Agent skill · Security

codebase-audit

Perform a full codebase review, categorize findings by severity, file GitHub issues, then fix each issue in an isolated git worktree and submit PRs. Use this skill when the user asks to audit the codebase, do a comprehensive code review, find and fix security/quality/reliability issues, or run a proactive health check across the entire repository.

TencentCloudBasegithub.com/TencentCloudBaseGitHub ↗
claude-codecursorMIT
Install
npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill codebase-audit --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 8
SKILL.md size: 7 KB
Bundled scripts: none
Path: skills/codebase-audit/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,066
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Codebase Audit → Issue → Worktree Fix → PR End-to-end workflow: systematically review the entire codebase, report findings as GitHub issues, fix each issue in an isolated git worktree, and submit PRs — all in one session. ## When to use this skill Use this skill when you need to: - Perform a full code review / audit of the codebase - Proactively find security vulnerabilities, logic bugs, or code quality problems - Turn code review findings into tracked GitHub issues - Fix each issue in isolation (worktree per issue) and submit PRs - Run a periodic codebase health check with automated follow-through - Audit and fix dependency security vulnerabilities (Dependabot alerts / npm audit) **Do NOT use for:** - Reviewing or fixing a single known bug (use `systematic-debugging` or direct fix) - Triaging existing open PRs (use `pr-review-fix`) - Processing attribution issues (use `mcp-attribution-worktree`) - Feature development or refactoring unrelated to audit findings ## Workflow ### Phase 1 — Review 1. Read `references/review-strategy.md` for the review scope and checklist. 2. Use the `code-explorer` subagent to read ALL source files in the target directory (default: `mcp/src/`). 3. For

What's inside
Steps it walks through
  1. When to use this skill
  2. Workflow
  3. Phase 1 — Review
  4. Phase 2 — Analyze & Classify
  5. Phase 3 — Create GitHub Issues
  6. Phase 4 — Worktree Fix
  7. Phase 5 — Verify & Report
  8. Routing
  9. Git safety rules
  10. Commit conventions
  11. Minimum self-check
Ships with 7 files
  • references/classification.md
  • references/dependency-audit.md
  • references/issue-workflow.md
  • references/review-strategy.md
  • references/security-severity-checklist.md
  • references/verification.md
  • references/worktree-fix.md
Commands it runs
gh issue create --title "<type>(<scope>): <summary>" --body "<structured body>" --label "<severity>,<category>"
git worktree add ../<repo>-audit-fix-<issue-number> -b fix/<slug>-<issue-number> origin/main
git commit -m 'fix(<scope>): 🔒 <english description>
Closes #<issue-number>'
git push github fix/<slug>-<issue-number>
gh pr create --title "fix(<scope>): 🔒 <summary>" --body "Closes #<issue-number>\n\n<description>" --base main
cd <original-dir>
git worktree remove ../<repo>-audit-fix-<issue-number>
gh pr checks <number>
More from CloudBase-AI-Toolkit
All skills →
About this skill
What does the codebase-audit skill do?

Perform a full codebase review, categorize findings by severity, file GitHub issues, then fix each issue in an isolated git worktree and submit PRs. Use this skill when the user asks to audit the codebase, do a comprehensive code review, find and fix security/quality/reliability issues, or run a proactive health check across the entire repository.

How do I install it?

Run `npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill codebase-audit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From TencentCloudBase/CloudBase-AI-Toolkit, a repository with 1,066 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going