agentleFS
Sign inStart free
Fadi88Fadi88/one-man-startup/.cursor/rules/skill-legal-review.mdc

one-man-startup / rules

Cursor rule16 starsChanged 2 days agoMITView on GitHub

The legal agent's method - read the founder's playbook and the region packs, grade each checklist item GREEN, YELLOW, RED or UNSETTLED with a cited and dated source, draft documents flagged for counsel, escalate. Use at setup, before launches, and on features touching personal data, payments, children, AI output or marketing claims.

We split this skill-legal-review.mdc into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not legal advice: Every output says so first, and lists what a lawyer should review.

    line 10
  2. Distinctive:

    Every grade cites a primary source where one exists (the law, the regulator's guidance) and the date it was checked.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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-legal-review.mdc
---
description: "The legal agent's method - read the founder's playbook and the region packs, grade each checklist item GREEN, YELLOW, RED or UNSETTLED with a cited and dated source, draft documents flagged for counsel, escalate. Use at setup, before launches, and on features touching personal data, payments, children, AI output or marketing claims."
alwaysApply: false
---

<!-- Generated by tools/sync_adapters.py from skills/legal-review/SKILL.md. Edit the source, not this file. -->

# Legal review

**Not legal advice.** Every output says so first, and lists what a lawyer should review.

## Read

- `project.toml`: regions, domain, audience, customer size, sensitive, and `origin`: a
  rebuild of an existing app adds the playbook's "Rebuilding an existing app" row to every
  launch review.
- `docs/legal/playbook.md`: the founder's positions (what we accept, what we escalate).
- `docs/legal/regions/<CODE>.md` for each region. A region with no pack is itself a RED.
- The feature's spec, design and UX files.

## Grade

For every applicable item in each pack's checklist:

| Item | Grade | Evidence in the product | Source | Checked |
|---|---|---|---|---|

- **GREEN** met; **YELLOW** met with a gap or an assumption, stated; **RED** not met, blocks
  launch; **UNSETTLED** the law's status is unclear or sources disagree, with both sources.
- Every grade cites a primary source where one exists (the law, the regulator's guidance) and
  the date it was checked. Law changes; an undated claim is worthless in six months.
- Packs older than 90 days are re-checked before a launch, and `python tools/link_check.py
  docs/legal/regions/*.md` shows no DEAD links.
- Each claim in a pack carries a short quote from the source it cites, so a reviewer can check
  it without trusting the agent that wrote it.

## Draft

Policies and notices go to `docs/legal/drafts/` with `DRAFT, NOT LEGAL ADVICE, REVIEW WITH
COUNSEL` as the first line: privacy policy, terms, cookie notice, AI disclosure, refund policy,
DPA for business customers. Write for the product as it is, from the spec and design, never
copied from another company.

## Escalate

Any RED, any UNSETTLED on the launch path, sensitive data categories, automated decisions about
people, cross-border transfers, enterprise contracts, regulator contact: to the founder, with a
recommendation to involve counsel and the exact questions to ask them.

Report in `docs/work/<id>/legal.md` (feature) or `docs/legal/launch-<date>.md` (launch).

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