ropa
Skill1 starsChanged 41 days agoMITView on GitHub
Build or review a Record of Processing Activities (GDPR Art. 30). Use when the user wants to document processing activities, create a ROPA, or audit an existing one.
In this repository6 other files it gives its agents.
- breach-responseSkill
- cookie-tracker-auditSkill
- dpa-reviewSkill
- dpiaSkill
- dsar-responseSkill
- privacy-policy-reviewSkill
The file
Files
Record of Processing Activities
For each processing activity capture: name and purpose; controller/joint controller/DPO contact; categories of data subjects; categories of personal data (flag special-category data); lawful basis (Art. 6, plus Art. 9 condition if relevant); recipients and processors; third-country transfers and safeguards; retention period; security measures (Art. 32).
Output as a table (or CSV if asked). When reviewing an existing record, list gaps: missing lawful basis, undefined retention, processors without DPAs, transfers without a mechanism. Ask the user about anything you cannot infer rather than guessing.
Handling unknowns and sources
- Record the evidence source for each row (policy page, code, contract). Mark unknowns OPEN and collect them in an "Open questions" list at the end; in a non-interactive run, do not stop to ask.
- Include one row per distinct purpose, including consent/cookie-driven processing (ads, pixels, analytics), payments, and rights handling. Mark inferred rows "inferred".
- Finish with a "Gaps" list: processors without a DPA, transfers without a mechanism or TIA, missing lawful basis or retention, joint-controller questions (e.g. ad pixels), and anything that contradicts the privacy policy.
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
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.