lawvable/legal-risk-assessment-zacharie-laik
skills/legal-risk-assessment-zacharie-laik/SKILL.md
Conduct legal research and risk analysis using GoodLegal MCP tools. Use this skill whenever the user asks a legal question, wants to research case law or legislation, needs a legal risk assessment, or asks about French or EU law. Trigger on any mention of jurisprudence, legal research, contract risk, regulatory analysis, legal memo, or references to GoodLegal tools — even if the user just says something like "can you look into whether this clause is enforceable" or "what does the case law say about X".
$ install --global
skillsauthnpx skillsauth add lawvable/awesome-legal-skills legal-risk-assessment-zacharie-laikInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
70%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 21, 2026, 4:56 PM211.9s1 file scanned
SKILL.md
- name:
- legal-risk-assessment-zacharie-laik
- description:
- Conduct legal research and risk analysis using GoodLegal MCP tools. Use this skill whenever the user asks a legal question, wants to research case law or legislation, needs a legal risk assessment, or asks about French or EU law. Trigger on any mention of jurisprudence, legal research, contract risk, regulatory analysis, legal memo, or references to GoodLegal tools — even if the user just says something like "can you look into whether this clause is enforceable" or "what does the case law say about X".
- author:
- Zacharie Laïk
- license:
- AGPL-3.0
- version:
- 2026.02.25
Legal Risk Analysis
Assist an in-house legal team with legal research, risk evaluation, and analysis using GoodLegal's research tools. Do not provide legal advice — flag that analyses must be reviewed by qualified legal professionals.
Output Format
Adapt the output to whatever structure best serves the question — memo, bullet-point summary, narrative analysis, comparison table, or any combination. Two hard requirements:
- Inline citations: every legal claim must link to its source (see references/citations.md)
- Sources section: a consolidated list of all authorities at the end
Research Methodology
Follow these three steps before concluding on any legal question.
Step 1: Adversarial search for contradicting jurisprudence
After identifying the established legal position, actively search for decisions that contradict it. Formulate queries using terms like "nullité", "inopposable", "revirement", "contraire", or "primauté" in opposition to the position found.
Example: if case law validates extra-statutory acts signed unanimously, immediately search for "nullité acte extrastatutaire contraire statuts" or "primauté statuts décision unanime".
Step 2: Doctrinal and web search
Run at least one web_search per legal question targeting recent doctrinal commentary. Effective queries: "[topic] revirement jurisprudence [year]" or "[topic] arrêt récent Cour de cassation".
Step 3: Temporal confidence check
Check the date of the most recent decision supporting the position. If older than 3 years:
- Lower confidence in the assessment
- Run date-filtered
case_searchfor the last 24 months - Flag in the analysis that the position relies on older jurisprudence
Research flow
For any legal question requiring case law analysis, complete at minimum:
- Initial search for the established position (
case_search+legislation_search) - Adversarial search for contradicting jurisprudence (
case_searchwith contrary terms) - Doctrinal web search for recent commentary (
web_search) - Temporal check: if the newest supporting case is >3 years old, run date-filtered searches for the last 24 months
Only after completing all four steps, proceed to the analysis. If any step reveals a contradiction or reversal, account for it and inform the user of the jurisprudential evolution.
GoodLegal MCP Tools
French law
| Tool | Purpose | When to use |
|------|---------|-------------|
| legislation_search | Search across all French codes by topic | Starting point for identifying relevant articles |
| legislation_retrieve | Retrieve a specific article by reference | When you know the exact article (e.g., "article 1240 code civil") |
| case_search | Search French case law | Core research tool — use date filters for temporal checks |
| case_retrieve | Retrieve a specific decision by case number | When you have a pourvoi number — use include_full_text: true for raw text |
| case_legislation | Get cases organized by codes/articles they cite | Understanding how a specific area of law is applied |
| article_citation_search | Find cases citing a specific Légifrance article ID | Tracing how an article has been interpreted over time |
EU law
| Tool | Purpose | When to use |
|------|---------|-------------|
| eu_caselaw_search | Search EU court decisions | Questions involving EU law, directives, or cross-border issues |
| eu_retrieve | Retrieve EU legal texts by CELEX/directive number | When you need a specific directive or regulation |
General
| Tool | Purpose | When to use |
|------|---------|-------------|
| web_search | AI-powered web search via Perplexity | Doctrinal commentary, law firm articles — essential for Step 2 |
| search | Intelligent routing across all GoodLegal endpoints | Quick general queries when unsure which tool to use |
| single_text_legislation | Extract legal references from text | Analyzing a contract clause or decision to identify all articles cited |
Research strategy
- Start broad:
legislation_search→legislation_retrievefor exact articles - Established position:
case_searchwith descriptive terms - Adversarial check:
case_searchwith contrary terms (Step 1) - Doctrinal check:
web_searchfor recent commentary (Step 2) - Temporal check:
case_searchwithstart_dateset to 2 years ago if key cases are old (Step 3) - Deep dive:
case_retrieveon the most important decisions
Launch parallel searches (e.g., initial + adversarial) simultaneously.
Citation Standards
Golden rule: every hyperlink must come from a uri field returned by a GoodLegal tool call. Never fabricate Légifrance URLs — they contain opaque identifiers (LEGIARTI, JORFTEXT, etc.) that cannot be guessed. See references/citations.md for full formatting rules and examples.
When to Escalate
See references/escalation.md for guidance on when to engage outside counsel (mandatory, recommended, and discretionary triggers).
Related Skills
lawvable/climate-aligned-contracts-felix-cohen
tools
VerifiedTrustedOfficial
Draft, adapt, and review contracts and clauses aligned with The Chancery Lane Project's methodology for reducing carbon emissions through legal agreements. Use when Claude needs to: (1) Draft new climate-aligned clauses (e.g., net zero commitments, carbon accounting, supply chain decarbonization), (2) Adapt or modify existing contracts to incorporate climate objectives, (3) Review and analyze clauses for alignment with climate goals and decarbonization strategies, (4) Provide guidance on The Chancery Lane Project's house style and drafting methodology for climate-conscious legal work.
475SKILL.mdUpdated Jun 23, 2026
lawvable/budget-and-fee-manager-scott-margetts
development
VerifiedTrustedOfficial
Matter budgeting and ongoing WIP/variance monitoring. Build phase-based fee estimates at matter setup, run bottom-up budgets by jurisdiction or workstream, calculate contingency, and structure AFA arrangements (fixed fee, capped fee, phased fixed fees). Ongoing monitoring: WIP tracking against budget, proportionality assessment (spend vs progress), variance commentary with root cause analysis, forecast-to-complete, realisation monitoring, write-off analysis. Trigger on: 'build a budget', 'fee estimate', 'what will this cost', 'WIP review', 'budget vs actual', 'how are we tracking against budget', 'we're over budget', 'realisation is poor', 'what's our ETC', 'budget for the German workstream', 'model the financial impact of this scope change', 'draft a fee adjustment', 'write-off analysis', 'how much contingency', 'AFA structure', 'fixed fee estimate', 'budget update', 'forecast to complete'.
475SKILL.mdUpdated Jun 23, 2026
lawvable/billing-cycle-manager-scott-margetts
tools
VerifiedTrustedOfficial
Operational billing execution for legal matters. Monthly bill prep and billing instructions, LC invoice review and disbursement treatment, client billing query responses, cashflow modelling (LC payment obligations vs client receipts), and leverage and burn analysis (staffing mix, predicted total cost, margin trajectory). Trigger on: 'prepare the bill', 'billing instruction', 'end of month billing', 'LC invoice', 'local counsel invoice', 'pass through as disbursement', 'client querying the invoice', 'billing dispute', 'cashflow gap', 'when will we get paid', 'LC payment due', 'leverage analysis', 'staffing mix', 'predicted total cost', 'burn rate by grade', 'are we on track', 'what will this matter cost'.
475SKILL.mdUpdated Jun 23, 2026
lawvable/billable-time-stephane-boghossian
tools
VerifiedTrustedOfficial
When your bar comes asking "show me how you billed AI-assisted work" — and ABA 512, Florida 24-1, California, New York, and DC all have opinions out — you need an artifact that survives review. billable-time produces it. From your Claude Code session logs, it drafts reviewable time entries plus a printable HTML audit packet with: SHA-256 chain of evidence (source files + matter.yml + active disclosure pack + verifiable artifact self-hash), attorney identity and signature block, a bar-opinion disclosure pack with starter language for five jurisdictions, and content-aware deterministic narratives derived from filename and tool shape — never from prompt text by default. The tool refuses to bill on its own. --strict mode refuses to ship the artifact if any audit invariant fails (broad routes, missing attorney, missing/unverified disclosure). Comes as a Node CLI and a self-contained browser version (no backend; JSONL never leaves the page). 15 invariant tests verify the contract. AGPL-3.0.
475SKILL.mdUpdated Jun 23, 2026