PackmindHub/doc-audit
.cursor/skills/doc-audit/SKILL.md
Audit Packmind end-user documentation (apps/doc/) for broken links, outdated CLI references, non-existent concepts, misleading information, and missing coverage. Produces a structured markdown report at project root. Use when docs may have drifted from the codebase, before a release, or on a regular cadence.
$ install --global
skillsauthnpx skillsauth add PackmindHub/packmind doc-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 9:34 PM2.2s1 file scanned
SKILL.md
- name:
- doc-audit
- description:
- Audit Packmind end-user documentation (apps/doc/) for broken links, outdated CLI references, non-existent concepts, misleading information, and missing coverage. Produces a structured markdown report at project root. Use when docs may have drifted from the codebase, before a release, or on a regular cadence.
Documentation Audit
Detect outdated, broken, or misleading documentation by cross-referencing MDX pages against the actual codebase. Produces a structured doc-audit-report.md at the project root.
This skill only detects issues — it does not fix them.
Phase 1: Build Ground Truth
Before launching any sub-agents, build a concise ground truth summary by gathering these four data sources:
- Navigation structure — Read
apps/doc/docs.jsonand extract all navigation groups with their page lists - CLI commands — List files in
apps/cli/src/infra/commands/to get current command files - Domain packages — List directories in
packages/to get current package names - Doc MDX files — Glob
apps/doc/**/*.mdxto get all actual pages on disk
Compile these into a ground truth summary string formatted as:
## Ground Truth
### Navigation Groups (from docs.json)
- Getting Started: index, getting-started/gs-install-cloud, ...
- Concepts: concepts/standards-management, ...
[list all groups]
### CLI Commands (from apps/cli/src/infra/commands/)
[list all *Command.ts and *Handler.ts files]
### Domain Packages (from packages/)
[list all package directory names]
### MDX Files on Disk (from apps/doc/**/*.mdx)
[list all .mdx file paths relative to apps/doc/]
### Current Date
{today's date}
Phase 2: Launch Parallel Sub-Agents
Launch 5 Explore sub-agents in parallel (subagent_type: Explore), one per section group. Each agent receives:
- The ground truth summary from Phase 1
- The full contents of
references/section-audit-instructions.md(read this file and include its contents in each prompt) - Its assigned section and list of MDX files to audit
Agent Assignments
| Agent | Sections | Pages to Audit |
|-------|----------|----------------|
| 1 | Getting Started + root pages | index.mdx, home.mdx + all getting-started/*.mdx |
| 2 | Concepts | All concepts/*.mdx + tools/import-from-knowledge-base.mdx |
| 3 | Tools & Integrations | tools/cli.mdx |
| 4 | Governance + Playbook Maintenance + Linter | All governance/*.mdx + playbook-maintenance/*.mdx + linter/*.mdx |
| 5 | Administration + Security | All administration/*.mdx + security/*.mdx |
Agent Prompt Template
Each agent's prompt should follow this structure:
You are auditing the {section_name} section of the Packmind documentation.
## Your Assigned Pages
{list of MDX file paths to read and audit}
## Ground Truth
{ground truth summary from Phase 1}
## Audit Instructions
{full contents of references/section-audit-instructions.md}
Read each assigned MDX page completely and apply all detection categories. Return your findings in the exact format specified in the instructions.
Sequential Fallback
If the Agent tool is unavailable, perform the audit sequentially: read each section's pages one by one and apply the same checks from references/section-audit-instructions.md directly.
Phase 3: Consolidate Report
After all sub-agents complete:
- Collect all findings from the 5 agents
- Deduplicate — remove exact duplicates (same page, same line, same issue)
- Sort by severity: ERROR first, then WARNING, then INFO
- Group by category within each severity level
- Write the report to
doc-audit-report.mdat the project root
Report Format
# Documentation Audit Report
Generated: {date} | Pages audited: {count}
## Summary
| Severity | Count |
|----------|-------|
| ERROR | N |
| WARNING | N |
| INFO | N |
## Errors
### [A] Broken Internal Links
- **{page}** (line ~{N}): Link to `{target}` — no matching MDX file exists
[... more findings]
### [B] Outdated CLI Commands
- **{page}** (line ~{N}): References `packmind-cli {cmd}` — command not found in CLI source
[... more findings]
### [C] Non-Existent Concepts
- **{page}** (line ~{N}): References `{concept}` — not found in codebase
[... more findings]
## Warnings
### [D] Misleading Information
- **{page}** (line ~{N}): "{quoted text}" — {reason}
[... more findings]
## Info
### [E] Missing Documentation Coverage
- CLI command `{cmd}` has no documentation
- Package `{pkg}` has no documentation page
[... more findings]
Omit any category section that has zero findings. Only include sections with actual results.
After writing the report, print a brief summary:
- Total issues found per severity
- Top 3 most problematic pages (by issue count)
- The report file path
Related Skills
PackmindHub/michel-ui-demo-recorder
tools
VerifiedTrustedCommunity
Record polished UI demo videos and screenshots of a running web app using Playwright MCP — for client deliverables, release notes, feature walkthroughs, or bug repros. Produces an HD WebM video with chapter markers, a mandatory animated cursor overlay, and a mandatory subtitle bar that narrates each step (positioned deliberately so it never masks the UI being demonstrated), plus full-page screenshots at each step. Use this whenever the user asks to "record a demo", "create a screencast", "make a UI walkthrough video", "document this feature with video", "show the client how X works", "capture screenshots of the app", or anything similar — even when the user only says "make a video" or "take screenshots" in the context of a running frontend. Also use it when the user wants to demonstrate a workflow, generate marketing-quality footage of an app, or produce repeatable visual documentation.
288SKILL.mdUpdated Jun 4, 2026
PackmindHub/michel-run-local-dev-stack
tools
VerifiedTrustedCommunity
The canonical recipe for starting, checking, and stopping the Packmind local dev stack with Docker Compose — the single source of truth other skills and the Michel agent defer to. Covers bringing the full stack (PostgreSQL, Redis, NestJS API, React/Vite frontend on :4200, MCP server, nginx) up in the background, the init services (dependency install + TypeORM migrations) you must wait on, the critical host-port trap that the API on container port 3000 is NOT exposed to the host and must be reached via the frontend Vite proxy at localhost:4200/api/v0, confirming the API and frontend are actually serving before you depend on them, the persistent-volume gotcha that leaves stale Postgres schema and node_modules behind between runs, building the CLI, and tearing everything down so no container is left blocking the run. Use this whenever you need Packmind running locally — to verify a change, record a UI or CLI demo, hit the API, seed data, or reproduce a bug — and whenever you are about to start or stop `docker compose`. If you are an autonomous agent (e.g. Michel) that started the stack, you MUST use the teardown half before finishing. Prefer this over running `nx serve` on the host for anything that needs the real, containerized stack.
288SKILL.mdUpdated Jun 4, 2026
PackmindHub/michel-create-pr-with-screenshots
tools
VerifiedTrustedCommunity
Best practices for creating GitHub pull requests that include inline images — CLI terminal screenshots (from cli-demo-recorder), UI screenshots/videos (from ui-demo-recorder), or any other visual artifact. Use this skill whenever opening or updating a PR that has visual artifacts to embed, or when images aren't rendering in a PR description. Also use it when asked "how do I add screenshots to a PR", "why isn't my image showing", or "embed a demo in the PR".
288SKILL.mdUpdated Jun 4, 2026
PackmindHub/scripts/michel/michel-create-packmind-dataset
tools
VerifiedTrustedCommunity
--- name: michel-create-packmind-dataset description: Seed a local Packmind instance with a realistic dataset — one organization populated with standards, commands, and skills — so an autonomous agent can exercise its own changes against lifelike data instead of an empty app. Use this whenever you need populated Packmind data to verify a change end-to-end: reproducing a bug that only shows with existing artifacts, recording a UI/CLI demo that needs content on screen, smoke-testing a new endpoint
288SKILL.mdUpdated Jun 4, 2026