agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/classify-data/SKILL.md

classify-data

Skill0 starsChanged 16 days agoMITView on GitHub

Classify data a change touches — PII, retention, residency — without inventing legal rules. Use when the user asks to classify data, mark PII, data handling, or /classify-data. Do not write product code.

The file

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:

    Do not invent retention periods, residency, or lawful basis.

    line 18
  2. Very specific:

    Read AGENTS.md if present.

    line 40
  3. Distinctive:

    Read the named spec. List fields / artifacts the change stores, sends, or logs.

    line 41

≈ “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

Classify data

Say what data this change touches and what you do not know. This is not write-nfr, not security-pass (that is a diff), and not legal advice.

Do not invent retention periods, residency, or lawful basis.

Is this the right skill?

SignalDo this instead
Threat model of a diffsecurity-pass
Event listspec-analytics
Schema expand/contractdata-change / plan-data-migration

Required inputs

  • The change: requirements, design, or contract path
  • context/ if it already states data rules

Human decisions (do not invent)

  • Retention, residency, lawful basis
  • Whether a field is allowed to be stored

Procedure

  1. Read AGENTS.md if present. Read context/ files that mention data or privacy.
  2. Read the named spec. List fields / artifacts the change stores, sends, or logs.
  3. Find the home: first existing docs/data/, or offer to create it. Name: docs/data/classify-<slug>.md.
  4. Open references/classify-template.md. Copy every heading. Write n/a when unused.
  5. Each item: name, flows where, PII yes/no/unknown, retention source or unknown, residency source or unknown.
  6. Secrets and credentials are never “unknown PII” — they are secrets; do not put values in the doc.
  7. Point legal questions at context/decision-rights.md. Do not answer them.

Output

  • Path: docs/data/classify-<slug>.md
  • Template: references/classify-template.md

Quality bar

  • Spec path is named
  • Every field has PII yes / no / unknown
  • Retention/residency are sourced or unknown
  • No legal rule invented
  • Unused headings are n/a

Done

  1. Path
  2. Field count + unknown count
  3. Next skill: security-pass on the implementation; human on unknowns

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