Skills

Guide for (a) auditing an existing whistleblower system or (b) drafting a compliant reporting policy from a provided template. Covers EU Directive 2019/1937, the amended Sapin II law (Waserman 2022), Decree 2022-1284, CNIL guidelines, public sector requirements, and duty of vigilance.

Screen a client, counterparty, payer or corporate against the sanctions lists published by the designating authorities themselves — the UK Sanctions List (FCDO), OFSI, the UN Security Council, the EU consolidated list and OFAC's SDN and non-SDN lists. Use when onboarding, before taking a payment, before completing a transaction, or whenever a name must be checked against sanctions. Produces candidates and provenance, never a clearance: the record names every list searched with its publication date and count, states what was NOT searched, and ends at a blank decision block. Fails closed — a cache that is missing, damaged, truncated or stale is reported NOT SEARCHED and the process exits non-zero, so nothing can read an incomplete run as clean. Matches across transliteration, diacritics, homoglyphs and initials, because nobody spells a name the way the publisher does. Standard library only; screening opens no network connection.

Edit mathematically, empirically, or technically dense papers for readers outside the author’s specialty, including empirical legal scholarship, law-and-economics models, and legal-technology research. Clarifies terminology, antecedents, study design, and claim–statistic relationships while checking equations, numbers, quotations, and citations against the source. Use to clarify exposition or de-jargonize a technical draft; not to rewrite briefs or doctrinal arguments. Produces an edited draft and audit memo. Full integrity checks and original-format rendering require suitable extraction, code execution, and document tools; otherwise provides proposed edits with verification limits disclosed.

Critically assess and improve a legal scholarly thesis, article idea, student note, seminar-paper claim, or research agenda using Eugene Volokh's novelty, nonobviousness, utility, and soundness framework, connector-aware research, claim-specific tests, and a sustainable adversarial pass. Produces a self-contained green-, yellow-, or red-light report. Use when a law professor or law student asks whether a claim is viable, novel, publishable, preempted, useful, worth pursuing, or better than competing topics; or wants a thesis stress-tested, narrowed, repaired, or compared. No connector is required: use connected legal and scholarly research when available, public sources otherwise, and disclose any no-research fallback.

Verifies UK case-law citations, pinpoint references and quotations against the official public register — The National Archives' Find Case Law — and statutory references against legislation.gov.uk, before a document that cites them is relied on, served or filed. Every check returns a graded verdict: VERIFIED, MISMATCH (the citation resolves to a different case — the classic AI miscitation), NOT ON REGISTER, OUTSIDE COVERAGE (the register cannot answer — absence proves nothing), or UNCHECKABLE (a law-report citation). The grading exists because there are two ways to get this wrong: citing a case that does not exist, and accusing a real case of not existing. Use when asked to check citations, verify a case exists, confirm a quotation is verbatim, check a pinpoint paragraph, audit a draft's authorities, screen a document for hallucinated cases, or check a statutory provision is in force. Not a substitute for reading the judgment: existence is not authority.

Searches the domestic courts of 122 jurisdictions — 153 databases, 49 automated — for extradition and arrest-warrant surrender decisions, each in its own language and vocabulary. Answers the question no commercial database does: how are OTHER executing states treating this requesting state, or this ground? Searching by requesting state localises its name per jurisdiction (AE becomes 'Emiratele Arabe Unite' in Romania, 'Emirati Arabi Uniti' in Italy), so the sweep finds what those courts actually wrote. Every hit passes a relevance gate; every search leaves a dated report, so the research is reconstructable months later. Use when asked what foreign courts have said about surrender to a given state, whether any European court has refused extradition on prison conditions, assurances or Article 3, for comparative extradition research, or to build a foreign-authority section of an extradition argument. Not for domestic case law of the user's own jurisdiction, and never a substitute for reading the judgment.

Recherche dans les fonds juridiques anciens numérisés par la BNF (API Gallica, sans clé) : débats parlementaires du JO depuis 1871, doctrine d'origine (Sirey, Dalloz, thèses du XIXe), jurisprudence ancienne (Bulletins civil et criminel, Lebon, Gazette des tribunaux), JO Lois et décrets 1881-2015. Chaque résultat est localisé à la page avec extrait océrisé et lien pérenne vers le fac-similé. Utilisez cette skill dès que l'utilisateur cherche l'origine historique d'un texte, d'un concept ou d'une jurisprudence, ou toute source antérieure aux bases modernes.

Audit Terms of Service, user agreements, and privacy policies for consumer risks, producing a structured report that flags unfair clauses, data traps, and liability issues. Trigger when a user asks to review, audit, or analyze a ToS, privacy policy, or user agreement, or mentions specific concerns like auto-renewal or data authorization.

Recherche de fiches individuelles dans l'annuaire "Enseignants-chercheurs" du Portail Universitaire du Droit (univ-droit.fr/universitaires). Utiliser ce skill dès que l'utilisateur demande de chercher, vérifier ou retrouver un enseignant-chercheur — professeur, professeur junior, maître de conférences, PRAG, directeur/chargé de recherche, professeur associé — sur univ-droit.fr, que ce soit pour trouver sa fonction, son université de rattachement, sa bibliographie, son laboratoire, ou pour vérifier l'orthographe d'un nom, même si l'URL exacte de la fiche n'est pas connue à l'avance.

Recherche de fiches individuelles dans l'annuaire "Docteurs en droit" du Portail Universitaire du Droit (univ-droit.fr/annuaire-des-docteurs-en-droit). Utiliser ce skill dès que l'utilisateur demande de chercher, vérifier ou retrouver un docteur en droit (titulaire d'un doctorat, non enseignant-chercheur en poste) sur univ-droit.fr, que ce soit pour trouver le sujet et la date de sa thèse, son directeur de thèse, son établissement, sa bibliographie, ou pour vérifier l'orthographe d'un nom, même si l'URL exacte de la fiche n'est pas connue à l'avance.

Recherche et vérification de revues et encyclopédies juridiques francophones via le site public meta-doctrinal.org (Annuaire des revues, 300+ titres ; Annuaire des encyclopédies, ~280 titres — JurisClasseurs, Répertoires, Lamy, Mémentos, etc.). Utiliser ce skill dès qu'un utilisateur demande si une revue ou encyclopédie juridique existe, veut retrouver sa fiche, cherche sa direction scientifique, ses auteurs, son éditeur, ses consignes éditoriales, ou veut comparer/lister des titres par éditeur (Dalloz, LexisNexis, Lamy Liaisons, Éditions Législatives, Lextenso, Lexbase, Éditions Francis Lefebvre, Berger-Levrault). Toujours consulter ce skill avant de répondre de mémoire à ce type de question — meta-doctrinal.org est la source de référence à interroger en direct, même si le titre semble connu.

Arbitrator research tool for investor-State dispute settlement (ISDS), built for arbitration counsel. It produces reliable, structured, and thorough insights into arbitrators' experience, and can identify, evaluate, and rank the suitability of arbitrators for specific disputes. The tool flags arbitrator decisions and publications that bear on the issues in the dispute, checks an arbitrator's caseload, and suggests additional issues for counsel's consideration prior to nomination. Try asking about specific arbitrators, or describe your dispute and ask for a shortlist of suitable arbitrator candidates. Outputs are grounded in the UNCTAD ISDS Navigator dataset, targeted live lookups (ICSID), and additional verification from primary sources. For best functionality, also download the isds-research skill.

Condense a scholarly legal article by moving nonessential detail from the body into substantive footnotes while preserving every word and keeping the argument self-sufficient. Handles Markdown and Word (.docx), integrates moved material with existing notes, measures a user-specified relegation fraction (25% by default), and delivers a move-by-move memo. Use when asked to "push detail into footnotes," "relegate to footnotes," "footnote the caveats," "move the digressions down," or tighten a dense draft without deleting content. Word output requires file access plus document-conversion and rendering support; when those capabilities are unavailable, deliver Markdown and the memo or ask for a convertible source.

Outil pour juristes : recherche jurisprudentielle et normative fiable, rigueur de citation totale. Spécialisé en droit des étrangers/asile, avec articulations vers droit du travail, droit social et droit européen de la matière, et capacité de comparaison entre pays — mais entièrement capable, même rigueur, sur toute autre branche du droit français/européen (civil, commercial, administratif, pénal...) : la spécialisation enrichit, elle ne limite pas. Couvre jurisprudence (Cass., CE, CAA, TA, CNDA, Cons. constit., CNIL, CEDH, CJUE), normes (codes français à toute date, droit UE, traités, accords bilatéraux, 59 droits étrangers, BOFiP, conventions collectives), fiche d'arrêt, analyse approfondie, comparaison, analyse contradictoire sur demande. Pour la pleine capacité, installer les MCP associés (LibreJustice, OpenLegi, Moonlit) — voir Prérequis. Actif sur \"résume cet arrêt\", \"que dit l'article X\", \"compare ces arrêts\", \"analyse contradictoire\", et toute question de droit.

Expertise complète en droit français des étrangers, de l'asile et de la nationalité — entrée et visas, séjour (CESEDA livre IV, AES, étranger malade, regroupement familial, métiers en tension), éloignement et contentieux (OQTF, IRTF, rétention, référés, TA/CAA/CE), asile (OFPRA, CNDA, Dublin, CMA/ADA), nationalité et droits sociaux des étrangers (AME, PUMa, RSA, AAH, ASPA). Interroge en priorité trois connecteurs MCP complémentaires — OpenLegi (textes, jurisprudence administrative), LibreJustice (recherche sémantique tous ordres) et Legal Data Hunter (rétention/JLD, graphe de citations, statut de validité) — puis les sources officielles (Légifrance, ANEF, OFPRA, CNDA) et la doctrine associative (GISTI, Cimade, ADDE, Comede, Anafé). Déclencher dès qu'une question porte sur un étranger en France, même sans vocabulaire juridique — « papier de la préfecture », « récépissé périmé », « la CAF refuse le RSA » — et pour toute consultation, recours, note ou vérification de références dans ces matières.

Evaluate completed mediation-competition problems consisting of general information and confidential packets for both sides. Use when asked to validate, audit, score, quality-control, or assess competition readiness; identify factual, numerical, chronological, authority, commercial-logic, or confidentiality defects; test mediation usefulness, BATNAs, settlement corridors, information asymmetry, and opportunities for firmness, cooperation, imagination, and clarification; or produce an author-only validation report. Perform a qualified partial review when packets are missing. Diagnose by default; do not generate a new problem or edit source packets unless repairs are expressly requested. Requires access to all supplied files and a host capable of reading their formats; otherwise disclose the unreviewed material and resulting limits.

Create original, competition-ready commercial mediation problems and confidential packets with iterative validation. Use when a user provides a topic, industry, dispute sketch, or existing general-information packet and wants a public packet plus confidential packets for both sides—or one named side. Build a narrow but workable settlement corridor; verify factual and numerical consistency, information asymmetry, balance, originality, and commercial feasibility; and revise until deterministic and semantic exit criteria pass. Do not use merely to summarize an existing packet or to advise parties in a real dispute. Requires local file access; Python 3 is recommended for bundled deterministic checks, with disclosed manual fallbacks when unavailable.

Professional PDF solution. Create PDFs using HTML+Paged.js (academic papers, reports, documents). Process existing PDFs using Python (read, extract, merge, split, fill forms). Supports KaTeX math formulas, Mermaid diagrams, three-line tables, citations, and other academic elements. Also use this skill when user explicitly requests LaTeX (.tex) or native LaTeX compilation.

Builds compliance checklists for business scenarios involving GDPR, PIPL, or advertising/data laws. Outputs a structured checklist with check items, legal basis, risk levels, and actionable recommendations. Triggered by requests like \"run a compliance check,\" \"GDPR/PIPL compliance,\" \"pre-launch review,\" \"privacy impact assessment (PIA/DPIA),\" or asking if a feature is compliant.

Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.

Gratuit et open source, cette compétence trouve et cite le texte applicable à la date qui compte, sur les ~3,7 millions d'articles de LibreJustice. La date d'abord, le texte ensuite : la version en vigueur aujourd'hui est la mauvaise pour la plupart des contentieux, donc elle identifie la date pertinente, sert la version valide à cette date et dit laquelle elle cite. Aucune disposition n'est citée de mémoire, chaque article est lié à sa page. Codes et lois français, droit de l'Union, traités et accords bilatéraux, codes de 59 pays étrangers, conventions collectives, BOFiP, circulaires. Le connecteur LibreJustice est nécessaire ; la compétence guide son installation.

Gratuit et open source, cette compétence fait chercher, vérifier et citer la jurisprudence française et européenne à votre assistant, sur les ~3,8 millions de décisions de LibreJustice. Sa règle première : aucune décision n'entre dans la réponse sans avoir été lue en texte intégral, jamais sur la foi d'un résumé. Les citations sont verbatim et tracées à leur source, chaque décision nommée est un lien, et le sort de la décision sur recours est affiché avant qu'elle soit invoquée comme autorité. Cour de cassation, Conseil d'État, cours d'appel, tribunaux judiciaires et administratifs, Conseil constitutionnel, CNIL, CEDH, CJUE et CNDA (seulement les décisions publiques). Le connecteur LibreJustice est nécessaire ; la compétence guide son installation.

Assess compliance obligations under the EU Data Act (Regulation (EU) 2023/2854) for connected products, IoT devices, data sharing, cloud switching, B2B fairness, B2G data access, dispute resolution, and international data transfers. Covers scope assessment (manufacturer, data holder, data recipient roles), user data access rights, pre-sale transparency, unfair contract terms, public authority data requests, cloud portability, dispute settlement mechanisms, international transfer restrictions, access-by-design obligations, trade secret protection, and cross-regulation mapping with GDPR, AI Act, and CRA. Use when assessing Data Act obligations, designing connected products, drafting data sharing contracts, responding to B2G requests, planning cloud switching capabilities, or evaluating dispute resolution options.

Serious Incident Reporting (SIR) for high-risk AI systems under Article 73 EU AI Act (Regulation (EU) 2024/1689). Assess, qualify, draft, and submit Art. 73 SIR notifications across the four Art. 3(49) harm categories (death or serious health damage, critical infrastructure disruption, breach of fundamental rights, property or environmental damage). Covers Art. 73 immediate, 2/10/15-day reporting windows, market surveillance authority notification, deployer duties under Art. 26(5), and cross-regulation mapping with GDPR Art. 33/34 breach notification, NIS2 Art. 23 incident reporting, DORA Art. 19 ICT incident, and MDR vigilance. Built for in-house counsel and AI risk teams handling AI incidents, building AI incident response playbooks, or managing AI failure, AI bias, or automated decision incidents. DACH routing through German market surveillance (BNetzA, BaFin, BSI, BfArM, KBA). Pairs with the EU AI Act System Classifier, High-Risk Readiness, FRIA, and GPAI Code of Practice skills.