agentleFS
Sign inStart free
Google CloudKnown publisherGoogleCloudPlatform/devrel-demos/agents/newsroom-harness/skills/write-bulletin/SKILL.md

write-bulletin

Skill397 starsChanged 12 days agoApache-2.0View on GitHub

Local Newsroom skill for structuring a 4-part breaking news bulletin that passes Truth, Safety, and Reading grades on the first try.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow this 4-beat recipe card whenever you draft a Newsroom story:

    line 8
  2. Very specific:

    Start with a sharp # Headline and a 1-sentence lead that states exactly what happened today.

    line 11

≈ “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

Local Skill: Write Breaking Bulletin (skills/write-bulletin)

Follow this 4-beat recipe card whenever you draft a Newsroom story:

  1. Beat 1 — The Headline & 1-Sentence Lead (Under 20 words): Start with a sharp # Headline and a 1-sentence lead that states exactly what happened today.
  2. Beat 2 — The Hard Receipts (With [Source: ...] Tags): In 2–3 short paragraphs, share the concrete numbers (cost, speed, date, or headcount) and tag each claim with [Source: <Verified Source>].
  3. Beat 3 — The 5th-Grade Breakdown: Explain how it works and why regular builders should care using a simple physical metaphor (no unexplained jargon, no paragraphs over 75 words).
  4. Beat 4 — What Happens Next: End with 1–2 crisp sentences on what to watch next, then run ./tools/newsroom grade <draft.md> to verify all three grades pass (100/100).

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