ln-611-docs-structure-auditor
Scannednpx machina-cli add skill levnikolaevich/claude-code-skills/ln-611-docs-structure-auditor --openclawPaths: File paths (
shared/,references/,../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.
Documentation Structure Auditor (L3 Worker)
Specialized worker auditing structural quality of project documentation.
Purpose & Scope
- Worker in ln-610 coordinator pipeline - invoked by ln-610-docs-auditor
- Audit documentation for structural quality across 7 categories
- Scan all
.mdfiles in project, build hierarchy from CLAUDE.md - Return structured findings to coordinator with severity, location, recommendations
- Calculate compliance score (X/10) for Documentation Structure
Inputs (from Coordinator)
MANDATORY READ: Load shared/references/task_delegation_pattern.md#audit-coordinator--worker-contract for contextStore structure.
Receives contextStore with: tech_stack, project_root, output_dir.
Workflow
- Parse Context: Extract tech stack, project root, output_dir from contextStore
- Scan Docs: Find all
.mdfiles in project (CLAUDE.md, README.md, docs/**) - Build Tree: Construct hierarchy from CLAUDE.md outward links
- Audit Categories 1-7: Run structural checks (see Audit Categories below)
- Collect Findings: Record each violation with severity, location (file:line), effort estimate (S/M/L), recommendation
- Calculate Score: Count violations by severity, calculate compliance score (X/10)
- Write Report: Build full markdown report per
shared/templates/audit_worker_report_template.md, write to{output_dir}/611-structure.mdin single Write call - Return Summary: Return minimal summary to coordinator (see Output Format)
Audit Categories
| # | Category | What to Check |
|---|---|---|
| 1 | Hierarchy & Links | CLAUDE.md is root; all docs reachable via links; no orphaned files; no broken links |
| 2 | Single Source of Truth | No content duplication; duplicates replaced with links to source; clear ownership |
| 3 | Proactive Compression | Eliminate verbose/redundant content; prose to tables; remove meaningless info; compress even under-limit files; see size_limits.md |
| 4 | Requirements Compliance | Correct sections; within size limits; no code blocks (tables/ASCII diagrams/text only); stack-appropriate doc links |
| 5 | Actuality (CRITICAL) | Verify facts against code: paths exist, functions match, APIs work, configs valid; outdated docs are worse than none |
| 6 | Legacy Cleanup | No history sections; no "was changed" notes; no deprecated info; current state only |
| 7 | Stack Adaptation | Links/refs match project stack; no Python examples in .NET project; official docs for correct platform |
Severity Mapping
| Issue Type | Severity |
|---|---|
| Outdated content (code mismatch) | CRITICAL |
| Broken links, orphaned docs | HIGH |
| Content duplication | MEDIUM |
| Missing compression opportunity | LOW |
| Legacy/history content | MEDIUM |
| Wrong stack references | HIGH |
Scoring Algorithm
MANDATORY READ: Load shared/references/audit_scoring.md for unified scoring formula.
Output Format
MANDATORY READ: Load shared/templates/audit_worker_report_template.md for file format.
Write report to {output_dir}/611-structure.md with category: "Documentation Structure" and checks: hierarchy_links, ssot, compression, requirements_compliance, actuality, legacy_cleanup, stack_adaptation.
Return summary to coordinator:
Report written: docs/project/.audit/ln-610/{YYYY-MM-DD}/611-structure.md
Score: X.X/10 | Issues: N (C:N H:N M:N L:N)
Critical Rules
- Do not auto-fix: Report violations only; coordinator aggregates for user
- Tech stack aware: Use contextStore
tech_stackto apply stack-specific checks (e.g., .NET vs Node.js doc standards) - Verify facts against code: Actively check every path, function name, API, config mentioned in docs
- Compress always: Size limits are upper bounds, not targets. A 100-line file instead of 300 is a win
- No code in docs: Documents describe algorithms in tables or ASCII diagrams. Code belongs in codebase
- Code is truth: When docs contradict code, report docs as needing update (not code)
- Delete, don't archive: Legacy content should be removed, not moved to "archive"
- Location precision: Always include
file:linefor programmatic navigation
Definition of Done
- contextStore parsed successfully (including output_dir)
- All 7 structural categories audited
- Findings collected with severity, location, effort, recommendation
- Score calculated using penalty algorithm
- Report written to
{output_dir}/611-structure.md(atomic single Write call) - Summary returned to coordinator
Reference Files
- Worker report template:
shared/templates/audit_worker_report_template.md - Audit scoring formula:
shared/references/audit_scoring.md - Audit output schema:
shared/references/audit_output_schema.md - Size limits and targets: references/size_limits.md
- Detailed checklist: references/audit_checklist.md
Version: 1.0.0 Last Updated: 2026-03-01
Source
git clone https://github.com/levnikolaevich/claude-code-skills/blob/master/ln-611-docs-structure-auditor/SKILL.mdView on GitHub Overview
The Documentation Structure Auditor is an L3 worker in the Claude-based pipeline. It scans all Markdown files, builds a hierarchy from CLAUDE.md outward links, checks seven structural categories, and returns findings with severity, location, and recommendations, plus a compliance score.
How This Skill Works
The agent loads contextStore, discovers the project root, and scans all Markdown files (CLAUDE.md, README.md, docs/**). It builds a hierarchical tree from CLAUDE.md via outward links, runs seven structural checks, records findings with severity, location, and effort, computes a score, and writes a single report to {output_dir}/611-structure.md using the audit worker template, then returns a summary to the coordinator.
When to Use It
- When validating documentation hierarchy and link integrity in a CLAUDE-based project
- When enforcing a single source of truth and avoiding content duplication
- When cleaning up legacy or deprecated content and removing outdated notes
- When ensuring stack-appropriate references and avoiding wrong platform examples
- When preparing a formal Documentation Structure score for audits
Quick Start
- Step 1: Load contextStore from shared/references/task_delegation_pattern.md and locate repo root
- Step 2: Run the auditor over all Markdown files (CLAUDE.md, README.md, docs/**) using Read/Grep/Glob/Bash
- Step 3: Open {output_dir}/611-structure.md to review checks and the computed Score, then report to the coordinator
Best Practices
- - Treat CLAUDE.md as the root and ensure all docs are reachable via links
- - Replace content duplication with links to the source and assign clear ownership
- - Apply proactive compression to verbose sections per size_limits.md guidelines
- - Ensure requirements sections are present, free of code blocks where required, and contain valid links
- - Run audits regularly and update the 611-structure.md report in the designated output_dir
Example Use Cases
- Audit a CLAUDE-based repository to surface orphaned docs and broken links
- Identify duplicated content and replace with proper source-linked references
- Compress verbose sections by converting to concise tables or summaries
- Verify code-related paths and APIs align with documented references
- Generate and publish the 611-structure.md report for ln-610 coordination