DocSutra AIDocumentation Truth Audit - v0.2.1 - by Vatsal Shah

Agent skills guide

The 16 portable skills, what backs each one, how to install them, and what is and is not verified.

What a skill is

A skill is a folder with a SKILL.md file (YAML frontmatter plus instructions) following the Agent Skills layout. DocSutra ships them in .agents/skills/ and copies them into the folder each AI host reads.

Install

docsutra install-skills --host claude --target .
HostFolder
Claude Code.claude/skills/
Cursor.cursor/skills/
Codex.agents/skills/
Gemini CLI.gemini/skills/
GitHub Copilot.github/skills/

These are installation paths. Host activation has not been verified in any of the five hosts. If a host does not load them, use the CLI directly.

The 16 skills and what backs them

SkillBackingPurpose
docsutra-primeCLIOrchestrates a read-only audit and routes findings
docsutra-link-guardianCLIFix broken links, anchors, case mismatches
docsutra-cli-contractCLICompare documented commands to a declared contract
docsutra-privacy-guardCLICredentials, unsafe schemes, pipe-to-shell, destructive commands
docsutra-accessible-docsCLIAlt text, link text, heading structure
docsutra-snippet-labCLI (classification only)Plan which snippets are safe to test; never executes
docsutra-evidence-verifierCLIIndependently re-check findings before reporting
docsutra-drift-radarCLI (diff)New versus resolved findings, baseline gating
docsutra-truth-keeperInstructions onlyClaim-by-claim fact checking against source
docsutra-api-cartographerInstructions onlyDocumented API versus actual API
docsutra-schema-sentinelInstructions onlyExample payloads versus a schema
docsutra-example-forgeInstructions onlyMinimal, verified examples
docsutra-diagram-alignmentInstructions onlyDiagrams versus repository structure
docsutra-localizationInstructions onlyTranslation parity
docsutra-patch-crafterInstructions onlySmallest reviewable fix previews
docsutra-release-notesInstructions onlyEvidence-based release notes

Why keep instruction-only skills

They carry the same guardrails (untrusted documents, no execution without approval, labelled evidence, redaction, preview-only edits) and require citations. They are marked instructions-only in each file and in agents/manifest.json so nobody mistakes them for automated checks. A test enforces that instruction-only skills never claim a CLI rule and CLI-backed skills reference real rule IDs.

Guardrails in every skill

Regenerating

Skills and the manifest are generated from one source: npm run build:skills. Edit scripts/build-skills.mjs, not the individual files.