System
Customization
Before executing, check for user customizations at:
~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/System/
If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.
System Skill
System validation, integrity audits, documentation tracking, and security scanning for the PAI system.
Visibility
This skill runs in the foreground so you can see all output, progress, and hear voice notifications as work happens. Documentation updates, integrity checks, and other system operations should be visible to maintain transparency.
Voice Notification
When executing a workflow, do BOTH:
-
Send voice notification:
curl -s -X POST http://localhost:8888/notify \ -H "Content-Type: application/json" \ -d '{"message": "Running WORKFLOWNAME workflow from System skill"}' \ > /dev/null 2>&1 & -
Output text notification:
Running the **WorkflowName** workflow from the **System** skill...
Workflow Routing
Core Operations (The Three)
| Workflow | Trigger | Purpose | File |
|---|---|---|---|
| IntegrityCheck | "integrity check", "audit system", "check references", "system health" | Find and fix broken references across the system | Workflows/IntegrityCheck.md |
| DocumentSession | "document session", "document today", "document this session", "log session" | Document current session's work from transcript | Workflows/DocumentSession.md |
| DocumentRecent | "document recent", "catch up docs", "what's undocumented", "document since last update" | Catch-up documentation for changes since last documented update | Workflows/DocumentRecent.md |
Composition Rules:
- Integrity Check → may produce fixes → Document Session
- After any session → Document Session
- Periodic catch-up → Document Recent
Security Workflows
| Workflow | Trigger | File |
|---|---|---|
| SecretScanning | "check for secrets", "scan for credentials", "security scan" | Workflows/SecretScanning.md |
| PrivacyCheck | "privacy check", "check for sensitive data", "data isolation" | Workflows/PrivacyCheck.md |
Utility Workflows
| Workflow | Trigger | File |
|---|---|---|
| WorkContextRecall | "we just worked on", "what did we do with", "remember when we", "didn't we already" | Workflows/WorkContextRecall.md |
Note: For public PAI integrity ("check PAI integrity", "audit PAI packs"), use the PAI skill → PAIIntegrityCheck.md
Examples
Core Operations
Example 1: Integrity Check
User: "Run an integrity check"
→ Invokes IntegrityCheck workflow
→ Spawns parallel agents to audit ~/.claude
→ Finds broken references, missing files
→ Returns list of issues found/fixed
Example 2: Document Current Session
User: "Document this session"
→ Invokes DocumentSession workflow
→ Reads current session transcript
→ Uses AI to extract what changed and why
→ Creates entry in MEMORY/PAISYSTEMUPDATES/
Example 3: Catch-up Documentation
User: "What's undocumented? Catch up the docs."
→ Invokes DocumentRecent workflow
→ Finds last documented update timestamp
→ Compares git history since then
→ Generates documentation for missed changes
Security Workflows
Example 4: Secret Scanning
User: "Check for secrets before I push"
→ Invokes SecretScanning workflow
→ Runs TruffleHog on specified directory
→ Reports any API keys, credentials found
Utility
Example 5: Recall Past Work
User: "We just worked on the status line - why broken again?"
→ Invokes WorkContextRecall workflow
→ Searches MEMORY/, git history for "status line"
→ Presents timeline of changes and possible regression
Quick Reference
The Three Core Operations
| Operation | Input | Output | Duration |
|---|---|---|---|
| IntegrityCheck | Codebase scan | List of broken refs found/fixed | ~2-5 min |
| DocumentSession | Session transcript | PAISYSTEMUPDATES entry | ~30s |
| DocumentRecent | Git history since last update | Multiple PAISYSTEMUPDATES entries | ~1-2 min |
Composition Patterns
End of Session: DocumentSession
After Refactoring: IntegrityCheck → DocumentSession
Catch-up: DocumentRecent
Security Audits
| Audit Type | Tool | Scope | Duration |
|---|---|---|---|
| Secret Scan | TruffleHog | Any directory | ~30s-2min |
| Privacy Check | grep/patterns | skills/ (excl USER/WORK) | ~30s |
Documentation Format
Verbose Narrative Structure:
- The Story (1-3 paragraphs): Background, Problem, Resolution
- How It Used To Work: Previous state with bullet points
- How It Works Now: New state with improvements
- Going Forward: Future implications
- Verification: How we know it works
When to Use
Integrity Checks
- After major refactoring
- Before releasing updates
- Periodic system health checks
- When something "feels broken"
- Before pushing to public PAI repo
Documentation
- End of significant work sessions
- After creating new skills/workflows/tools
- When architectural decisions are made
- To maintain system history
Security Scanning
- Before any git commit to public repos
- When auditing for credential leaks
- Periodic security hygiene checks
- After receiving external code/content
Privacy Validation
- After working with USER/ or WORK/ content
- Before any public commits
- When creating new skills that might reference personal data
- Periodic audit to ensure data isolation
Work Context Recall
- When user asks about past work ("we just fixed that")
- Questions about why decisions were made
- Finding artifacts from previous sessions
- Debugging something that was "already fixed"
- Resuming multi-session projects
Tools
| Tool | Purpose | Location |
|---|---|---|
| SecretScan.ts | TruffleHog wrapper for credential detection | CORE/Tools/SecretScan.ts |
| CreateUpdate.ts | Create new system update entries | Tools/CreateUpdate.ts |
| UpdateIndex.ts | Regenerate index.json and CHANGELOG.md | Tools/UpdateIndex.ts |
| UpdateSearch.ts | Search and query system updates | Tools/UpdateSearch.ts |
| ExtractArchitectureUpdates.ts | Historical migration tool (one-time use) | Tools/ExtractArchitectureUpdates.ts |
Templates
| Template | Purpose | Location |
|---|---|---|
| Update.md | Template for system update entries | Templates/Update.md |
Output Locations
| Output | Location |
|---|---|
| Integrity Reports | MEMORY/STATE/integrity/YYYY-MM-DD.md |
| System Updates | MEMORY/PAISYSTEMUPDATES/YYYY/MM/*.md |
| Update Index | MEMORY/PAISYSTEMUPDATES/index.json |
| Changelog | MEMORY/PAISYSTEMUPDATES/CHANGELOG.md |
Related Skills
- PAI - Public PAI repository management (includes PAIIntegrityCheck)
- CORE - System architecture and memory documentation
- Evals - Regression testing and capability verification
More from danielmiessler/personal_ai_infrastructure
osint
Structured OSINT investigations — people lookup, company intel, investment due diligence, entity/threat intel, domain recon, organization research using public sources with ethical authorization framework. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate, company lookup, domain lookup, entity lookup, organization lookup, threat intel, discover OSINT sources.
259firstprinciples
Physics-based reasoning framework (Musk/Elon methodology) that deconstructs problems to irreducible fundamental truths rather than reasoning by analogy. Three-step structure: DECONSTRUCT (break to constituent parts and actual values), CHALLENGE (classify every element as hard constraint / soft constraint / unvalidated assumption — only physics is truly immutable), RECONSTRUCT (build optimal solution from fundamentals alone, ignoring inherited form). Outputs: constituent-parts breakdown, constraint classification table, and reconstructed solution with key insight. Three workflows: Deconstruct.md, Challenge.md, Reconstruct.md. Integrates with RedTeam (attack assumptions before deploying adversarial agents), Security (decompose threat model), Architecture (challenge design constraints), and Pentesters (decompose assumed security boundaries). Other skills invoke via: Challenge on all stated constraints → classify as hard/soft/assumption. Cross-domain synthesis: solutions from unrelated fields often apply once the fundamental truths are exposed. NOT FOR incident investigation and causal chains (use RootCauseAnalysis). NOT FOR structural feedback loops (use SystemsThinking). USE WHEN first principles, fundamental truths, challenge assumptions, is this a real constraint, rebuild from scratch, what are we actually paying for, what is this really made of, start over, physics first, question everything, reasoning by analogy, is this really necessary.
160documents
Read, write, convert, and analyze documents — routes to PDF, DOCX, XLSX, PPTX sub-skills for creation, editing, extraction, and format conversion. USE WHEN document, process file, create document, convert format, extract text, PDF, DOCX, XLSX, PPTX, Word, Excel, spreadsheet, PowerPoint, presentation, slides, consulting report, large PDF, merge PDF, fill form, tracked changes, redlining.
114council
Multi-agent collaborative debate that produces visible round-by-round transcripts with genuine intellectual friction. All council members are custom-composed via ComposeAgent (Agents skill) with domain expertise, unique voice, and personality tailored to the specific topic — never built-in generic types. ComposeAgent invoked as: bun run ~/.claude/skills/Agents/Tools/ComposeAgent.ts. Two workflows: DEBATE (3 rounds, full transcript + synthesis, parallel execution within rounds, 40-90 seconds total) and QUICK (1 round, fast perspective check). Context files: CouncilMembers.md (agent composition instructions), RoundStructure.md (three-round structure and timing), OutputFormat.md (transcript format templates). Agents are designed per debate topic to create real disagreement; 4-6 well-composed agents outperform 12 generic ones. Council is collaborative-adversarial (debate to find best path); for pure adversarial attack on an idea, use RedTeam instead. NOT FOR parallel task execution across agents (use Delegation skill). USE WHEN council, debate, multiple perspectives, weigh options, deliberate, get different views, multi-agent discussion, what would experts say, is there consensus, pros and cons from multiple angles.
112privateinvestigator
Ethical people-finding using 15 parallel research agents (45 search threads) across public records, social media, reverse lookups. Public data only, no pretexting. USE WHEN find person, locate, reconnect, people search, skip trace, reverse lookup, social media search, public records search, verify identity.
112redteam
Military-grade adversarial analysis that deploys 32 parallel expert agents (engineers, architects, pentesters, interns) to stress-test ideas, strategies, and plans — not systems or infrastructure. Two workflows: ParallelAnalysis (5-phase: decompose into 24 atomic claims → 32-agent parallel attack → synthesis → steelman → counter-argument, each 8 points) and AdversarialValidation (competing proposals synthesized into best solution). Context files: Philosophy.md (core principles, success criteria, agent types), Integration.md (how to combine with FirstPrinciples, Council, and other skills; output format). Targets arguments, not network vulnerabilities. Findings ranked by severity; goal is to strengthen, not destroy — weaknesses delivered with remediation paths. Collaborates with FirstPrinciples (decompose assumptions before attacking) and Council (Council debates to find paths; RedTeam attacks whatever survives). Also invoked internally by Ideate (TEST phase) and WorldThreatModel (horizon stress-testing). NOT FOR AI instruction set auditing (use BitterPillEngineering). NOT FOR network/system vulnerability testing (use a security assessment skill). USE WHEN red team, attack idea, counterarguments, critique, stress test, devil's advocate, find weaknesses, break this, poke holes, what could go wrong, strongest objection, adversarial validation, battle of bots.
112