agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/cat-agent-skills/submissions/audit-readiness/skills/evidence-gather/SKILL.md

evidence-gather

Skill95 starsChanged 6 days agoMITView on GitHub

Builds the evidence register for the mapped clauses from the uploaded QMS exports and document indexes. Use when the user says "gather the evidence", "what do we have on file", "build the evidence register", or after scope-map in a readiness run.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    After scope-map in every run.

    line 11
  2. Distinctive:

    Every item cites its document id / export row.

    line 21
  3. Distinctive:

    Never omit an item because it looks old.

    line 24

≈ “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

Evidence Gather

Purpose

Assemble the register the Govern engine validates: every candidate evidence item with type, date, area, person, and source identity.

When to use

After scope-map in every run.

Inputs

mapped.json; uploaded evidence indexes/exports (CSV/JSON/folder listings of minutes, audit reports, training records, calibration logs, NCR logs).

Steps

  1. For each required evidence type, list the items on file: type, date, area, person, doc id.
  2. Record dates exactly as documented - freshness is the engine's call, not this skill's.
  3. Write evidence.json.

Output

evidence.json - the register.

Grounding requirements

Every item cites its document id / export row.

Constraints

  • Gather only; no completeness or freshness judgments - "the folder looks full" is not a status.
  • Never omit an item because it looks old; the engine needs it to prove staleness.

Escalation / uncertainty

Evidence types with zero candidates are recorded as empty, not padded.

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