agentleFS
TheVellerTheVeller/claude-skills/skills/obsidian-vault/autocommit/SKILL.md

autocommit

Skill4 starsChanged 14 days agoMITView on GitHub

Operate the local auto-commit daemon for this vault. Use when the user wants to start, stop, restart, inspect, debug, or verify the auto-commit system, or asks about background git automation in this workspace.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use this skill for normal manual git workflows.

    line 25
  2. Distinctive:

    Run from repo root:

    line 29
  3. Very specific:

    After starting, verify again with status.

    line 65
  4. Distinctive:

    if not healthy, the most likely reason

    line 100
  5. Distinctive:

    Do not restart blindly if the user is in the middle of sensitive git operations.

    line 104
  6. Distinctive:

    Do not hide when the daemon is flaky.

    line 105
  7. Distinctive:

    Treat nested repos and unrelated git states carefully.

    line 106

≈ “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

Autocommit

Manage the vault's local auto-commit system safely and consistently.

This skill is for the modular daemon behind:

  • .scripts/auto-commit-control.sh
  • .scripts/auto-commit.sh
  • .scripts/auto-commit/

Use This Skill For

  • starting the auto-commit monitor
  • stopping it
  • restarting it
  • checking status
  • reading recent logs
  • understanding why it is not committing or not staying alive

Do not use this skill for normal manual git workflows. This is specifically for the background daemon.

Core Commands

Run from repo root:

bash .scripts/auto-commit-control.sh start
bash .scripts/auto-commit-control.sh stop
bash .scripts/auto-commit-control.sh status
bash .scripts/auto-commit-control.sh logs
bash .scripts/auto-commit-control.sh restart

Standard Workflow

1. Check Status First

Always start with:

bash .scripts/auto-commit-control.sh status

If running, report:

  • running/not running
  • whether the user actually wants a change

2. If Starting

Before starting, verify:

  • fswatch exists
  • there is no obvious git operation in progress

Then run:

bash .scripts/auto-commit-control.sh start

After starting, verify again with status.

3. If It Fails

Check:

tail -n 80 .scripts/.auto-commit.log

Then inspect:

  • .scripts/auto-commit-control.sh
  • .scripts/auto-commit.sh
  • .scripts/auto-commit/core/monitor.sh
  • .scripts/auto-commit/integrations/obsidian-detector.sh

Key failure patterns:

  • fswatch missing
  • process starts but dies immediately
  • Obsidian Git conflict heuristics skipping too aggressively
  • commit generation failing
  • push failing while commit succeeds

4. If Reviewing Behavior

Useful references:

  • 06_Metadata/Tools/Misc/Auto-Commit-System.md
  • .scripts/auto-commit/README.md

Reporting Back

When done, report:

  • current daemon state
  • what command was run
  • whether it is now healthy
  • if not healthy, the most likely reason

Safety

  • Do not restart blindly if the user is in the middle of sensitive git operations.
  • Do not hide when the daemon is flaky; say whether it truly stayed running.
  • Treat nested repos and unrelated git states carefully.

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.