agentleFS
krishagelkrishagel/geoffrey/skills/pai-monitor/SKILL.md

pai-monitor

Skill9 starsChanged 11 months agoMITView on GitHub

Monitor Personal AI Infrastructure repo for updates and identify improvement opportunities for Geoffrey. Use when you want to sync Geoffrey with PAI's latest patterns, packs, or architectural decisions.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When invoked with an argument, focus analysis on that area:

    line 31
  2. Distinctive:

    Check releases for version info

    line 47
  3. Distinctive:

    Check recent commits for significant updates

    line 56
  4. Distinctive:

    Look for new patterns or breaking changes

    line 57
  5. Very specific:

    Read these Geoffrey files:

    line 65
  6. Distinctive:

    Create inventory of current skills and their purposes.

    line 75
  7. Very specific:

    Check Geoffrey's adherence to PAI founding principles:

    line 105
  8. Distinctive:

    Create a markdown report with this structure:

    line 120
  9. Distinctive:

    Start with Phase 1: - Always fetch fresh PAI data, don't rely on cached knowledge

    line 196
  10. Distinctive:

    Prioritize in Phase 3: - Not all gaps need filling.

    line 198
  11. Distinctive:

    Actionable Phase 4: - Every recommendation should have clear next steps

    line 199
  12. Distinctive:

    When focusing on a specific area, still provide brief context from other phases but concentrate analysis on the requested focus.

    line 201

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

PAI Monitor

Monitor the Personal AI Infrastructure repository and identify opportunities to improve Geoffrey.

Focus Areas

When invoked with an argument, focus analysis on that area:

  • packs - Deep dive on PAI pack additions/changes
  • hooks - Hook system evolution and patterns
  • skills - Skill structure and patterns
  • patterns - Architectural patterns (memory, validation, etc.)

Without an argument, perform full analysis across all areas.


Phase 1: Fetch PAI Current State

1.1 Core Documentation

Fetch these from github.com/danielmiessler/Personal_AI_Infrastructure:

  • README.md - Overall structure and philosophy
  • CLAUDE.md - System instructions and principles
  • Check releases for version info

1.2 Pack Structure

Explore the Packs/ directory:

  • List all available packs
  • Sample key packs: hooks, algorithm, memory, skills
  • Note any new packs since last analysis

1.3 Recent Changes

  • Check recent commits for significant updates
  • Look for new patterns or breaking changes
  • Note any announcements or migration guides

Phase 2: Analyze Geoffrey Current State

2.1 Core Architecture

Read these Geoffrey files:

  • CLAUDE.md - Founding principles and guidelines
  • README.md - Current capabilities
  • .claude-plugin/plugin.json - Version info

2.2 Skills Inventory

# Glob for all skills
skills/*/SKILL.md

Create inventory of current skills and their purposes.

2.3 Pattern Identification

Identify Geoffrey's current patterns:

  • Hook system usage
  • Knowledge storage approach
  • Skill structure conventions
  • Validation patterns

Phase 3: Gap Analysis

Compare Geoffrey against PAI across these dimensions:

3.1 Pack/Skill Coverage

  • What PAI packs do we lack equivalent skills for?
  • Which packs would provide highest value?
  • Are there redundant or outdated skills?

3.2 Architectural Patterns

  • Hook system: How does PAI's compare to our hooks.json?
  • Memory system: Knowledge persistence patterns
  • Validation: Secret prevention, protected files

3.3 Documentation Patterns

  • Does PAI use VERIFY.md, INSTALL.md, or other conventions?
  • Are there documentation patterns we should adopt?

3.4 Principles Alignment

Check Geoffrey's adherence to PAI founding principles:

  • Scaffolding > Model
  • Code Before Prompts
  • Deterministic Output
  • Goal → Code → CLI → Prompts
  • Test First

3.5 New Features

  • Recent PAI additions worth adopting
  • Experimental features to watch

Phase 4: Generate Report

Create a markdown report with this structure:

# PAI Monitor Report

**Geoffrey Version:** [from plugin.json]
**PAI Version Analyzed:** [from releases or README]
**Analysis Date:** [today's date]

## Executive Summary
[2-3 sentence summary of key findings]

## PAI Recent Changes
| Date | Change | Relevance to Geoffrey |
|------|--------|----------------------|
| ... | ... | ... |

## Packs/Features We Could Adopt
| Priority | Pack/Feature | Purpose | Complexity | Notes |
|----------|-------------|---------|------------|-------|
| High | ... | ... | ... | ... |
| Medium | ... | ... | ... | ... |
| Low | ... | ... | ... | ... |

## Pattern Improvements

### 1. [Pattern Name]
- **PAI Implementation:** [how they do it]
- **Geoffrey Current:** [how we do it / missing]
- **Adoption Benefit:** [why adopt]
- **Files to Modify:** [list]

### 2. [Pattern Name]
...

## Principles Alignment Check
| PAI Principle | Geoffrey Status | Gap |
|--------------|-----------------|-----|
| Scaffolding > Model | [status] | [gap if any] |
| Code Before Prompts | [status] | [gap if any] |
| ... | ... | ... |

## Recommended Actions

### Immediate (This Week)
- [ ] Action 1
- [ ] Action 2

### Short-Term (This Month)
- [ ] Action 1
- [ ] Action 2

### Long-Term (Explore)
- [ ] Action 1
- [ ] Action 2

Key PAI Areas to Monitor

Based on repo structure, these are the primary areas:

AreaDescriptionGeoffrey Equivalent
Packs/24+ modular capability packagesskills/
Releases/Full system snapshotsplugin versions
Hook System14+ event typeshooks.json
Memory SystemKnowledge persistenceObsidian vault
Algorithm SystemISC tracking, metricscompound learnings
Validation.pai-protected.json(none currently)

Execution Notes

  1. Start with Phase 1 - Always fetch fresh PAI data, don't rely on cached knowledge
  2. Be thorough in Phase 2 - Accurate self-assessment is critical for gap analysis
  3. Prioritize in Phase 3 - Not all gaps need filling; focus on high-value opportunities
  4. Actionable Phase 4 - Every recommendation should have clear next steps

When focusing on a specific area, still provide brief context from other phases but concentrate analysis on the requested focus.

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.