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

clawdbot-monitor

Skill9 starsChanged 11 months agoMITView on GitHub

Monitor Clawdbot repo for updates and identify improvement opportunities for Geoffrey. Use when comparing Geoffrey to Clawdbot patterns, skills, or features.

The file

Show its rules and text

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    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 40
  2. Distinctive:

    memory: - Search patterns, embeddings, persistence

    line 44
  3. Distinctive:

    Check releases page for version info

    line 56
  4. Distinctive:

    Check for new skills since last analysis

    line 63
  5. Distinctive:

    Check recent commits for significant updates

    line 72
  6. Distinctive:

    Look for new patterns or breaking changes

    line 73
  7. Very specific:

    Read these Geoffrey files:

    line 81
  8. Distinctive:

    Create inventory of current skills and their purposes.

    line 91
  9. Distinctive:

    Search and retrieval approaches

    line 132
  10. Distinctive:

    Create a markdown report with this structure:

    line 142
  11. Distinctive:

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

    line 227
  12. Very specific:

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

    line 229
  13. Distinctive:

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

    line 230
  14. Distinctive:

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

    line 233

≈ “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

Clawdbot Monitor

Monitor the Clawdbot repository and identify opportunities to improve Geoffrey.

Clawdbot vs Geoffrey Quick Comparison

AspectClawdbotGeoffrey
ScopeMulti-channel messaging hub (WhatsApp, Discord, etc.)Claude Code plugin for personal AI
Skills60+ (CLI wrappers, platform integrations)26 (specialized workflows)
HooksEvent-driven TypeScript handlershooks.json configuration
MemoryHybrid vector + BM25 with SQLite-vecObsidian vault + knowledge-manager
ReleasesWeekly (v2026.x.x latest)Versioned plugin (v0.x.x)

Focus Areas

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

  • skills - Skill formats, metadata, categories, CLI patterns
  • hooks - Event types, handler patterns, automation
  • extensions - Plugin architecture, provider isolation
  • memory - Search patterns, embeddings, persistence

Without an argument, perform full analysis across all areas.


Phase 1: Fetch Clawdbot Current State

1.1 Core Documentation

Fetch these from github.com/clawdbot/clawdbot:

  • README.md - Overall structure and philosophy
  • CLAUDE.md - System instructions (if exists)
  • Check releases page for version info

1.2 Skill Structure

Explore the skills directory:

  • List all available skills
  • Sample key skills that overlap with Geoffrey's domains
  • Note skill metadata patterns (requires.bins, requires.config, install methods)
  • Check for new skills since last analysis

1.3 Hook System

Examine hook architecture:

  • Event types (session, command, boot)
  • Handler patterns (TypeScript)
  • Compare to Geoffrey's hooks.json approach

1.4 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 (hooks.json)
  • Knowledge storage approach (Obsidian vault)
  • Skill structure conventions (SKILL.md frontmatter)
  • Validation patterns

Phase 3: Gap Analysis

Compare Geoffrey against Clawdbot across these dimensions:

3.1 Skill Coverage

  • What Clawdbot skills do we lack equivalent skills for?
  • Which skills would provide highest value for Geoffrey's use case?
  • Are there redundant or outdated skills?

3.2 Skill Metadata System

  • requires.bins - CLI dependency declarations
  • requires.config - Configuration requirements
  • Install methods - How skills auto-install dependencies
  • Compare to Geoffrey's current skill structure

3.3 Hook System

  • Clawdbot: Event-driven TypeScript handlers
  • Geoffrey: hooks.json configuration
  • What event types are missing?
  • What patterns could we adopt?

3.4 Extension Architecture

  • Plugin isolation patterns
  • Multi-provider support (LLM providers, messaging channels)
  • How Clawdbot handles modularity

3.5 Memory System

  • Clawdbot: Hybrid vector + BM25 with SQLite-vec
  • Geoffrey: Obsidian vault + knowledge-manager
  • Embedding integration patterns
  • Search and retrieval approaches

3.6 New Features

  • Recent Clawdbot additions worth adopting
  • Experimental features to watch

Phase 4: Generate Report

Create a markdown report with this structure:

# Clawdbot Monitor Report

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

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

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

## Features/Patterns to Adopt
| Priority | Feature | Purpose | Complexity | Notes |
|----------|---------|---------|------------|-------|
| High | ... | ... | ... | ... |
| Medium | ... | ... | ... | ... |
| Low | ... | ... | ... | ... |

## Pattern Improvements

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

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

## Skill Coverage Comparison
| Domain | Clawdbot Skill | Geoffrey Equivalent | Gap |
|--------|---------------|--------------------| ----|
| ... | ... | ... | ... |

## 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 Clawdbot Areas to Monitor

Based on repo structure, these are the primary areas:

AreaDescriptionGeoffrey Equivalent
skills/60+ modular skillsskills/ (26)
HooksEvent-driven TypeScripthooks.json
ExtensionsPlugin architecture(none currently)
MemoryHybrid vector + BM25Obsidian vault
ChannelsWhatsApp, Discord, etc.N/A (Claude Code only)

Key Differences from PAI Monitor

AspectPAIClawdbot
Update frequencyLess frequentWeekly releases
ArchitecturePacks + CLIDaemon + extensions
Skill count24 packs60+ skills
Memory modelFile-basedVector DB (SQLite-vec)
TargetPersonal AIMessaging hub

Execution Notes

  1. Start with Phase 1 - Always fetch fresh Clawdbot 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 for Geoffrey's use case
  4. Actionable Phase 4 - Every recommendation should have clear next steps
  5. Note Architecture Differences - Clawdbot is a daemon, Geoffrey is a plugin; some patterns won't translate

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.