agentleFS
systemind-teamsystemind-team/AICOO-Skills/skills/autonomous-sync/SKILL.md

autonomous-sync

Skill35 starsChanged 4 months agoMITView on GitHub

Use this skill when the user wants to keep their Aicoo agent updated automatically, set up scheduled syncs, configure triggers for knowledge updates, use CRON jobs, /loop commands, file watchers, or hooks to push changes to Aicoo. Triggers on: 'auto sync', 'keep updated', 'schedule', 'CRON', 'loop', 'trigger', 'watch files', 'auto update', 'periodic sync', 'hook', 'autonomous'.

  • Reads credentials
  • Sends data out

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Use these endpoints in automation:

    line 16
  2. Very specific:

    Create new note: POST /api/v1/os/notes

    line 22
  3. Distinctive:

    After substantial chat sessions:

    line 67
  4. Very specific:

    If no matching note exists, call POST /os/notes.

    line 89
  5. Distinctive:

    Search first to avoid duplicates.

    line 101
  6. Distinctive:

    Prefer patching canonical notes over creating near-duplicates.

    line 103
  7. Distinctive:

    Use accumulate for larger batches.

    line 104

≈ “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

Autonomous Sync — Keep Your Agent Updated

Set up automatic triggers to keep Aicoo knowledge current.

Prerequisites

  • AICOO_API_KEY must be set
  • Base URL: https://www.aicoo.io/api/v1

Sync Contract (post-refactor)

Use these endpoints in automation:

  1. Search overlap: POST /api/v1/os/notes/search
  2. Deterministic grep (exact/regex + context): POST /api/v1/os/notes/grep
  3. Snapshot before edits: POST /api/v1/os/snapshots/{noteId}
  4. Edit existing note: PATCH /api/v1/os/notes/{noteId}
  5. Create new note: POST /api/v1/os/notes
  6. Reorganize with move/copy: POST /api/v1/os/notes/{id}/move, POST /api/v1/os/notes/{id}/copy
  7. Bulk updates: POST /api/v1/accumulate

Strategy 1: Rule-Based (/loop or cron)

Claude Code /loop

/loop 30m sync new decisions and project updates to Aicoo: search existing notes, snapshot before major edits, patch existing notes or create new ones.

Cron example

# daily at 9:00
0 9 * * * /path/to/aicoo-sync.sh >> /tmp/aicoo-sync.log 2>&1

Strategy 2: Event-Driven (hooks)

Claude hooks

Add to .claude/settings.json:

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "./aicoo-skills/scripts/sync-detector.sh"
          }
        ]
      }
    ]
  }
}

Strategy 3: Conversation-Driven

After substantial chat sessions:

# 1) search
curl -s -X POST "$PULSE_BASE/os/notes/search" \
  -H "Authorization: Bearer $AICOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"database migration strategy"}' | jq .

# 2) snapshot before overwrite
curl -s -X POST "$PULSE_BASE/os/snapshots/42" \
  -H "Authorization: Bearer $AICOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"label":"Pre-update"}' | jq .

# 3) patch
curl -s -X PATCH "$PULSE_BASE/os/notes/42" \
  -H "Authorization: Bearer $AICOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content":"# Updated content..."}' | jq .

If no matching note exists, call POST /os/notes.

What to Sync

  • decisions
  • preferences
  • project updates
  • meeting outcomes
  • policy/constraint changes

Safety Rules

  1. Search first to avoid duplicates.
  2. Snapshot before high-impact edits.
  3. Prefer patching canonical notes over creating near-duplicates.
  4. Use accumulate for larger batches.

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.