Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
nickcrew avatar

Doc Health Audit

  • 5 installs
  • 28 repo stars
  • Updated June 29, 2026
  • nickcrew/claude-cortex

Helps with security tasks.

About

doc-health-audit is a Claude Code skill for security. It helps solo builders move faster with AI-assisted development.

  • doc-health-audit
  • Security
  • AI-coding skill

Doc Health Audit by the numbers

  • 5 all-time installs (skills.sh)
  • +2 installs in the week ending Jul 26, 2026 (Skillselion tracking)
  • Ranked #1,720 of 2,202 Security skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/nickcrew/claude-cortex --skill doc-health-audit

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs5
repo stars28
Last updatedJune 29, 2026
Repositorynickcrew/claude-cortex

What it does

Helps with security tasks.

Files

SKILL.mdMarkdownGitHub ↗

Documentation Health Audit

Orchestrate a comprehensive documentation assessment across five dimensions. Each phase builds on the previous — structural issues are found before accuracy is checked, accuracy before completeness, and so on.

This skill does not duplicate any phase logic. It defines the run order, phase gating, and combined summary. Each phase delegates to its dedicated skill.

When to Use

  • Pre-release audit — full pass before shipping
  • Periodic health check — monthly or quarterly
  • After a major refactor that touched many docs
  • When documentation quality is unknown or untrusted
  • First-time assessment of a doc set

For single-dimension checks, use the individual skills directly.

Pipeline

Phase 1: Structure     →  doc-maintenance
Phase 2: Accuracy      →  doc-claim-validator
Phase 3: Completeness  →  doc-completeness-audit
Phase 4: Quality       →  doc-quality-review
Phase 5: Architecture  →  doc-architecture-review

Why This Order

Each phase depends on the prior phase being reasonably healthy:

PhaseDepends onReason
StructureFoundation. Broken links and orphans must be visible before anything else
AccuracyStructureCan't verify claims in docs you can't find or that have broken references
CompletenessAccuracyNo point inventorying gaps if existing docs contain false claims
QualityCompletenessReview prose quality only on docs you intend to keep
ArchitectureCompletenessNeed to know what's missing before evaluating whether the structure can hold it

---

Execution

Step 1: Determine Scope

Before running phases, establish what to audit:

  • Full audit — all documentation (docs/, site/, README.md)
  • Scoped audit — specific directory or doc set (e.g., "just the reference section")
  • Changed-only audit — docs modified since a git ref (git diff --name-only main...HEAD -- '*.md')

Pass the scope to each phase so they operate on the same set.

Step 2: Run Phases with Gating

Run each phase sequentially. After each phase, evaluate the gate condition.

Phase 1: Structure (doc-maintenance)

Run: Invoke doc-maintenance on the scoped doc set.

Gate condition: Check the findings.

  • If >10 broken internal links → WARN the user: "Structural issues found. Fix these

first for accurate results in later phases, or continue anyway?"

  • If critical structural issues (missing index pages, completely broken navigation) →

RECOMMEND STOP. Later phases will produce unreliable results.

  • Otherwise → CONTINUE
Phase 2: Accuracy (doc-claim-validator)

Run: Invoke doc-claim-validator on the scoped doc set.

Gate condition: Check the findings.

  • If P0 findings (user-facing docs that would break if followed) → WARN the user.

These should be fixed before assessing completeness, but the audit can continue.

  • Otherwise → CONTINUE
Phase 3: Completeness (doc-completeness-audit)

Run: Invoke doc-completeness-audit on the scoped doc set.

Gate condition: No gate — always continue to quality. Completeness gaps don't affect quality assessment of existing docs.

Phase 4: Quality (doc-quality-review)

Run: Invoke doc-quality-review on the scoped doc set (excluding any docs flagged for removal in earlier phases).

Gate condition: No gate — always continue to architecture.

Phase 5: Architecture (doc-architecture-review)

Run: Invoke doc-architecture-review on the scoped doc set. Pass the completeness gap list from Phase 3 so the architecture review can assess whether the current structure can accommodate the missing docs.

Gate condition: Final phase — no gate.

Step 3: Produce Combined Summary

After all phases complete (or after an early stop), merge results into a single dashboard.

---

Combined Summary Format

# Documentation Health Audit

**Audit date:** YYYY-MM-DD
**Scope:** [what was audited]
**Phases completed:** N / 5
**Early stop:** [yes/no — if yes, which phase and why]

---

## Dashboard

| Phase | Skill | Status | Key Metric | Top Finding |
|-------|-------|--------|------------|-------------|
| 1. Structure | doc-maintenance | PASS/WARN/FAIL | N broken links, N orphans | [one line] |
| 2. Accuracy | doc-claim-validator | PASS/WARN/FAIL | N P0, N P1 claims failed | [one line] |
| 3. Completeness | doc-completeness-audit | PASS/WARN/FAIL | N% coverage, N P0 gaps | [one line] |
| 4. Quality | doc-quality-review | PASS/WARN/FAIL | Grade: [A-F], avg score N/25 | [one line] |
| 5. Architecture | doc-architecture-review | PASS/WARN/FAIL | Grade: [A-F], N/35 score | [one line] |

**Overall health:** [Healthy / Needs Attention / Critical]

---

## Priority Actions

Top 5 actions across all phases, ordered by impact:

1. [Phase N] [specific action] — [why it matters]
2. [Phase N] [specific action] — [why it matters]
3. [Phase N] [specific action] — [why it matters]
4. [Phase N] [specific action] — [why it matters]
5. [Phase N] [specific action] — [why it matters]

---

## Phase Reports

[Include or link to each phase's full report below]

### Phase 1: Structure
[doc-maintenance report]

### Phase 2: Accuracy
[doc-claim-validator report]

### Phase 3: Completeness
[doc-completeness-audit report]

### Phase 4: Quality
[doc-quality-review report]

### Phase 5: Architecture
[doc-architecture-review report]

---

Partial Runs

Not every audit needs all five phases. Common partial runs:

ScenarioPhases to run
"Are the docs accurate?"1 + 2 only
"What's missing?"1 + 3 only
"Is the writing good?"4 only
"Can users find things?"1 + 5 only
"Quick pre-release check"1 + 2 + 3 (skip quality and architecture)
"Full audit"All 5

When running a subset, skip gates for omitted phases.

---

Anti-Patterns

  • Do not run all five phases if you only need one — use the individual skill directly
  • Do not skip Phase 1 (structure) — it's the foundation for everything else
  • Do not ignore gate warnings — they exist because later phases produce unreliable results on broken foundations
  • Do not combine this with doc remediation in the same session — audit first, fix separately
  • Do not run this on archived docs (docs/archive/) — they are historical

Related skills

Securityappsec

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.