← ClaudeAtlas

docguard-guardlisted

Run DocGuard guard validation against Canonical-Driven Development standards. Parses output, triages severity, suggests targeted fixes, and optionally chains to docguard-fix for automated remediation. Use as a quality gate before commits or after implementation phases.
jaroslawherod/micold-ai-ide · ★ 1 · AI & Automation · score 70
Install: claude install-skill jaroslawherod/micold-ai-ide
<!-- docguard:version: 0.34.9 --> # DocGuard Guard Skill ## User Input ```text $ARGUMENTS ``` You **MUST** consider the user input before proceeding (if not empty). ## Goal Execute DocGuard's full guard validator suite against the current project, parse structured results, triage findings by severity and impact, and produce an actionable remediation plan. This skill transforms raw CLI output into an AI-digestible quality assessment. ## Pre-Execution Checks 1. **Verify DocGuard is available**: - Check if `npx docguard-cli --version` succeeds - If not available, check if `node cli/docguard.mjs --help` exists (local dev mode) - If neither works: ERROR "DocGuard CLI not found. Install with: npm i -g docguard-cli" 2. **Detect project root**: - Look for `.docguard.json`, `docs-canonical/`, or `CHANGELOG.md` as project markers - If none found: ERROR "No CDD project detected. Run `docguard init` first." ## Execution Flow ### Step 1: Run Guard with Machine-Readable Output Execute the guard command and capture full output: ```bash npx docguard-cli guard 2>&1 ``` If in a DocGuard development environment (cli/docguard.mjs exists), use: ```bash node cli/docguard.mjs guard 2>&1 ``` ### Step 2: Parse Validator Results Extract from guard output each validator's status. Build an internal results table: | Validator | Priority | Checks Passed | Total Checks | Status | |-----------|----------|---------------|--------------|--------| | Structure | HIGH | N | M | ✅/