agentleFS
Sign inStart free
BhenderlongBhenderlong/vallorix-mcp-plugin/skills/evidence-check/SKILL.md

evidence-check

Skill0 starsChanged 19 days agoMITView on GitHub

Surface evidence that is missing, manual, or expiring across the organization's measures — so nothing lapses before an audit

6 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

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Pull measures + their evidence: Call listMeasures (focus on IMPLEMENTED ones — those are the controls currently claimed as met), then …

    line 9

“Common” is measured: kept by at least 6 in 10 of the 5 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

Audit the evidence backing the organization's controls and flag what needs attention, from the user's own Vallorix instance.

Steps

  1. Pull measures + their evidence. Call listMeasures (focus on IMPLEMENTED ones — those are the controls currently claimed as met), then listMeasureEvidences for each to get the attached evidence with its automation state (FULLY / PARTIALLY / AUTOMATION_READY / MANUAL) and expiry/validity dates.
  2. Bucket the evidence:
    • Expiring / expired — validity date passed or within 30 days. Highest priority: an implemented control with expired evidence will fail the audit.
    • Manual, not yet automated — MANUAL where an AUTOMATION_READY path exists: a candidate to connect a collector and stop doing it by hand.
    • Missing — an IMPLEMENTED measure with no evidence attached. That's a claim with no proof.
  3. Present a scannable report:
    • Headline counts: "7 pieces of evidence expiring in 30 days · 12 still manual · 2 implemented controls with no evidence."
    • A table per bucket: measure, evidence, state, expiry, framework(s) it supports.
  4. Recommend actions: refresh the expiring items first; for AUTOMATION_READY manual evidence, suggest connecting the relevant collector in Vallorix so it stays fresh automatically; for missing evidence, point to the measure that needs it.
  5. End with the next step: "Want me to draft what to collect for the 2 unproven controls, or focus on the expiring batch first?"

Edge cases

  • All evidence fresh and automated: "All implemented controls have current evidence; nothing expiring in 30 days. Clean."
  • Large volume: group by framework and summarize; show the top at-risk items with "[N] more — filter by framework?"
  • No implemented measures yet: point the user to /vallorix:framework-readiness to see what to implement first.

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