agentleFS
Sign inStart free
ric03uecric03uec/clawrium/skills/hermes/daily-digest/SKILL.md

daily-digest

Skill67 starsChanged 2 months agoApache-2.0View on GitHub

Post a daily engineer-tone summary of the last 24h of activity on ric03uec/clawrium to Discord.

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 1

    Distinctive

    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:

    If a single PR did the heavy lifting, say so explicitly — don't level the slope.

    line 72
  2. Very specific:

    Never @here or @everyone.

    line 79
  3. Very specific:

    If 0 PRs merged and 0 issues opened or closed, post a one-line "Quiet day on clawrium." entry — silence reads as "the bot is broken."

    line 80

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “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

daily-digest

Once per day, summarize what happened on ric03uec/clawrium in the last 24 hours and post it to the project's home Discord channel.

Inputs (last 24h, in ric03uec/clawrium)

  • Merged PRs — title, number, author, one-line summary you derive from the PR body.
  • Issues opened — title, number, current labels.
  • Issues closed — title, number, the closing PR if any.
  • Your own run logs from the previous day (memory keyed daily-digest:last-run). Use it to avoid repeating the same items.

Commands:

gh pr list --repo ric03uec/clawrium --state merged --search \
  "merged:>$(date -u -d '24 hours ago' +%Y-%m-%dT%H:%M:%SZ)" \
  --json number,title,author,body
gh issue list --repo ric03uec/clawrium --state open --search \
  "created:>$(date -u -d '24 hours ago' +%Y-%m-%dT%H:%M:%SZ)" \
  --json number,title,labels
gh issue list --repo ric03uec/clawrium --state closed --search \
  "closed:>$(date -u -d '24 hours ago' +%Y-%m-%dT%H:%M:%SZ)" \
  --json number,title,closedByPullRequestsReferences

Output

A single Discord message in the home channel, structured as:

**clawrium digest — <YYYY-MM-DD>**

**Shipped (N)**
- #<num> <title> — <one-line summary>

**Opened (N)**
- #<num> <title> — <labels>

**Closed (N)**
- #<num> <title> — closed by #<pr>

Quiet day: <only if nothing material happened>

Send via the hermes Discord channel adapter (the agent already has the home channel id bound). Do not open a thread; the message is the unit.

Voice

  • Engineer to engineer. No marketing copy ("exciting", "robust", "delights"), no hedging through verbosity.
  • Emoji only when it encodes information (✅ for a green CI run that unblocks a release; 🔒 for a security fix). Skip them for flair.
  • Past tense for shipped; present tense for state ("Open: 14").
  • If a single PR did the heavy lifting, say so explicitly — don't level the slope.

Hard constraints

  • One message per day. Idempotent — re-runs within the same day update rather than duplicate (track the last-message id in skill memory).
  • Never @here or @everyone.
  • If 0 PRs merged and 0 issues opened or closed, post a one-line "Quiet day on clawrium." entry — silence reads as "the bot is broken."

Anti-patterns

  • Paraphrasing each PR body into a paragraph. One line per PR.
  • Listing internal refactors that did not change user-visible behavior. Group them: "+ 4 internal cleanups (#a, #b, #c, #d)".
  • Restating yesterday's items. Use the run log to dedup.

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.

Check your setup, free