Harness-engineering harness-docs-pipeline

name: harness-docs-pipeline version: "1.0.0" description: Orchestrator composing 4 documentation skills into a sequential pipeline with convergence-based remediation and qualitative health reporting stability: static cognitive_mode: constructive-architect triggers:

• manual
• on_doc_check platforms:
• claude-code
• gemini-cli
• cursor
• codex tools:
• Bash
• Read
• Write
• Edit
• Glob
• Grep cli: command: harness skill run harness-docs-pipeline args:
  • name: path description: Project root path required: false
  • name: fix description: Enable convergence-based auto-fix (default detect + report only) required: false
  • name: no-freshen description: Skip graph staleness check required: false
  • name: bootstrap description: Force AGENTS.md regeneration even if one exists required: false
  • name: ci description: Non-interactive mode — apply safe fixes only, report everything else required: false mcp: tool: run_skill input: skill: harness-docs-pipeline path: string type: rigid tier: 2 phases:
• name: freshen description: Check graph freshness, detect AGENTS.md, trigger bootstrap if needed required: true
• name: detect description: Invoke detect-doc-drift, classify and prioritize findings required: true
• name: fix description: Convergence loop — classify, apply safe fixes, verify, re-detect required: false
• name: audit description: Invoke validate-context-engineering, find gaps, dedup against fixes required: true
• name: fill description: Convergence loop — fill gaps, regenerate AGENTS.md if needed, verify required: false
• name: report description: Synthesize verdict (PASS/WARN/FAIL) with per-category breakdown required: true state: persistent: false files:
  • .harness/handoff.json depends_on:
• detect-doc-drift
• align-documentation
• validate-context-engineering
• harness-knowledge-mapper