agentleFS
jaroslawherodjaroslawherod/micold-ai-ide/.claude/skills/speckit-docguard-guard/SKILL.md

speckit-docguard-guard

Skill1 starsChanged 3 days agoApache-2.0View on GitHub

Run the full quality gate with severity triage and actionable remediation

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run DocGuard guard validation:

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Docguard Guard Skill

DocGuard Guard

Validate your project against its canonical documentation. Runs 160+ automated checks across validators.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Execution

  1. Run DocGuard guard validation:
npx --yes docguard-cli@latest guard $ARGUMENTS
  1. Parse each validator's result and build a severity-ranked findings table. Status glyphs: ✅ pass, ⚠️ warning, ❌ fail, ➖ N/A (nothing to validate — NOT a pass; the dimension was not assessed).
  2. Triage by severity:
    • CRITICAL: Structure, Security, Test-Spec failures → fix immediately
    • HIGH: Doc Sections, Drift-Comments, Changelog, Traceability, API-Surface → fix before commit
    • MEDIUM: Freshness, Docs-Coverage, Doc-Quality, Metrics → fix this sprint
    • LOW: TODO-Tracking, Schema-Sync, Spec-Kit, Metadata → fix when convenient
  3. For each failing check, provide an exact fix — specific file, section, and content.
  4. Re-run guard after fixes. Iterate until all checks pass (max 3 iterations).

Validators

ValidatorWhat It Checks
StructureRequired CDD files exist
Doc SectionsCanonical docs have required sections
Docs-SyncExternal doc references are valid
Drift-Comments// DRIFT: comments have DRIFT-LOG entries
ChangelogCHANGELOG.md is maintained
Test-SpecTEST-SPEC.md matches actual test files
EnvironmentEnvironment docs and .env.example exist
SecurityNo hardcoded secrets, .gitignore configured
ArchitectureLayer boundaries and diagrams present
FreshnessDocs updated after recent code changes
TraceabilityCanonical docs linked to source code
Docs-DiffEntity/route/field drift between code and docs
API-SurfaceAPI-REFERENCE.md endpoints match the real API surface (OpenAPI spec / routes)
Metadata-SyncMetadata headers are consistent
Docs-CoverageAll config files documented
Doc-QualityReadability, IEEE 830 compliance
TODO-TrackingTODOs are tracked
Schema-SyncSchema documentation matches code
Spec-KitSpec quality (FR-IDs, sections)
Metrics-ConsistencyInternal counts are accurate

Flags

  • --format json — Output results as JSON
  • --dir <path> — Run on a different directory

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.