agentleFS
stunt-doublestunt-double/stuntdouble-mcp/skills/check-compliance/SKILL.md

check-compliance

Skill1 starsChanged 33 days agoMITView on GitHub

Check a product against legal and compliance requirements (cookie consent, privacy and terms access, required disclosures, claim substantiation, unsubscribe flows) and collect evidence for counsel to review.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Scope: if no requirements were supplied, ask which regimes apply (e.g.

    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

Check compliance

This produces evidence for the team and their counsel, not legal advice. Report observations against the stated requirements (met, not met, unclear), never legal conclusions, and quote the page verbatim on anything ambiguous.

  1. Context: list_workspaces(), list_projects(workspace_id). Match the URL to a project, or let create_checklist find or create it.
  2. Scope: if no requirements were supplied, ask which regimes apply (e.g. GDPR cookie consent, AU Consumer Law pricing, financial disclaimers). Do not guess jurisdictions.
  3. Actor and rules: list_actors(workspace_id), else create_actor(...). Check list_workspace_guidelines(workspace_id) first (an obligation shared by several products is one rule attached with set_project_guideline), then add_project_guideline(project_id, category: "compliance", content, title), one obligation per guideline so a finding can name it.
  4. Checklist that exercises behaviour, not presence, e.g. "A cookie banner appears before non-essential tracking and the reject option works", "Privacy policy and terms are linked from every footer", "Prices include mandatory taxes or say they do not", "Required disclaimers sit next to the claims they qualify". Actors have their own inboxes, so email flows can include "Marketing emails contain a working unsubscribe link".
  5. Run: run_checklist(checklist_id), poll get_checklist_run(run_id) until terminal.
  6. Report per requirement with evidence, plus a list of items for counsel.
  7. Standing coverage: offer create_workflow (schedule for content edits, deploy trigger for releases; see setup-guardrails).

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.