Skip to content

mgiovani/ai-arsenal / skills/docs-check

docs-check

Verified

Read-only audit of documentation against the current codebase, flags stale docs, missing sections, broken links, and hallucinated claims (wrong file references, wrong counts, diagram entities that don't exist in code). Use for "check the docs", "audit documentation", "are the docs stale", "find hallucinations in docs", "docs health check", "does this doc still match the code", or before onboarding/release. Reports only, never edits files, for actually fixing or regenerating docs use docs-update instead.

FileKindSize
SKILL.mdskill md8.0 KB
evals/evals.jsonconfig3.6 KB
evals/trigger-eval.jsonconfig1.9 KB
references/scoring-criteria.mdmarkdown2.0 KB
references/verification-patterns.mdmarkdown4.8 KB

evals/trigger-eval.json

View on GitHub
[
  {"query": "can you check if our docs are stale compared to the code", "should_trigger": true},
  {"query": "audit documentation in docs/ and tell me what's out of date", "should_trigger": true},
  {"query": "does docs/architecture.md still match the actual services we have?", "should_trigger": true},
  {"query": "find hallucinations in our README, like made-up file references", "should_trigger": true},
  {"query": "run a docs health check before we onboard the new hires", "should_trigger": true},
  {"query": "is the ER diagram in data-model.md still accurate?", "should_trigger": true},
  {"query": "we're about to release, can you flag any broken links or stale sections in the docs", "should_trigger": true},
  {"query": "the README claims 5 microservices, is that still true?", "should_trigger": true},
  {"query": "check docs quality, focus on core", "should_trigger": true},
  {"query": "our onboarding doc might be out of sync with the codebase, verify it", "should_trigger": true},
  {"query": "update the architecture doc to match the new microservices split", "should_trigger": false},
  {"query": "regenerate the ER diagram for data-model.md", "should_trigger": false},
  {"query": "write an ADR for switching to event sourcing", "should_trigger": false},
  {"query": "create the initial docs/ structure for this new project", "should_trigger": false},
  {"query": "review this PR for correctness and style before I merge", "should_trigger": false},
  {"query": "do a security review of the auth module", "should_trigger": false},
  {"query": "draft an RFC proposing we move to a monorepo", "should_trigger": false},
  {"query": "sync the README with the current package.json dependencies", "should_trigger": false},
  {"query": "generate a Mermaid diagram of the service architecture", "should_trigger": false},
  {"query": "fix the broken links you found in the docs last time", "should_trigger": false}
]
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall