pm-audit — community pm-audit, dev_ignition, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Project Management Agents needing comprehensive audit and compliance analysis for Ignition development environments. full-stack application for provisioning and managing Ignition development environments. It provides a web-based interface for version control, environment management, automation gateway configuration, device management, Vision client testing with QF-Test automation, gateway health monitoring, and real-time terminal access to containers via WebSkt

LopeWale LopeWale
[1]
[0]
Updated: 2/21/2026

Agent Capability Analysis

The pm-audit skill by LopeWale is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for Project Management Agents needing comprehensive audit and compliance analysis for Ignition development environments.

Core Value

Empowers agents to perform full-stack audits, including version control, environment management, and gateway health monitoring, using configuration data from ops/config.yaml and vocabulary mapping from ops/derivation-manifest.md.

Capabilities Granted for pm-audit

Automating audits for decision register coverage and completeness
Validating schema compliance across all decisions
Identifying orphan decisions and broken wiki-links
Running full audits for all checks

! Prerequisites & Limits

  • Requires access to ops/config.yaml and ops/derivation-manifest.md files
  • Limited to auditing Ignition development environments
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

pm-audit

Install pm-audit, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Runtime Configuration (Step 0)

Read ops/derivation-manifest.md for vocabulary mapping. Read ops/config.yaml for all maintenance thresholds.


EXECUTE NOW

Target: $ARGUMENTS

Parse immediately:

  • If empty: run full audit (all checks)
  • If "orphans": find orphan decisions only
  • If "links": check broken wiki-links only
  • If "schema": validate schema compliance across all decisions
  • If "registers": audit decision register coverage and completeness

START NOW.


Philosophy

A knowledge system that cannot audit itself will rot.

Individual /pm-review checks decisions for quality. /pm-audit checks the system for structural integrity. These are different problems. A system can contain individually high-quality decisions that are nevertheless disconnected, uncategorized, and inaccessible — effectively invisible to future coordination.

/pm-audit is the health scan. It finds the issues that individual review misses: decisions no register points to, wiki-links to files that were deleted or renamed, registers that grew too large to navigate, schema drift where fields added in new templates haven't been backfilled into old decisions.

Run /pm-audit when the vault feels slow or when coordination starts feeling inefficient — that inefficiency often has a structural cause.


Audit Checks

Check 1: Orphan Decisions

A decision not referenced by any decision register is an orphan. Orphans exist in the vault but cannot be discovered through normal navigation.

bash
1# Get all decision filenames 2ls decisions/*.md | grep -v "index.md" | grep -v "-register.md" 3 4# For each decision, check if it appears in any register 5for f in decisions/*.md; do 6 basename=$(basename "$f" .md) 7 count=$(rg "$basename" decisions/*-register.md decisions/index.md --count 2>/dev/null | grep -v ":0" | wc -l) 8 if [ "$count" -eq 0 ]; then 9 echo "ORPHAN: $basename" 10 fi 11done

Wiki-links pointing to non-existent files.

bash
1# Extract all [[links]] from decisions/ 2rg "\[\[([^\]]+)\]\]" decisions/ --include="*.md" -o --no-filename | sort -u 3 4# Cross-reference against actual files 5# Flag any [[link]] where the target file doesn't exist

Check 3: Schema Violations

bash
1# Missing required fields 2rg "^description: \"\"" decisions/ --include="*.md" -l 3rg "last_reviewed: YYYY-MM-DD" decisions/ --include="*.md" -l 4rg "^type: $" decisions/ --include="*.md" -l 5 6# Invalid enum values 7rg "^type:" decisions/ --include="*.md" -h | sort | uniq -c | sort -rn 8rg "^status:" decisions/ --include="*.md" -h | sort | uniq -c | sort -rn 9rg "^meta_state:" decisions/ --include="*.md" -h | sort | uniq -c | sort -rn

Check 4: Register Size and Coverage

bash
1# Count decisions in each register 2for f in decisions/*-register.md; do 3 count=$(rg "\[\[" "$f" | wc -l) 4 echo "$f: $count references" 5done 6 7# Check for registers approaching the split threshold (35 decisions)

Registers approaching 35 decisions should be flagged for split consideration.

Check 5: Stale Decisions

bash
1# Find decisions by last_reviewed date 2# Flag any older than stale_issue_days from config.yaml 3rg "^last_reviewed:" decisions/ --include="*.md" -h | sort | head -20

Check 6: Pending Observations and Tensions Backlog

bash
1# Count pending observations 2rg "^status: pending" ops/observations/ --include="*.md" -l | wc -l 3 4# Count pending tensions 5rg "^status: pending" ops/tensions/ --include="*.md" -l | wc -l

If pending observations > threshold (from config.yaml), flag for /pm-retrospect. If pending tensions > threshold, flag for /pm-retrospect.

Check 7: Inbox Pressure

bash
1ls inbox/ | wc -l

If inbox has items, flag for /pm-document processing.


Output Format

## Audit Complete — YYYY-MM-DD

### System Metrics
- Total decisions: N
- Total decision registers: N
- Total observations (pending/total): N/N
- Total tensions (pending/total): N/N
- Inbox items awaiting processing: N

### Check 1: Orphan Decisions
- Orphans found: N
- [[decision-a]], [[decision-b]] — not referenced by any register

### Check 2: Broken Wiki-Links
- Broken links found: N
- In [[decision-x]]: [[nonexistent-decision]] — target file missing

### Check 3: Schema Violations
- Violations found: N
- [[decision-y]] — missing last_reviewed date
- [[decision-z]] — description is empty

### Check 4: Register Coverage
- [[qftest-register]]: 12 decisions (healthy)
- [[architecture-register]]: 28 decisions (approaching split threshold — flag)
- [[sprint-register]]: 5 decisions (healthy)

### Check 5: Stale Decisions
- Stale decisions (>14 days): N
- [[decision-a]] — last reviewed 21 days ago

### Check 6: Pending Backlog
- Pending observations: N [TRIGGER: /pm-retrospect] if > threshold
- Pending tensions: N [TRIGGER: /pm-retrospect] if > threshold

### Check 7: Inbox
- Inbox items: N [TRIGGER: /pm-document] if > 0

---

### Priority Actions
1. [CRITICAL] Fix N orphan decisions — assign to registers
2. [HIGH] Process N pending observations — run /pm-retrospect
3. [MEDIUM] Update N stale decisions
4. [LOW] Review N schema violations

### Vault Health Score: N/100
[Breakdown: orphans -Xpts, schema violations -Xpts, stale decisions -Xpts, broken links -Xpts]

Vault Health Scoring

IssuePenalty per instance
Orphan decision-3 pts
Broken wiki-link-2 pts
Schema violation-2 pts
Stale decision (>14 days)-1 pt
Pending observation >threshold-5 pts flat
Pending tension >threshold-5 pts flat

Starting from 100. Report final score.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is pm-audit?

Perfect for Project Management Agents needing comprehensive audit and compliance analysis for Ignition development environments. full-stack application for provisioning and managing Ignition development environments. It provides a web-based interface for version control, environment management, automation gateway configuration, device management, Vision client testing with QF-Test automation, gateway health monitoring, and real-time terminal access to containers via WebSkt

How do I install pm-audit?

Run the command: npx killer-skills add LopeWale/dev_ignition. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for pm-audit?

Key use cases include: Automating audits for decision register coverage and completeness, Validating schema compliance across all decisions, Identifying orphan decisions and broken wiki-links, Running full audits for all checks.

Which IDEs are compatible with pm-audit?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for pm-audit?

Requires access to ops/config.yaml and ops/derivation-manifest.md files. Limited to auditing Ignition development environments.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add LopeWale/dev_ignition. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use pm-audit immediately in the current project.

Related Skills

Looking for an alternative to pm-audit or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI