agentleFS
systemind-teamsystemind-team/AICOO-Skills/skills/inbox-monitoring/SKILL.md

inbox-monitoring

Skill35 starsChanged 4 months agoMITView on GitHub

Use this skill when the user wants to monitor Aicoo inbox activity, check new conversations/messages, track pending requests, or run periodic inbox checks. Triggers on: 'inbox monitoring', 'monitor inbox', 'new messages', 'pending requests', 'message watch', '收件箱监控', '/v1/conversations', '/v1/network/requests'.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Use /loop or /routine.

    line 59
  2. Distinctive:

    Use the provided script:

    line 75
  3. Very specific:

    If no new items, return a single line: No new inbox activity since last check.

    line 97

≈ “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

Inbox Monitoring

Monitor incoming communication in Aicoo and surface what needs action.

Prerequisites

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

Endpoints

  • GET /api/v1/conversations?view=all&limit=...
  • GET /api/v1/network/requests
  • GET /api/v1/os/network (optional context: links/visitors/contacts)

Core Workflow

Step 1: Pull conversation inbox

curl -s "https://www.aicoo.io/api/v1/conversations?view=all&limit=50" \
  -H "Authorization: Bearer $AICOO_API_KEY" | jq .

Views:

  • view=me for direct/human
  • view=coo for shared-agent conversations
  • view=all for combined monitor

Step 2: Pull pending requests

curl -s "https://www.aicoo.io/api/v1/network/requests" \
  -H "Authorization: Bearer $AICOO_API_KEY" | jq .

Step 3: Optional network context

curl -s "https://www.aicoo.io/api/v1/os/network" \
  -H "Authorization: Bearer $AICOO_API_KEY" | jq .

Step 4: Build action queue

Prioritize in this order:

  1. New inbound agent/human messages requiring response
  2. Incoming pending requests (type: agent first, then type: friend)
  3. High-signal visitor or share-link activity

Claude Code Automation

Use /loop or /routine.

/loop example

/loop 15m monitor my Aicoo inbox using /v1/conversations?view=all and /v1/network/requests; report only new items since last check and recommended replies.

/routine example

/routine inbox-monitor every 15 minutes: check /v1/conversations + /v1/network/requests and summarize urgent items only.

OpenClaw Automation (CRON)

Use the provided script:

# Every 15 minutes
*/15 * * * * /path/to/aicoo-skills/scripts/inbox-monitor-cron.sh >> /tmp/aicoo-inbox-monitor.log 2>&1

Optional envs:

  • PULSE_INBOX_VIEW (all | me | coo, default: all)
  • PULSE_INBOX_LIMIT (default: 50)
  • PULSE_INBOX_STATE_FILE (default: /tmp/pulse-inbox-monitor-state.json)

Output Contract

For each run, return:

  1. newMessages count
  2. newIncomingRequests count
  3. top urgent items (contact + timestamp + one-line summary)
  4. suggested next actions (reply / accept / ignore)

If no new items, return a single line: No new inbox activity since last check.

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.