Manually: put the files in place
.cursor/skills/pr-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MiniMax-AI/skills pr-review2Manually: put the files in place
.github/skills/pr-review/SKILL.md1Skills CLI (Vercel)
npx skills add MiniMax-AI/skills --skill pr-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/MiniMax-AI/skills --path .claude/skills/pr-reviewManually: put the files in place
.devin/skills/pr-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add MiniMax-AI/skills --skill pr-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set17
The whole set →
pptx-generator A skill to read, edit, and build PowerPoint decks from scratch using PptxGenJS and XML workflows. Useful when generating presentations from code or extracting slide text.
Claude Code CX Codex Cursor +1
6,000installs
minimax-docx A skill for generating, filling and formatting Word documents with OpenXML SDK. Use it when the agent must deliver a .docx, not plain text.
Claude Code CX Codex Cursor +1
4,500installs
minimax-xlsx Skill to create, read, edit, and validate Excel files (.xlsx, .xlsm, .csv, .tsv) directly in code. Use it when you need to build a financial model, add calculated columns, or fix broken formulas while preserving formatting and macros.
Claude Code CX Codex Cursor +1
3,800installs
minimax-pdf Generates professional PDFs with visual identity: reports, resumes, portfolios. Design is derived from document type, with consistent color and typography throughout.
Claude Code CX Codex Cursor +1
3,800installs
fullstack-dev Guides full-stack backend architecture and frontend integration. It enforces a structured checklist from requirement gathering to verification smoke tests.
Claude Code CX Codex Cursor +1
3,400installs
frontend-dev Orchestrates frontend development, motion design, AI-generated media, and conversion copy. Built for landing pages, marketing sites, and dashboards.
Claude Code CX Codex Cursor +1
3,200installs
vision-analysis Describes images, extracts text, and reviews UI mockups using the MiniMax vision MCP tool. Handy when an agent needs to understand a screenshot or design file.
Claude Code CX Codex Cursor +1
2,700installs
android-native-dev Guides AI agents through native Android development: project scaffolding, Gradle setup, Jetpack Compose dependencies, and product flavors.
Claude Code CX Codex Cursor +1
2,700installs
Similar
learn-reverse-engineering Interactive tutor for reading compiled programs. One lesson per invocation: from file formats and disassembly to symbolic execution and AI-assisted analysis. Requires Python 3.10+ and your own source code.
Claude Code CX Codex Cursor +1
425installs
ai-debt-detector This skill audits AI-generated code for missed failure paths, orphaned resources, fake dependencies, and architecture drift before a merge.
Claude Code CX Codex Cursor
2,900installs
guidelines-advisor Audits smart contract codebases against Trail of Bits guidelines. It spots upgradeability pitfalls, flawed inheritance, and testing gaps.
Claude Code CX Codex Cursor +1
5,400installs
react19-concurrent-patterns
official Preserves React 18 concurrent patterns during React 19 migrations and guides the adoption of use(), useOptimistic, and Actions.
GitHub Copilot
1,100installs
mcp-security-audit
official Audits MCP server configurations for exposed secrets, shell injection, mutable package references, and unapproved servers. Use it before changing .mcp.json.
GitHub Copilot
1,100installs
arize-trace
official Export Arize traces and spans by ID, then inspect them to investigate errors or LLM app behavior. Use it when you need to examine trace data already collected.
GitHub Copilot
1,100installs
improve-codebase-architecture This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review.
Claude Code
1,163,035installs
tdd Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details.
Claude Code
1,141,062installs
Questions about pr-review
How to install pr-review in Claude Code?
Run npx skills add MiniMax-AI/skills --skill pr-review -a claude-code in your terminal. This registers the skill under ~/.claude/skills/pr-review/SKILL.md.
What does pr-review do?
It reviews pull requests using a two-phase check: hard automated validation of skill file structure followed by a qualitative content audit.
What are the prerequisites for running pr-review?
You need Python installed locally so the skill can execute .claude/skills/pr-review/scripts/validate_skills.py during phase one.
Source text
SKILL.md · MIT
--- name: pr-review description: > Review pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or checking existing skills for compliance. Run the validation script first for hard checks, then apply quality guidelines for content review. Triggers: PR review, pull request, validate skill, check skill. license: MIT metadata: version: "1.0" category: tooling --- # PR Review Skill Review pull requests against repository standards. Two-phase process: automated validation, then manual content review. ## Phase 1: Automated Validation (Hard Rules) Run the validation script to check structural requirements: ```bash python .claude/skills/pr-review/scripts/validate_skills.py ``` The script checks: - `SKILL.md` exists in every skill directory - YAML frontmatter is parseable - Required fields present: `name`, `description` - `name` matches directory name - No hardcoded secrets detected All ERROR-level checks must pass. WARNING-level items (missing `license`, `metadata`) should be flagged but are not blockers. See [references/structure-rules.md](references/structure-rules.md) for the complete hard rules specification. ## Phase 2: Content Review (Soft Guidelines) After automated checks pass, review the PR against quality guidelines: 1. **Skill scope** — Does it overlap with existing skills? Is the boundary clear? 2. **Description quality** — Does the `description` include clear trigger conditions? 3. **File size** — Are reference docs reasonably sized for context window consumption? 4. **API key handling** — If external APIs are used, are credentials read from environment variables? 5. **Script quality** — Do scripts have shebang, requirements.txt, and error handling? 6. **Language** — Are SKILL.md and code written in English? 7. **README sync** — Are `README.md` and `README_zh.md` updated for new skills? See [references/quality-guidelines.md](references/quality-guidelines.md) for soft guidelines details. ## Review Checklist Summary ### Must Pass (Blockers) - [ ] `validate_skills.py` exits with code 0 - [ ] PR title follows conventional commit format - [ ] One PR, one purpose ### Should Pass (Flagged in Review) - [ ] No functional overlap with existing skills - [ ] Description includes trigger conditions - [ ] Files are reasonably sized - [ ] API keys via environment variables - [ ] README tables updated for new skills (Source column set to `Community`)
© MiniMax-AI · MIT · MiniMax-AI/skills
