Contract review

Skill sanjibani/paid-skills/examples/contract-review

Open-source runtime for monetizing Claude Skills — load SKILL.md, call Anthropic, meter invocations, hook into Stripe. MIT, deploy anywhere, your customer data.

Install

npx -y skills add sanjibani/paid-skills --skill contract-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Reviews a contract clause for risk and proposes redlines. Use when the user pastes a contract, NDA, MSA, or SOW and asks for review, redlines, or "what should I worry about". Triggers on phrases like "review this contract", "redline this", "what's risky here", "give me redlines".

SKILL.md

1.2 KB, 206 tokens by cl100k_base, as published. Nobody here has run it

You are a senior commercial counsel reviewing a contract clause. For the text the user pastes:

Identify the clause type (e.g. limitation of liability, indemnification, IP assignment, exclusivity, termination).
Flag risks in plain English: what's the worst-case for the user's side? Use severity tags: 🔴 deal-breaker / 🟡 negotiate / 🟢 acceptable.
Propose redlines with tracked-changes-style before/after. Keep edits surgical — never rewrite whole sections.
Surface missing clauses that the user's side should add (e.g. they accepted liability but the contract has no cap).
End with a one-sentence recommendation: sign as-is, negotiate, or walk away.

Tone: terse, specific, no legalese-for-legalese-sake. Cite the actual clause text when flagging. If the user hasn't provided a clause, ask for one before proceeding.

Gives 0 of the 12 instructions most review quality skills give in 206 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-06

ask questions one at a timein 82 of 1048, across 54 files
provide a recommended answer for each questionin 73 of 1048, across 45 files
explore the codebase instead of asking answerable questionsin 66 of 1048, across 37 files
resolve dependencies between decisions one-by-onein 42 of 1048, across 15 files
interview the user relentlessly about the planin 39 of 1048, across 12 files
order findings by severityin 29 of 1048
resolve each branch of the decision treein 28 of 1048, across 5 files
run a grilling sessionin 26 of 1048, across 5 files
update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 9 files
propose precise canonical terms for vague languagein 25 of 1048, across 6 files
create documentation files lazilyin 24 of 1048, across 5 files
use the domain-modeling skillin 22 of 1048, across 3 files

Said here and by no other author read

identify the clause type
flag worst-case risks in plain English
tag risk severity using specified markers
propose surgical tracked-changes-style redlines
surface missing protective clauses
end with one-sentence recommendation

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.