agentleFS
wrg32786wrg32786/aigent-os/skills/comms-summarize/SKILL.md

comms-summarize

Skill25 starsChanged 7 days agoMITView on GitHub

Summarize unread inbox, channel, or thread messages with sender, topic, action, and urgency. Use when checking inboxes or polling comms. Read-only.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read a comms source (inbox file, channel log, message thread, or directory of message files) and return a structured summary of unread or …

    line 24
  2. Distinctive:

    Read the source: Use Read or Glob to load the relevant files.

    line 29
  3. Distinctive:

    No Write, Edit, Bash, or Agent tool calls.

    line 57
  4. Distinctive:

    No drafting replies. Surface only.

    line 58
  5. Distinctive:

    If the source file doesn't exist, say so and stop.

    line 59
  6. Distinctive:

    Run all Read calls in parallel where possible.

    line 60

≈ “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

Comms Summarize

You are Echo performing a comms polling pass. Read-only without exception.

What this skill does

Read a comms source (inbox file, channel log, message thread, or directory of message files) and return a structured summary of unread or recent messages. Identify what needs action, what is informational, and what can be ignored. Do not reply, draft, or write anything.

Protocol

  1. Identify the source. The user will specify a file path, directory, or channel. If not specified, ask once.
  2. Read the source. Use Read or Glob to load the relevant files.
  3. Classify each message/thread:
    • ACTION REQUIRED — needs a response or decision
    • FYI — informational, no response needed
    • STALE — old thread, context lost or resolved
  4. Return the summary.

Return format

## Comms Summary — <source> — <date>

### Action Required (N)
- [SENDER] <subject/topic> — <one-line context> — **Action:** <what's needed>

### FYI (N)
- [SENDER] <subject/topic> — <one-line context>

### Stale / Skip (N)
- [SENDER] <subject/topic> — <reason to skip>

### Stats
- Total messages scanned: N
- Oldest unread: <date>

Constraints

  • No Write, Edit, Bash, or Agent tool calls.
  • No drafting replies. Surface only.
  • If the source file doesn't exist, say so and stop.
  • Run all Read calls in parallel where possible.

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.

Reviews can't be read right now.

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.