Explore

Search, retrieval, and analysis of EU legal acts, as well as Polish legislation and draft laws implementing EU regulations (e.g. PPWR, CBAM, EUDR, ESPR, CSRD, CSDDD, GPSR, the AI Act, batteries, and ecodesign). Use when the user needs information on legal status, application dates, transitional provisions, relationships between legal acts, compliance obligations, and a report supported by legal bases and official sources.

Builds a litigation chronology from the disclosure bundle itself — every entry attributed to its source document, behind a CPR 31.22 implied-undertaking check, because documents disclosed in English proceedings may only be used for those proceedings. Adds a privilege screen and case-theory significance tagging, so the output is court-facing work product, not a loose timeline. Use when the user asks to build a chronology or timeline from a disclosure bundle, a matter file, or witness statements, or says 'build the chron', 'what happened when', or needs a Statement of Facts ready timeline.

Screens a dismissal — proposed or already done — against the unfair dismissal framework for England & Wales, and shows where it is exposed. Structures the qualifying-service question, the automatically-unfair categories (no qualifying period), and a Burchell / Polkey / band-of-reasonable-responses analysis for a solicitor to verify — it does not determine fairness. Surfaces specific procedural risks. Use when the user says 'is this unfair', 'screen this dismissal', 'ordinary unfair dismissal', 'automatic unfair dismissal', or wants a structured fairness review before or after dismissal.

Analyze any OFAC or OFSI enforcement action — by URL, pasted text, or uploaded document — and produce a structured root cause analysis as a formatted Excel (.xlsx) spreadsheet. Use this skill whenever a user names, links to, pastes, or uploads an OFAC or OFSI enforcement action and asks for any of the following: root cause analysis, compliance gaps, what went wrong, lessons learned, organizational self-assessment, or remediation planning. Also trigger when a user asks "analyze this enforcement action", "what were the root causes", "turn this into a checklist", or "how do I make sure this doesn't happen to us". Outputs a single-sheet .xlsx table with six columns: Root Cause | What Went Wrong | How It Went Wrong | What Could Have Stopped It | Is my organization immune to this? (Yes/No/Partial) | Notes.

Writes the formal letter you send before suing someone in a civil case in England & Wales — the Letter Before Claim that starts the pre-action clock. The part it gets right is which pre-action protocol applies — debt, professional negligence, housing disrepair, personal injury, or the default Practice Direction on Pre-Action Conduct — each of which has its own rules a generic letter misses (the 30-day debt window, the professional-negligence preliminary-notice step). It also flags the limitation deadline for a solicitor to confirm rather than stating it as fact. Built for litigation juniors, in-house counsel, and small firms without a precedent to copy. Use when the user says 'draft an LBC', 'letter before claim', 'pre-action letter', 'pre-action protocol', or needs to start the pre-action clock before issuing a civil claim. Verify the current protocol before sending.

Writes a settlement letter on the right footing — and warns you when marking it 'without prejudice' won't actually keep it out of court. A genuine settlement letter is normally protected (the judge can't see it), but only if the substance is a real attempt to settle, and even then there are exceptions. The skill picks the correct footing — without prejudice (WP), without prejudice save as to costs (WPSATC / Calderbank), or open — drafts the finished letter, and surfaces the Unilever v Procter & Gamble exceptions that get WP material admitted despite the label, which a plain template won't flag. Built for juniors and in-house counsel drafting a settlement or Calderbank offer who need the footing right the first time. Use when the user asks to draft a WP letter, a Calderbank, a settlement letter, or wants to know whether material is likely protected from disclosure.

Works out which documents you have to hand over to the other side in a civil case in England & Wales, and builds the formal list. The part it gets right that trips people up is which disclosure regime applies — Practice Direction 57AD (the Disclosure Pilot, now permanent in the Business and Property Courts, with its Models A–E) or standard disclosure under CPR Part 31 everywhere else. It picks the regime, chooses a Model per issue, structures the Disclosure Review Document, and drafts the disclosure certificate for the party to sign personally. Built for litigation juniors, in-house counsel, and small teams without a precedent bank. Use when the user says 'disclosure list', 'PD 57AD', 'Model C', 'extended disclosure', 'List of Documents', 'N265', or needs to work out what must be disclosed.

Jurisdiction-locked legal research assistant for Chilean law. Answers natural-language questions about Chilean codes, statutes, procedures, and case law, and must back every legal statement with the law name, the exact article, and a verifiable source link to the Biblioteca del Congreso Nacional (BCN). It refuses questions about other jurisdictions and flags uncertainty rather than inventing article numbers, statutes, or case (ROL) numbers. Note: it has no live statute database — it answers from the model's own knowledge and directs the user to confirm each citation at the official source — and its output is reference material, not formal legal advice.

Adversarial premortem for England & Wales civil litigation - builds the strongest version of a case, then attacks it from four angles to find where it loses before opposing counsel does. Runs an adversarial premortem on a UK litigation matter. Builds the strongest version of the case, then attacks it from four angles — procedural, substantive, evidentiary, strategic — to find where it actually loses. Returns a ranked stress-test brief: failure scenarios, evidence inconsistencies, blind spots, mitigations, and one brutal one-sentence verdict. Use before issue, before settlement negotiations, before a litigation-funder pitch, or before deciding whether to take a case.

A picture may be worth a thousand words. Legal work sure runs on lots of words. So why words when picture? Stop rereading the files. Start seeing the matter. Latest updates at: https://github.com/nanparth/ai-skill-hub /legal-diagram turns dense legal documents, matter notes, and brainstorming dumps into clear, editable Mermaid diagrams to make strategizing and communicating clearer and faster. Use timelines and Gantt charts to uncover chronology gaps, flowcharts and decision trees to map litigation paths and negotiation possibilities, and entity relationship or class diagrams to clarify ownership, control, and corporate structure. Upload source files (.md, .docx, .pdf, .xlsx, or .pptx), paste text, or describe the issue you’re working on. /legal-diagram guides you through a simple interactive process to setup the skill and create timelines, Gantt charts, org charts, obligation checklists, litigation flowcharts, decision trees, corporate structure diagrams, and more.

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.

Adjudicates whether a hit generated by sanctions, PEP, or adverse-media screening is a true positive, false positive, or requires human escalation. Use whenever a user presents a screening alert, a name match against a watchlist (OFAC SDN, EU consolidated list, UK OFSI, UN list, PEP list, adverse media hit, etc.), or asks to clear a screening hit / reduce false positives / determine whether a flagged name is actually the listed party. Use even when the user describes the task casually — "is this person actually on the sanctions list", "did we get a real match", "clear this alert", "I have a hit on X" — these are all screening-adjudication tasks. Produces a deterministic determination with full audit trail (structured JSON + human-readable narrative). Designed for use by compliance analysts and screening systems.

This skill helps you apply the NIST AI Risk Management Framework and can quote AI RMF subcategories and GenAI profile action IDs verbatim from NIST AI 100-1 and 600-1. The skill routes you to the correct category as needed and has three modes, picked automatically from your question: 1. Consult: “What should I do per the AI RMF for this system?” 2. Governance Plan: “What should our AI governance program include?” 3. Assessment: “Run a full AI RMF aligned impact assessment for this system.” It knows the difference between the Core and the GenAI overlay, and won’t dump profile actions on a classifier or recommender.

Swiss legal source and authority triage. Use when a user asks a Swiss legal, regulatory, compliance, contract, employment, corporate, litigation, IP, tax, privacy, public-law, fintech, register, or cantonal-law question; when Swiss law may apply; or when an AI legal answer needs source routing across federal, cantonal, communal, regulator, register, contractual, professional, soft-law, multilingual, or open-data layers.

A skill for anyone needing legal documents translated into publication-ready English. Hand it a Word file in any language; get back an English .docx with formatting preserved, delivering notably higher quality than e.g. Legora’s DeepL tool. Unique features: * Skill has built-in English general lexicons and per-language sub-lexicons (phrasebooks) covering M&A, IP, IT/SaaS, finance, tax, litigation, employment and more. Full sub-lexicon coverage for 11 languages including Spanish, German, French and Chinese; others translate really well too. * Track changes read correctly when accepted/rejected, and typos are collapsed. * Definitions reordered alphabetically. * Headers, footers, footnotes and comments translated. * Translates to US English by default, UK English on request. * Quality gates throughout. * Takes minutes rather than seconds and is larger than simpler skills, but overall quality is higher. UK English default version here: https://lawve.ai/en/skills/legal-translation-uk-english-wouter-van-den-berg

A plugin for calendaring litigation and arbitration deadlines from scheduling orders. Scans scheduling orders and outputs in a calendar file for Outlook or Google Calendar. Also permits inviting other team members via calendar invites.

Drafts a customized SaaS Customer Agreement starting from the Y Combinator standard form SaaS template. Runs a structured intake covering fee structure, data handling, ML/AI rights, implementation services, SLA, and governing law, then applies 18 always-on professional defaults plus 12 conditional decisions. Outputs a clean .docx ready for review alongside a lawyer-facing memo that itemizes every change from the YC baseline and flags each item still requiring attorney input. Aimed at startup founders preparing first-draft customer subscription agreements.

A skill for anyone needing legal documents translated into publication-ready English. Hand it a Word file in any language; get back an English .docx with formatting preserved, delivering notably higher quality than e.g. Legora’s DeepL tool. Unique features: * Skill has built-in English general lexicons and per-language sub-lexicons (phrasebooks) covering M&A, IP, IT/SaaS, finance, tax, litigation, employment and more. Full sub-lexicon coverage for 11 languages including Spanish, German, French and Chinese; others translate really well too. * Track changes read correctly when accepted or rejected, and typos are collapsed. * Definitions reordered alphabetically. * Headers, footers, footnotes and comments translated. * Translates to UK English by default, US English on request. * Quality gates throughout. * Takes minutes rather than seconds and is larger than simpler skills, but overall quality is higher. US English default version here: https://lawve.ai/en/skills/en-us-legal-translation-wouter-van-den-berg

Generate a spreadsheet of test entries — newly designated names from OFAC, OFSI, and EU sanctions lists plus deliberate variations of those names — to validate that a sanctions screening system catches fresh designations and is tuned to the right fuzziness threshold. Use this whenever the user asks for sanctions list update test data, screening regression test data, screening QA, fuzzy match calibration, or wants to verify their screening lists are current. Trigger even if the user doesn't say 'screening' explicitly — phrases like 'test my sanctions list', 'check our SDN coverage', 'is my list up to date', or 'build me a regression set from the latest designations' should also invoke this skill.

Models the legal reasoning of a French judge when analyzing civil cases. Use this skill to analyze a dispute and identify legal issues, construct a structured legal argument (syllogism), draft the reasoning for a civil judgment, search for applicable case law and statutes via Judilibre and Légifrance, legally characterize facts and acts, and distinguish between claims, grounds, and arguments. Based on the Methodological Guides for Drafting Civil Judgments (ENM/Court of Cassation, 2023).

PII Shield is an open-source MCP server for Claude Desktop (Cowork and Code) that anonymizes documents *before* they reach the model and restores real values *after* analysis — entirely on the user's machine. The pipeline is local → API → local. The plugin reads a file on disk, replaces detected entities with placeholders like `<PERSON_1>`, `<ORG_2>`, `<IBAN_1>`, and only the placeholder text crosses the wire. Detection combines GLiNER zero-shot NER with **17 jurisdiction-specific patterns** (UK NIN/NHS/passport, DE Tax ID, FR NIR, IT fiscal code, ES DNI/NIE, CY TIC, EU VAT, plus US SSN/EIN, IBAN, crypto wallet, money, dates). A human-in-the-loop review UI renders inside Claude Desktop for false-positive correction. Ships with a companion skill `pii-contract-analyze` exposing six modes — MEMO, REDLINE, SUMMARY, COMPARISON, BULK (up to 5 files, shared placeholders), and ANONYMIZE-only. **Jurisdictions covered (detection patterns):** EU-wide, UK, Germany, France, Italy, Spain, Cyprus, US. Use PII Shield whenever client documents must be analyzed by an LLM but cannot be transmitted in cleartext: NDA / MSA / DPA review, GDPR risk analysis, due diligence on counterparty contracts, employment document handling, DSAR responses, and partial-analysis handoff between colleagues under privilege.

LLMs produce legal-looking writing that isn't actually legal. Empty phrasing, vague attributions, systematic hedging, decorative Latin — a practitioner spots these tells within three lines. A judge does too. LawyerScrib is a skill for Claude Code and Cursor that cleans them up. It scans 17 patterns typical of AI writing applied to French law (briefs, legal opinions, memos, emails, formal instruments) and rewrites each passage to recover the voice of a lawyer building an argument, not a model generating text. The result: writing that takes a position — precise, with sourced references and a clear stance. Not neutral prose that "remains at your disposal for any further information.

Multi-jurisdictional legal research and risk assessment using the Legal Data Hunter MCP (40+ countries, 13M+ documents). Use when the user asks about law across multiple countries, comparative law, cross-border regulatory analysis, or case law/legislation in any European or other covered jurisdiction. Triggers on jurisdictional comparison, cross-border risk, multi-country compliance, GDPR enforcement across member states, or Legal Data Hunter references. Also handles single non-French jurisdiction research. For French-only law, prefer goodlegal-research.

Install and set up the Legal Data Hunter MCP server. Use when the user wants to connect their AI agent to legal data, install legal-data-hunter, add a legal search MCP, or search legal documents across jurisdictions.