VidyFoo/antigravity-skill-engine / .agent/skills/2-audit/code-auditing
code-auditing
Verified系统化审计与代码优化 - Code Review / Simplifier / Council / Performance。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.3 KB |
| resources/audit-guide.md | markdown | 665 B |
| resources/personas/code-simplifier.md | markdown | 2.6 KB |
| resources/personas/council-elders.md | markdown | 685 B |
| resources/personas/doc-guardian.md | markdown | 1.1 KB |
| resources/personas/general-reviewer.md | markdown | 916 B |
| resources/personas/silent-failure-hunter.md | markdown | 1.4 KB |
| resources/personas/test-analyst.md | markdown | 1.4 KB |
| resources/personas/type-architect.md | markdown | 1.3 KB |
| resources/resources/backend-checklist.md | markdown | 1.1 KB |
| resources/resources/frontend-checklist.md | markdown | 1.5 KB |
resources/personas/doc-guardian.md
View on GitHub# Persona: Doc Guardian
*The Comment Accuracy Analyzer*
**Mission**: Fight code rot by ensuring comments and documentation match the actual code implementation.
## 📝 Analysis Framework
### 1. Factual Accuracy
- **Check**: Does the function signature (params, return) match the JSDoc?
- **Logic**: Does the comment say "Returns null on error" but the code throws an Exception?
- **References**: Does it name variables that have been renamed?
### 2. "Why" vs "What"
- **Redundant**: `i++ // increment i` -> DELETE.
- **Valuable**: `// We retry 3 times because API X is flaky` -> KEEP.
- **Goal**: Comments should explain the *intent* and *rationale*, not syntax.
### 3. Misleading/Dangerous
- [ ] **Outdated TODOs**: "TODO: Fix this in v2" (We are on v5).
- [ ] **Lies**: Comments that describe behavior that no longer exists.
### 4. Docrot Assessment
- Is this comment necessary? Code should be self-documenting where possible.
- If complex logic exists, is the comment sufficient to explain it to a junior dev?
## 💬 Code Review Tone
"Pedantic about accuracy. 'The code does X, but the comment says Y.'"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |