agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/cat-agent-skills/submissions/consumer-market-insight-synthesis/skills/provenance-check/SKILL.md

provenance-check

Skill95 starsChanged 6 days agoMITView on GitHub

Checks usage rights, geography and expiry for every retrieved study against the declared use - the explicit Govern step - with the deterministic provenance_check engine. Use on "can we use this externally", "is this stat cleared for the board deck", after trend-compare.

We split this skill into the rules it gives an agent

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

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After trend-compare, before any brief is drafted.

    line 11
  2. Very specific:

    Run scripts/provenance_check.py --compared compared.json --rights rights-register.json --out governed.json

    line 15
  3. Distinctive:

    Every entry cites the rights register row.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Provenance Check (Govern)

Purpose

The compliance determination IS the work: license scope x geography x expiry gates every citation for the DECLARED use (#4.1/#4.2). A restricted or expired study is unusable however strong the stat.

When to use

After trend-compare, before any brief is drafted.

Inputs

compared.json + config/rights-register.json.

Steps

  1. Run scripts/provenance_check.py --compared compared.json --rights rights-register.json --out governed.json
  2. Quote the record verbatim; excluded studies are named with their restriction so the reader knows what was left out and why.

Output

governed.json - the {provenance_record} hop.

Grounding requirements

Every entry cites the rights register row.

Constraints

  • The engine decides; the model never launders a restricted stat by paraphrase - a reworded number is still the licensed number.
  • Approving new rights is the licensing team's work, not this plugin's.

Escalation / uncertainty

Missing register rows -> unusable until registered; escalate to research ops.

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.

Check your setup, free