agentleFS
itsmuskanagarwalitsmuskanagarwal/effective-agents-lab/skills/legal-contract-review/SKILL.md

legal-contract-review

Skill0 starsChanged 4 months agoMITView on GitHub

Use when a contract or legal agreement needs to be reviewed for risk, unusual terms, or deviation from standard practice — e.g. "review this contract", "what are the risky clauses", or "how does this compare to our standard terms". Not a substitute for a lawyer; flags issues for human legal review.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill 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:

    Every substantive clause appears in the inventory with an effect description, not just a label.

    line 25
  2. Distinctive:

    Every unfavorable/unusual clause has a concrete downside scenario stated.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Legal contract review

Clause-by-clause risk flagging for contracts, built on document-analysis rather than re-parsing the contract independently. This skill does not give legal advice — it produces a structured risk inventory for a human lawyer to review.

Workflow

  1. Apply document-analysis first to get the contract's structure, parties, dates, and defined terms.
  2. Build a clause inventory. List every substantive clause (not boilerplate) with a one-line description of its effect: what it obligates, permits, or restricts, and who it binds.
  3. Compare against standard/expected terms (see references/standard-clause-checklist.md for this repo's synthetic example checklist). For each clause, note: standard, favorable-to-us, unfavorable-to-us, or unusual/non-standard.
  4. Flag risk explicitly, don't just describe. For each unfavorable or unusual clause, state the concrete downside scenario ("if X happens, we owe Y with no cap") rather than only describing the clause's language.
  5. Check for missing standard clauses. A standard protection that's absent (e.g. no limitation of liability, no termination-for-convenience) is itself a finding — call it out the same way you'd call out an unfavorable clause.
  6. Never render a legal conclusion. Output a risk inventory and questions for counsel, not "this contract is safe to sign."

Composition

Builds on document-analysis. Can hand its structured risk inventory to compliance-review when the contract also needs a policy/regulatory check, not just a commercial-risk one.

Quality bar

  • Every substantive clause appears in the inventory with an effect description, not just a label.
  • Every unfavorable/unusual clause has a concrete downside scenario stated.
  • Missing standard protections are flagged as findings, not omitted.
  • Output never states a legal conclusion or "safe to sign" — it defers that to human counsel.

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.