legal-risk-assessment
Skill21 starsChanged 4 months agoMITView on GitHub
Severity-by-likelihood legal risk register for a situation or deal — enumerates concrete risks, scores each one impact 1-5 × likelihood 1-5, renders a heat-map table, attaches mitigations to every risk at or above threshold, defines escalation criteria for immediate human counsel, and sets monitoring triggers. Use when the user says 'what's our exposure', 'how risky is this deal', 'assess the legal risk of this', or before committing to anything with real downside.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- insight68/Skillstheir own version, first seen Nov 8, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
- Tgoldi/claude-skillstheir own version, first seen Oct 13, 2026
- edu6565/claude-skillstheir own version, first seen Oct 11, 2026
- EvolutionAPI/evo-nexustheir own version, first seen Oct 8, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- anthropics/knowledge-work-plugins★ 36ksame name
- THUYRan/Legal-Skills-Chinese★ 974same name
- EvolutionAPI/evo-nexus★ 545same name
- evolution-foundation/evo-nexus★ 535same name
- insight68/Skills★ 5same name
- JustineDevs/premortem★ 2same name
- nisarth/claude-skills-store★ 1same name
- yiyan-yixing/skills★ 1same name
- edu6565/claude-skills★ 0same name
- Tgoldi/claude-skills★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository63 other files it gives its agents.
- account-intelligenceSkill
- account-researchSkill
- ad-creativeSkill
- agent-evaluationSkill
- agent-reliabilitySkill
- ai-adoption-leadSkill
- ai-data-stewardSkill
- ai-seoSkill
- ai-workflow-architectSkill
- appsec-reviewSkill
- audit-supportSkill
- brand-guidelinesSkill
- call-prepSkill
- cash-flow-snapshotSkill
- chief-of-staffSkill
- claude-memSkill
- close-managementSkill
- compliance-checkSkill
- context7Skill
- copywritingSkill
- croSkill
- cto-advisorSkill
- customer-researchSkill
- draft-outreachSkill
- financial-statementsSkill
- frontend-designSkill
- growth-engineeringSkill
- growth-experimentsSkill
- growth-strategySkill
- hook-generatorSkill
- invoice-chaseSkill
- journal-entrySkill
- lead-magnetsSkill
- lifecycle-growthSkill
- margin-analyzerSkill
- mcp-builderSkill
- objection-handlerSkill
- pipeline-reviewSkill
- plan-payrollSkill
- post-writerSkill
- profile-optimizerSkill
- proposal-builderSkill
- reconciliationSkill
- reels-scriptingSkill
- revenue-operationsSkill
- review-contractSkill
- run-campaignSkill
- signature-requestSkill
- skill-creatorSkill
- skill-vettingSkill
- superpowersSkill
- tasteSkill
- tax-prepSkill
- token-accountantSkill
- transitionsSkill
- triage-ndaSkill
- ui-ux-pro-maxSkill
- variance-analysisSkill
- vendor-checkSkill
- voice-builderSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
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
- Distinctive: line 17
Before an exec or board commit on a contested move
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Legal Risk Assessment — Risk Assessor
"Flag legal risk"
Turns "this feels risky" into a scored, sorted register with owners and tripwires. Works from a description of the situation plus any documents provided.
When to use
- "What's our exposure if we sign this?" — deal downside read
- "How risky is operating without a signed DPA for a quarter?"
- "Rank the legal risks of this expansion plan"
- Before an exec or board commit on a contested move
- Clause-level contract surgery belongs to
review-contract; this skill scores the whole situation
Workflow
- Frame the situation: the decision at stake, timeline, jurisdictions, counterparties, and what "bad" concretely looks like for the business.
- Enumerate risks across the standard surfaces — contractual, regulatory, IP, privacy and data, employment, litigation, reputational-with-legal-consequence. Each risk is a concrete event ("residuals clause lets the vendor reuse our roadmap"), never a category name ("IP risk").
- Score each risk: impact 1-5 (1 = nuisance cost … 5 = company-changing) × likelihood 1-5 (1 = remote … 5 = expected). Score = impact × likelihood, with a one-line rationale per score — unexplained numbers are guesses.
- Render the heat map sorted by score, descending.
- Attach a mitigation to every risk at or above threshold (default: score ≥ 8, overridable): the action, its owner, and the residual score once done.
- Define escalation criteria — observable conditions that send this to human counsel immediately (e.g., any impact-5 risk, regulator contact, a litigation threat received, press involvement).
- Set monitoring triggers: events that reopen the assessment ("counterparty misses a payment", "new guidance published on X"), each with a named watcher.
- Deliver the dated register and a one-sentence bottom line: proceed, proceed with mitigations, or do not proceed.
Output format
LEGAL RISK REGISTER — <matter> — <date>
Decision at stake: <one line> Mitigation threshold: score ≥ 8
HEAT MAP (sorted by score)
| # | Risk (concrete event) | Impact (1-5) | Likelihood (1-5) | Score | Rationale |
|---|-----------------------|--------------|------------------|-------|------------|
| 1 | <risk> | 4 | 4 | 16 | <one line> |
| 2 | <risk> | 5 | 2 | 10 | <one line> |
| 3 | <risk> | 2 | 3 | 6 | <one line> |
MITIGATIONS (score ≥ threshold)
| Risk # | Mitigation action | Owner | Residual score |
|--------|-------------------|-------|----------------|
| 1 | <action> | <who> | <I × L after> |
ESCALATE TO HUMAN COUNSEL IMMEDIATELY IF
- <observable condition>
- <observable condition>
MONITORING TRIGGERS
- <event> → reassess risk #<n> — watcher: <who>
BOTTOM LINE: <proceed / proceed with mitigations / do not proceed> — <one sentence why>
*Issue-spotting support, not legal advice — engage counsel for binding decisions.*Quality bar
- Every risk is a concrete event, not a category label
- Every score carries a one-line rationale — no bare numbers
- Every risk at or above threshold has a mitigation, an owner, and a residual score
- Escalation criteria are observable conditions, not judgment calls
- Register is dated and every monitoring trigger names a watcher
- Bottom line commits to one recommendation
Example
Invocation: "We're about to sign a 3-year exclusive distribution deal in a market we've never operated in. Exposure?"
Produces: A register of seven risks. Top score 16: exclusivity lock-in with no minimum-performance exit (impact 4 × likelihood 4), mitigated by a termination-for-underperformance clause (residual 8). Escalation fires if the counterparty demands a non-compete covering existing markets; monitoring trigger on quarterly sales versus floor, watched by the deal owner. Bottom line: proceed with mitigations.
Issue-spotting support, not legal advice — engage counsel for binding decisions.
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.

