Review Codebase
技能 已验证 活跃Multi-phase deep codebase review with severity ratings and structured output. Covers architecture, security, code quality, and UX/accessibility in a single coordinated pass. Produces a prioritized findings table suitable for direct conversion to GitHub issues via the create-github-issues skill.
To provide a thorough, multi-dimensional assessment of a codebase's quality and structure, producing actionable, prioritized findings for improvement.
功能
- Multi-phase codebase review
- Severity ratings for findings
- Structured output for issue conversion
- Covers architecture, security, code quality, and UX/accessibility
- Input parameters for scope and output format
使用场景
- Conducting whole-project or subproject quality checks
- Onboarding to new codebases to build a mental model
- Performing periodic health checks after sustained development
- Using findings to directly create GitHub issues or plan sprints
非目标
- Reviewing individual pull requests (use `review-pull-request` skill)
- Performing single-domain deep dives (use specialized skills like `security-audit-codebase`)
- Implementing fixes (use `clean-codebase` skill)
Practical Utility
- info:Usage examplesWhile the SKILL.md describes inputs and expected outputs, it does not provide concrete, ready-to-use examples with specific inputs and their corresponding outputs.
安装
/plugin install agent-almanac@pjt222-agent-almanac质量评分
已验证类似扩展
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
使用我的浏览器
100当工作依赖于用户实时浏览器会话或可见的渲染状态，而不是静态抓取时使用，尤其是在浏览器调试上下文或 DevTools 选择的元素或请求、登录仪表板或 CMS 流程、localhost 应用、上传、下载、媒体检查、DOM 或 iframe 检查、Shadow DOM，或看起来像软 404、身份验证墙、反机器人检查或速率限制的浏览器故障时。
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.
Semgrep Rule Creator
100Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.
Safe Mode
100Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
Fixflow
100使用严格的交付工作流执行编码任务：构建完整计划、分步实现、持续运行测试，并默认在每一步 (`per_step`) 后提交。当用户要求行为驱动交付或需求不明确时，支持显式提交策略覆盖 (`final_only`, `milestone`) 和可选的 BDD（给定/当/则）。