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

verify-sources

Skill397 starsChanged 12 days agoApache-2.0View on GitHub

Local Newsroom skill for triangulating incoming news tips against the memory graph and primary sources before drafting.

2 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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 this step-by-step recipe card whenever a new tip, press release, or claim arrives at the Newsroom desk:

    line 8
  2. Very specific:

    Look up the company, project, or source in memory/memory_graph.json.

    line 11
  3. Distinctive:

    Every number, benchmark, price, or quote needs at least one primary source (an official repo, peer-reviewed paper, public filing, or …

    line 15
  4. Very specific:

    Add newly discovered facts (with verified: true or verified: false) to the scratchpad array in memory/memory_graph.json so the Dreaming …

    line 19

≈ “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: Verify Sources (skills/verify-sources)

Use this step-by-step recipe card whenever a new tip, press release, or claim arrives at the Newsroom desk:

  1. Step 1 — Check the Memory Graph: Look up the company, project, or source in memory/memory_graph.json.
    • Is the source listed under verified_sources?
    • Is the source flagged under known_rumor_mills? (If so, reject any claim that relies on it alone.)
  2. Step 2 — Demand Primary Receipts: Every number, benchmark, price, or quote needs at least one primary source (an official repo, peer-reviewed paper, public filing, or reproducible lab test).
  3. Step 3 — Tag Every Fact: Attach [Source: <Name>] right after every factual or numeric sentence. Never leave [UNVERIFIED] or "sources say" in a finished draft.
  4. Step 4 — Log New Findings to the Scratchpad: Add newly discovered facts (with verified: true or verified: false) to the scratchpad array in memory/memory_graph.json so the Dreaming routine (memory/dream.py) can consolidate them after your story ships.

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