agentleFS
chipoto69chipoto69/claude-skills/obsidian-bridge/SKILL.md

obsidian-bridge

Skill2 starsChanged 10 months agoMITView on GitHub

Orchestrates the knowledge capture pipeline: harvester → analyzer → forge → obsidian. Manages automatic triggers via hooks and coordinates skill chaining.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After 30 minutes of no activity, accumulated data is flushed.

    line 74
  2. Distinctive:

    If ATLAS knowledge base is detected, the bridge:

    line 123
  3. Distinctive:

    Run the full chain:

    line 164

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Obsidian Bridge

Master orchestrator for the knowledge capture and documentation pipeline.

Pipeline Overview

┌──────────────────────────────────────────────────────────────────────────────┐
│                         KNOWLEDGE PIPELINE                                    │
└──────────────────────────────────────────────────────────────────────────────┘

  TRIGGERS              CAPTURE              TRANSFORM             OUTPUT
  ────────              ───────              ─────────             ──────
                        
  ┌─────────┐       ┌─────────────┐      ┌───────────────┐     ┌──────────────┐
  │Git Commit│──────▶│   DevLog    │─────▶│   Knowledge   │────▶│   Obsidian   │
  └─────────┘       │  Harvester  │      │     Forge     │     │    Notes     │
                    └─────────────┘      └───────────────┘     └──────────────┘
  ┌─────────┐              │                    │                     │
  │ Project │──────────────┤                    │                     │
  │ Switch  │              ▼                    │                     ▼
  └─────────┘       ┌─────────────┐             │              ┌──────────────┐
                    │   Project   │─────────────┘              │   Portfolio  │
  ┌─────────┐       │  Analyzer   │                            │     HTML     │
  │ 3x Daily│───────▶─────────────┘                            └──────────────┘
  │ Rollup  │              │
  └─────────┘              ▼
                    ┌─────────────┐
  ┌─────────┐       │    AGI      │
  │  Idle   │───────▶│   Memory   │
  │ 30 min  │       │  Integration│
  └─────────┘       └─────────────┘

Automatic Triggers

1. Git Commit Hook

Install with:

python ~/.claude/skills/obsidian-bridge/scripts/install-hooks.py

This adds a post-commit hook to all tracked repos that:

  • Captures commit context
  • Stages data for next rollup

2. Time-Based Rollups

Add to crontab:

# 3x daily rollups at 9am, 2pm, 9pm
0 9,14,21 * * * ~/.claude/skills/obsidian-bridge/scripts/scheduled-rollup.sh

3. Project Switch Detection

The harvester monitors PWD changes and flushes data when switching projects.

4. Idle Flush

After 30 minutes of no activity, accumulated data is flushed.

Usage

Manual Full Pipeline

# Run complete pipeline for current project
/sync

# Run for specific project
/sync --project ATLAS-main

# Dry run (preview only)
/sync --dry-run

Individual Steps

# Just harvest
python ~/.claude/skills/devlog-harvester/scripts/harvest.py

# Just synthesize
python ~/.claude/skills/knowledge-forge/scripts/synthesize.py --all

# Just generate portfolio
python ~/.claude/skills/portfolio-forge/scripts/generate.py

Integration with AGI-Memory

The bridge syncs with AGI-memory MCP:

# On harvest, also store to AGI-memory
mcp_memory_remember(
    content=f"Session on {project}: {commits} commits, {summary}",
    type="episodic",
    importance=0.7,
    concepts=["project:{project}", "devlog"]
)

This enables:

  • Cross-session recall ("What did I work on last week?")
  • Project context retrieval
  • Pattern recognition across sessions

Integration with ATLAS

If ATLAS knowledge base is detected, the bridge:

  1. Exports session notes in ATLAS-compatible format
  2. Syncs to ATLAS mind.mv2 via memvid
  3. Enables ATLAS agents to access development context

Configuration

~/.config/devlog/config.yaml:

pipeline:
  # Enable automatic triggers
  auto_commit_harvest: true
  auto_rollup: true
  rollup_times: ["09:00", "14:00", "21:00"]
  
  # Idle detection
  idle_threshold_minutes: 30
  
  # AGI-memory integration
  sync_to_agi_memory: true
  
  # ATLAS integration
  atlas_integration: true
  atlas_mind_path: ~/.claude/mind.mv2
  
  # Portfolio generation
  auto_portfolio: daily  # or: on_sync, manual
  portfolio_output: ~/Documents/Vaultage/06_Metadata/Portfolio
  
  # Projects to track (empty = all)
  tracked_projects: []
  
  # Projects to ignore
  ignored_projects:
    - node_modules
    - .git
    - __pycache__

Skill Chain Commands

Run the full chain:

/chain harvest → analyze → forge → portfolio

Or use the shorthand:

/sync --full

Files

  • scripts/run-pipeline.py - Main orchestrator
  • scripts/install-hooks.py - Git hook installer
  • scripts/scheduled-rollup.sh - Cron script
  • scripts/agi-memory-sync.py - AGI-memory integration

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.