pr-review
minimax-ai/skills
Validate and review pull requests for MiniMax Skills repository compliance.
What is pr-review?
Review pull requests against repository standards using a two-phase process: automated validation of structural requirements, then manual content review against quality guidelines. Use this when reviewing PRs, validating new skill submissions, or checking existing skills for compliance.
- Run automated validation script to check SKILL.md structure, YAML frontmatter, required fields, and detect hardcoded secrets
- Verify skill name matches directory name and all ERROR-level checks pass
- Review skill scope for overlap with existing skills and clear boundaries
- Assess description quality, file sizes, API key handling, and script quality
- Check README synchronization and conventional commit formatting in PR titles
How to install pr-review
npx skills add https://github.com/minimax-ai/skills --skill pr-review- Python environment with access to validate_skills.py script
- Access to the MiniMax Skills repository structure
- Familiarity with YAML frontmatter and SKILL.md format
How to use pr-review
- 1.Run the validation script: python .claude/skills/pr-review/scripts/validate_skills.py
- 2.Review script output for ERROR-level failures (blockers) and WARNING-level items
- 3.Check PR title follows conventional commit format
- 4.Verify one PR addresses one purpose
- 5.Review skill scope for overlap with existing skills
- 6.Assess description quality includes trigger conditions
- 7.Verify files are reasonably sized for context window
- 8.Confirm API keys use environment variables, not hardcoded secrets
Use cases
- Validate a new skill submission before merging to ensure it meets repository standards
- Review an existing skill for compliance with hard rules and soft guidelines
- Check a PR that modifies multiple skills for consistency and proper documentation
- Verify API credentials are read from environment variables rather than hardcoded
- Ensure README tables are updated when new community skills are added
- Repository maintainers reviewing pull requests
- Skill contributors validating their submissions before opening a PR
- Code reviewers checking skill compliance and quality
- DevOps engineers ensuring security practices in skill submissions
pr-review FAQ
Phase 1 (Automated Validation) runs hard structural checks via validate_skills.py that must pass—checking SKILL.md existence, YAML parsing, required fields, and secret detection. Phase 2 (Content Review) applies soft guidelines for quality assessment like scope clarity, description quality, file sizing, and API key handling.
No. WARNING-level items like missing `license` or `metadata` fields should be flagged but are not blockers. Only ERROR-level checks must pass for the PR to be approved.
Verify that any external API credentials are read from environment variables, not hardcoded in scripts or configuration files. This is a security requirement.
Yes, if adding a new skill, update both README.md and README_zh.md with the skill entry. Set the Source column to 'Community' for community-contributed skills.
Each pull request should address a single, focused change—either adding one new skill, fixing one skill, or updating documentation for one feature. Avoid bundling unrelated changes in a single PR.
Full instructions (SKILL.md)
Source of truth, from minimax-ai/skills.
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:
python .claude/skills/pr-review/scripts/validate_skills.py
The script checks:
SKILL.mdexists in every skill directory- YAML frontmatter is parseable
- Required fields present:
name,description namematches 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 for the complete hard rules specification.
Phase 2: Content Review (Soft Guidelines)
After automated checks pass, review the PR against quality guidelines:
- Skill scope — Does it overlap with existing skills? Is the boundary clear?
- Description quality — Does the
descriptioninclude clear trigger conditions? - File size — Are reference docs reasonably sized for context window consumption?
- API key handling — If external APIs are used, are credentials read from environment variables?
- Script quality — Do scripts have shebang, requirements.txt, and error handling?
- Language — Are SKILL.md and code written in English?
- README sync — Are
README.mdandREADME_zh.mdupdated for new skills?
See references/quality-guidelines.md for soft guidelines details.
Review Checklist Summary
Must Pass (Blockers)
-
validate_skills.pyexits 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)
Related skills
More from minimax-ai/skills and the wider catalog.
react-native-dev
Build production React Native and Expo apps with navigation, animations, state management, and deployment patterns.
shader-dev
36 GLSL shader techniques for ray marching, SDFs, fluid simulation, particles, and visual effects.
vision-analysis
Analyze, describe, and extract information from images using MiniMax vision capabilities.
android-native-dev
Android native development guide covering Material Design 3, Kotlin/Compose, project setup, and build configuration.
mintlify-api
Interact with the Mintlify REST API to manage deployments, trigger builds, and query documentation site metadata programmatically.
mintlify
Guidance for writing and organizing Mintlify documentation sites correctly the first time.