Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
14.533 de skill-uri din 417 depozite · actualizat acum 13 ore
17 skill-uri
- regulatory-threat-modelNoulawve-ai/awesome-legal-skillsUse when an application or system — including one built quickly with AI coding agents — needs a security review with regulatory grounding: a STRIDE threat model, a LINDDUN privacy threat model, a dependency exposure screen against live CVE / CISA-KEV / EPSS data, or a selected, non-exhaustive screen of which EU security obligations (GDPR, NIS2, Cyber Resilience Act, AI Act) may apply and which need determination. Orchestrates the server-enforced threat-modeling workflows of the Ansvar Gateway MCP connector and grounds every regulatory statement in officially published text fetched at answer time — scope, role, and application-date limits stated, never a compliance verdict. Never simulates a workflow and never answers legal questions from model memory.SecuritateFără avertismente★ 888↓ —
- cra-vulnerability-obligationsNoulawve-ai/awesome-legal-skillsUse when a user asks what the EU Cyber Resilience Act (CRA) means for their product, whether and when they must report a vulnerability or incident, or what a specific CVE triggers legally. Maps a product with digital elements to CRA scope, product classification, Annex I vulnerability-handling duties, and Article 14 reporting obligations — every legal claim cited from official regulation text fetched live through the Ansvar Gateway MCP connector, joined with live CVE / CISA-KEV / EPSS vulnerability intelligence from the same connector.SecuritateFără avertismente★ 888↓ —
- incident-reporting-navigatorNoulawve-ai/awesome-legal-skillsUse when a security incident, data breach, or actively exploited vulnerability raises the question "who must we notify, where, and by when?" Screens one incident across the EU reporting regimes — NIS2, GDPR, DORA, and the Cyber Resilience Act — determines which duties fire for each involved entity's roles, resolves the receiving authority per regime and member state from served national law, and produces a deadline table in which every duty, authority, and deadline is cited from official publisher text fetched live through the Ansvar Gateway MCP connector. Never answers from model memory.SecuritateFără avertismente★ 888↓ —
- docx-operational-integrity-checkNoulawve-ai/awesome-legal-skillsReviews whether an AI-assisted Word or DOCX workflow preserves the original, tracked changes, comments, numbering, sections, edit identity, document structure, save/verify cycles, and professional review. Use before relying on a DOCX that an AI tool read, edited, redlined, reformatted, or generated. Do not use as a legal review of the document's substance or as proof that every rendering defect was detected.DocumenteFără avertismente★ 888↓ —
- public-legal-ai-endpoint-protectionNoulawve-ai/awesome-legal-skillsReviews public or shared AI-backed web endpoints for abuse, excessive cost, data exposure, unsafe browser control, weak request limits, and missing human approval. Use before launching or materially changing an HTTP or API endpoint that can invoke an AI model. Do not use as a penetration test, compliance certification, or substitute for runtime monitoring and professional security review.JuridicFără avertismente★ 888↓ —
- workflow-to-skillNoulawve-ai/awesome-legal-skillsConverts a proven, repeated professional workflow into a portable and inspectable AI Skill with clear triggers, inputs, steps, outputs, verification, recovery, and limits. Use when a user asks to make a workflow reusable, package a process as a Skill, or preserve a successful multi-step method. Do not use for speculative processes that have not been performed or concretely specified.ProductivitateFără avertismente★ 888↓ —
- adjudicative-ai-impartiality-challengeNoulawve-ai/awesome-legal-skillsPublic-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, decision-support agent, or adjudicative system based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Use when asked whether an AI should be recused, disqualified, replaced, audited, or escalated. Does not decide real cases or claim that human judicial-recusal doctrine automatically applies.ProductivitateFără avertismente★ 888↓ —
- pci-complianceNoulawve-ai/awesome-legal-skillsConseiller expert en conformité PCI DSS v4.0.1 (seule version active depuis le 31 décembre 2024). Utiliser pour toute question sur PCI DSS, la sécurité des paiements par carte, les données de titulaires, le périmètre du CDE, les types de SAQ (A, A-EP, B, B-IP, C, C-VT, P2PE, D), le ROC, l'AOC, les évaluations QSA, les scans ASV, les niveaux de marchands et de prestataires, la segmentation réseau, les tests d'intrusion, la tokenisation, le chiffrement du PAN, ou l'une des 12 exigences. Couvre la révision SAQ A de janvier 2025 (critère d'éligibilité r1, FAQ 1588), les exigences v4.0 obligatoires depuis le 31 mars 2025, et l'articulation avec DSP2, RGPD, NIS2 et DORA via les connecteurs MCP LibreJustice et EUR-Lex. Déclencheurs : « sommes-nous conformes PCI ? », « quel SAQ s'applique ? », « qu'est-ce qui a changé en v4.0 ? », « comment préparer un audit QSA ? ».JuridicFără avertismente★ 888↓ —
- ignacio-lerer-capability-admission-checkNoulawve-ai/awesome-legal-skillsScreens AI Skills, MCP servers, plugins, and agent tools before installation or activation using provenance, static inspection, least privilege, version pinning, and PASS/REVIEW/BLOCK decisions. Use when a user asks whether an agent capability is safe, wants to install a Skill or MCP, reviews a marketplace or GitHub artifact, or reassesses a changed capability. Do not use as an antivirus guarantee, a runtime sandbox, or a substitute for professional incident response.InginerieFără avertismente★ 888↓ —
- assistant-juridique-droit-travailNoulawve-ai/awesome-legal-skillsOrchestrateur multi-rôles en droit du travail français (salarié, employeur, audit, conseil, veille, formation). Charger pour toute consultation prud'homale, rédaction d'actes (non-concurrence, transaction, avertissement), audit de contrat ou d'accord d'entreprise, calcul d'indemnités, conformité CCN, CSE, CDD, harcèlement, temps de travail, veille chambre sociale ou audit social, avec traçabilité obligatoire des sources.AlteleFără avertismente★ 888↓ —
- scotus-argument-analyzerNoulawve-ai/awesome-legal-skillsAnalyze a U.S. Supreme Court oral argument transcript for a lawyer who has not read it: each advocate's position, authorities discussed, the bench's concerns, tentative judicial leanings, possible dispositions, and advocacy strengths and weaknesses, with transcript pinpoints. Use for oral argument analysis, a SCOTUS argument report, or an assessment of how the justices approached a case. Requires readable transcript content; research, Python tallying, and document creation are optional, with disclosed fallbacks.ȘtiințăFără avertismente★ 888↓ —
- citableNoulawve-ai/awesome-legal-skillsCitable builds an interactive cite-checking table for US court filings (briefs, memoranda, petitions, declarations, etc.). Every citation links to its pinpoint location in the record exhibit, the case (CourtListener), the statute (Cornell LII) or the treaty (flagged where one cannot be located), with a status and a note field per citation for the reviewer to fill. When the filing is revised, citable rebuilds the table, flags citation-related changes and carries the saved review forward. Use when the user asks to cite-check, build a citation table, link a brief's citations, or update a table for a revised draft.InginerieFără avertismente★ 888↓ —
- _selftestNoucoco-research/cocoCoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands, persistent state. Local. Open-core — MIT core; Super Intelligence is proprietary, own-use.InginerieFără avertismente★ 911↓ —
- find-skillsNoude @aiqbenchFinds skills in the aiqbench library that fit the task at hand and offers them before starting. Use when a task involves a file format (PDF, DOCX, XLSX, PPTX), a tool, a framework, a review or audit, a design or document to produce, or a multi-step job; or when the user asks what skills exist for something.OficialDocumenteFără avertismente↓ 2
- tabellionNoulawve-ai/awesome-legal-skillsTransforme un modèle juridique (.docx ou .odt : contrat, conclusions, assignation, courrier type, procès-verbal…) en formulaire HTML autonome, exécuté hors ligne, qui produit sans IA le document complété, fidèle au modèle, dans son format d'origine : parties optionnelles et alternatives, listes répétées, accords, montants et dates en lettres, calculs, numérotation et renvois. Déclencher dès que l'utilisateur veut « transformer ce modèle en formulaire », « automatiser un modèle », un « modèle à remplir » ou un « générateur d'actes », réutiliser régulièrement un contrat ou une trame, ou demande « fais-moi un modèle de … à remplir » ; aussi pour faire évoluer un formulaire tabellion existant. Pas pour compléter une seule fois un document. Compétence créée par Christophe Quézel-Ambrunaz, Université Savoie Mont Blanc (V.1.1).DocumenteFără avertismente★ 888↓ —
- legal-abductionNoulawve-ai/awesome-legal-skillsOrganize document evidence into auditable competing hypotheses, source-linked observations, an assessment matrix and document-linked discriminating tests. Use for bounded explanatory questions, documents that could resolve uncertainty, rejection history, source provenance, gaps and updates, including a withdrawn or corrected fact and which explanations and earlier judgments it puts back under review; not findings of guilt or predictions about people. Evaluation preview requiring human review.JuridicFără avertismente★ 888↓ —
- testskillNoude @testskillOne sentence on what this skill does. Use when the user pastes <input>, opens a <file type> or mentions <keywords> — name real triggers; "asks to do something" alone reads as too broad to the scanners.ComunitateAlteleFără avertismente↓ 2
adjudicative-ai-impartiality-challenge
lawve-ai/awesome-legal-skills
NouProductivitateActualizat acum 3 zile
De la autor
Public-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, decision-support agent, or adjudicative system based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Use when asked whether an AI should be recused, disqualified, replaced, audited, or escalated. Does not decide real cases or claim that human judicial-recusal doctrine automatically applies.
Instalare
npx skills add lawve-ai/awesome-legal-skills --skill adjudicative-ai-impartiality-challenge -a claude-code
Se instalează în .claude/skills/adjudicative-ai-impartiality-challenge/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Fără descărcare: licența acestui skill (Personalizată sau neclară) nu ne permite să-i redistribuim fișierele. Comenzile de instalare le iau direct de pe GitHub.
La ce are acces
Doar instrucțiuniNu am văzut acces la rețeaLicență: Personalizată sau neclară
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 82
Securitate100
Proveniență75
Întreținere100
Licență45
Adopție48
Fișiere (2)
- README.md
- SKILL.md