Review Skill
技能 已验证 活跃Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise SMEs on what to address. Use when a user wants to review, validate, or quality-check an Agent Skill.
To ensure Agent Skills meet structural and content quality standards before publishing, by providing automated validation and expert-like review.
功能
- Structural validation using skill-validator CLI
- Optional LLM scoring for content quality
- Interpretation of validation and scoring results
- Step-by-step workflow guidance
- Clear prerequisite checks and installation instructions
使用场景
- Reviewing a new agent skill for structural correctness
- Assessing the content quality of an agent skill with LLM scoring
- Getting actionable feedback on areas for improvement in an agent skill
- Validating an agent skill before it is published to a catalog
非目标
- Executing the agent skill itself
- Modifying the agent skill code directly
- Providing a general-purpose code linter or static analysis tool
Documentation
- info:Configuration & parameter referenceThe SKILL.md mentions environment variables for LLM scoring and configuration state but does not explicitly document their precedence or default values.
Code Execution
- info:ValidationThe `skill-validator` CLI likely performs internal validation, but the skill itself doesn't explicitly demonstrate schema validation for its own inputs or outputs.
安装
npx skills add mongodb/agent-skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Claude Handoff
100运行 /handoff 以捕获会话数据，然后编写一个引用该数据的分阶段实施计划。创建用于跟踪的 beads。
Unslop Review
100重写代码审查意见，使其听起来像人类同事所写。消除 "I noticed...", "I was wondering if perhaps...", "It might be worth considering..." 这类企业AI的套话。每条评论都直截了当：地点、问题、具体修复方案。用于用户说“人性化审查”、“减少PR评论中的废话”、“让反馈听起来更人性化”、“审查此PR”、“代码审查”、“/review”、“/unslop-review”时。在审查PR时自动触发。
Review Pull Request
100Review a pull request end-to-end using GitHub CLI. Covers diff analysis, commit history review, CI/CD check verification, severity-leveled feedback (blocking/suggestion/nit/praise), and gh pr review submission. Use when a pull request is assigned for review, performing a self-review before requesting others' input, conducting a second review after feedback is addressed, or auditing a merged PR for post-merge quality assessment.
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
ClawSweeper Skill
100Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.
Codex PR Review
100Revisa pull requests en proyectos Drupal 11 (u otro) siguiendo la metodología Codex (lógica de negocio, edge cases de hooks/queries, seguridad, performance, completitud). Genera un informe .md en la carpeta del IDE detectado (.antigravity/, .cursor/, .vscode/ o docs/) con hallazgos por severidad y soluciones accionables. Usar cuando el usuario pida "revisión Codex", "revisión de PR", "revisar PR", "revisar PR"