MiniMax Skills is a collection of development skills, APIs, and configuration formats for AI coding agents. Developers use it to get structured guidance for frontend, backend, Android, iOS, and shader work across several technology stacks. Catalogue entries package its skills, agents, and plugins for use with coding assistants.
Borrowing it
Nothing to install: this file belongs to MiniMax-AI/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MiniMax-AI/skills/main/.claude/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/MiniMax-AI/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/minimax-ai/skills/pr-review)<a href="https://agentmods.dev/skills/minimax-ai/skills/pr-review"><img src="https://agentmods.dev/badge/skills/minimax-ai/skills/pr-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/minimax-ai/skills/pr-review"><img src="https://agentmods.dev/badge/skills/minimax-ai/skills/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.00542 |
| Opus 5 | $0.00032 | $0.00271 |
| Sonnet 5 | $0.00013 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 64 lines · 63 tokens per session scan A c4b12fa291ee
pr-review is a skill published in the GitHub repository MiniMax-AI/skills (13,541 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 542 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…