Agent Workflow Claude Skills
4 122 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 844 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 589 copies of these same skills sitting in other people's repositories — counted once here, not 589 times.
4 122 unique 665 authors 4 updated this month 506 from vendors
Use when a lawyer, legal team, or client needs to assess AI agents that can act on someone's behalf: send messages, search, draft, file, pay, delete, connect to accounts, use tools, or rely on external data. Produces a practical delegation, oversight, accountability, and control audit for legal operations.
Claude skill that turns Claude into a Connecticut-specific divorce planner — nine operating modes from pre-flight intake to post-judgment modification, modeled on Untangle.us's feature surface and grounded in C.G.S. Title 46b, Practice Book Chapter 25, and the 2026-08-01 CCSG schedule. Covers eligibility triage (nonadversarial under § 46b-44a vs standard), financial affidavit (JD-FM-6), child support (JD-FM-220 / CCSG-1 / 1A), alimony (§ 46b-82 fourteen factors), parenting plan (with GAL/AMC escalation under JD-FM-224), settlement agreement (JD-FM-172, TCJA-aware), filing packet (marshal 12-day rule, $360 + $50 fees, JD-FM-75 waiver), and post-judgment motion practice. Hard UPL gate: refuses non-CT, domestic violence (refers CTCADV 1-888-774-2900), hidden assets, courtroom advocacy. Heppner-aware: AI prompts are not privileged. First family-law skill in the Lawvable registry.
Audits legal AI outputs, prompts, skills, workflows and MCP/tool instructions for fluent but unsupported reasoning, missing evidence, overconfidence, hidden assumptions, weak causal links and absent human-review gates.
| Fast 15-25 minute triage for preliminary EU AI Act classification and compliance assessment. This skill should be used when the user asks to "do a quick AI Act assessment", "check if the AI Act applies to us", "run a preliminary classification", "do an AI Act triage", "quick check", "preliminary assessment", "Schnellprüfung", "Ersteinschätzung", or needs a fast initial assessment before committing to full analysis.
| Determines the organization's role (provider, deployer, importer, distributor, or quasi-provider) and assesses Art. 25 quasi-provider risk of the EU AI Act. This skill should be used when the user asks to "determine AI Act roles", "check if we are provider or deployer", "assess quasi-provider status", "check Art. 25 substantial modification", "check value chain responsibilities", or mentions "Betreiber", "Anbieter", "wesentliche Veränderung", or finetuning implications under the AI Act.
| Determines whether a technology qualifies as an AI system under Art. 3(1) of the EU AI Act and classifies its risk tier (prohibited, high-risk, GPAI with systemic risk, limited risk, minimal risk). This skill should be used when the user asks to "classify an AI system under the AI Act", "determine the AI Act risk tier", "check if something is an AI system", "assess prohibited practices", "check high-risk classification", "determine Art. 6 exception applicability", or mentions "KI-Verordnung", "Risikoklassifizierung", Art. 5, Annex III, or GPAI systemic risk.
>- LawyerScrib est un skill pour Claude Code et Cursor qui nettoie ces traces. Il scanne 17 patterns typiques de l'écriture IA appliquée au droit français (conclusions, consultations, notes, mails, actes) et réécrit chaque passage pour retrouver le ton d'un avocat qui argumente, pas d'un modèle qui rédige.
| Restructure any rough build, research, or legal-drafting request into an IRAC-shaped prompt — Issue, Rule, Analysis, Conclusion — optimized for a frontier model. It's the bar-exam framework, repurposed as prompt engineering. The skill leads with the issue and ends with the conclusion (where models weight attention most), forces you to name your constraints and non-goals, and specifies what "good" looks like before a single token is generated. Use it before any non-trivial build, or whenever a vague ask deserves a precise brief.
EU Digital Regulation Legal Analysis Forge — generates a tailored expert prompt for structured legal analysis of an EU digital-regulation document, optionally executes it in-session, and always produces a plain-English explainer alongside the formal output. Handles Regulations, Directives, Commission Guidelines, EDPB Opinions, CJEU and AG judgments, national DPA decisions, codes of conduct, and draft consultations across the EU digital stack.
Use this skill whenever a lawyer or mediator needs help analyzing a dispute for mediation purposes. This includes: reviewing case materials (pleadings, contracts, correspondence, evidence) to identify issues in dispute, summarizing each party's position and interests, conducting legal analysis of the key issues, proposing mediation strategies or settlement directions, and preparing for mediation sessions. Trigger this skill when the user mentions 'mediation', 'dispute analysis', 'settlement', 'dispute resolution', 'identify issues in dispute', 'party positions', 'mediation brief', 'case analysis for mediation', 'ADR', 'mediation preparation', 'caucus strategy', 'settlement options', or any request to analyze a conflict between two or more parties with the goal of finding resolution. Also trigger when the user uploads case files and asks for a structured breakdown of who wants what, what the core disagreements are, or how the case might settle. Even if the user doesn't explicitly say 'mediation', trigger when the context involves analyzing opposing positions in a dispute with a resolution-oriented (rather than litigation-oriented) goal.
>- >Ce skill donne accès à l'API de judilibre. Vous formulez votre demande en français, il interroge la base Judlibre et renvoie les réponses. Attention le skill ne fonctionne que si des domaines supplémentaires sont utilisés et que l'utilisateur a rentré sa propre clé Judlibre. Ce skill et son auteur n'ont aucun lien avec la Cour de cassation ou Judilibre
Determines whether a specific AI-agent action, output, recommendation, or proposed commitment remains admissible for execution or institutional reliance under current authority, delegated scope, evidence, facts, policy, risk, escalation, and revocation conditions. Use this Skill before an enterprise or regulated AI agent executes, updates records, triggers workflows, communicates externally, or before an institution relies on an agentic output in a way that creates consequence.
Sanctions and export control analysis tool for Claude Desktop. Real-time individual screening across 30+ official lists (UN, EU, OFAC, OFSI, French DGT...), sectoral analysis, dual-use goods (EU Reg. 2021/821), US/China extraterritorial regimes (EAR, ITAR, FDPR, ECL), USD/SWIFT risk and jurisdictional mapping across 30+ countries. All results sourced and verified in real time — no memory-based answers. Responds in French, English, German, Spanish, Russian and Chinese. Updated 19 May 2026 (EU 20th package, UK SEUC, Cuba EO). Indicative guidance only — not legal advice.
Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends the model's capabilities with specialized knowledge, workflows, or tool integrations.
Guide to analyze a current work session and propose improvements to skills. Use (1) automatically after working with a skill to capture learnings, (2) when the user suggests improvements, corrections, or additions during a skill-related session, or (3) when the user manually invokes `self-improve`.
Audits legal AI skills, prompts, workflows, MCP/tool instructions, and agent packages for prompt injection, malicious instructions, unsafe scripts, suspicious metadata, credential exposure, exfiltration paths, persistence mechanisms, and supply-chain risk. Use before installing, importing, publishing, promoting, modifying, or trusting third-party or generated AI skills and legal workflows. Do not use as a generic code review unless skill trust, workflow safety, prompt injection, or supply-chain hygiene is in scope.
Audit an AI agent skill before installing it. Use proactively whenever the user is about to add, install, enable, or evaluate an unfamiliar skill — including phrases like "audit this skill", "is this skill safe", "scan skill before install", "check skill for malicious code", "review this plugin", or any pre-install gate on an untrusted, third-party, or community-distributed skill bundle. Runs ten categories of static checks (code execution, network exfiltration, credential harvesting, persistence, prompt injection, supply-chain hooks, obfuscation, destructive filesystem ops, secrets, Trojan Source / homoglyphs) and emits a PASS / WARN / FAIL verdict.
>Ce skill génère des sujets d'entraînement pour les deux épreuves écrites de consultation du CRFPA : l'épreuve de droit des obligations (tronc commun) et l'épreuve de spécialité (civil, affaires, social, pénal, administratif, international et européen, fiscal). Chaque sujet est accompagné d'une grille de notation détaillée sur 20 points. Vous ciblez un thème précis, ou vous laissez le skill procéder à un tirage au sort couvrant l'ensemble du programme. Connexion aux MCP OpenLegi et GoodLegal requise : toutes les références d'articles et d'arrêts sont vérifiées sur les sources officielles, sans citation inventée
Use when setting up firebase_ai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
Configure the Canvas Authoring MCP server for the current coauthoring session. USE WHEN "configure MCP", "set up MCP server", "MCP not working", "connect Canvas Apps MCP", "canvas-authoring not available", "MCP not configured", "set up canvas apps".
Adds a data source or connector to a Power Apps code app. Asks what the user wants to accomplish and routes to the appropriate specialized skill.
Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.
Creates, updates, and deploys Power Apps generative pages for model-driven apps using React v17, TypeScript, and Fluent UI V9. Orchestrates specialist agents for planning, entity creation, and code generation. Use it when user asks to build, retrieve, or update a page in an existing Microsoft Power Apps model-driven app. Use it when user mentions "generative page", "page in a model-driven", or "genux". This skill stands alone and does not require /app-builder — but if the user wants a whole app built (tables, forms, views, sitemap) rather than pages for an app that already exists, use /app-builder instead.
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
How the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.
Wave methodology knowledge for the buddy agent — what each wave does, its inputs and outputs, and how to route questions.
Cross-agent collaboration protocols, workflow handoff patterns, and commit message formats for TDD/Mikado/refactoring workflows
Shared density-resolution contract for wave skills. Canonical detail on the D12 cascade, density resolver call, ad-hoc override workflow, and DocumentationDensityEvent telemetry emission. Referenced from nw-discover / nw-discuss / nw-design / nw-devops / nw-distill / nw-deliver.
Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.
Creates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE). Use when building a new AI agent or validating an existing agent specification.
Agent safety boundaries - input validation, output filtering, scope constraints, and document creation policy
>- Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.
>- Execute the next TaskMaster task using the implementation plan with CDD verification. Picks the next ready task, matches it to the plan step, implements via a dispatched subagent, verifies subtasks with evidence, marks the task done, and loops until every task is complete. Wraps the TaskMaster next -> in-progress -> done lifecycle with CDD GREEN / RED / BLUE verification and the plugin's triple-verification rule. Autonomous by design — no user prompts inside the loop.
>- Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholders_found, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis, and expands every task into verifiable subtasks. Autonomous-safe. Declares GENERATE complete so HANDOFF can follow.
>- handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a structured AskUserQuestion multi-option picker for user agency, and dispatches the chosen mode. Mode D (Atlas Fleet) is selectable only when detect_capabilities returns tier=premium (licensed atlas-launcher detected); otherwise it is a locked Atlas Pro teaser. user-agency mechanism. Declares HANDOFF complete so EXECUTE can follow.
How App Store ratings actually behave — per-storefront isolation (your US stars show nowhere else), the never-reset rule, phased release + manual release as rating protection, and where prompting/replying fit. Use when planning ratings strategy for new markets, considering a ratings reset, setting release options, or diagnosing "why is my rating missing in country X.
Apple Intelligence skills for on-device AI features including Foundation Models, Visual Intelligence, App Intents, and intelligent assistants. Use when implementing AI-powered features.
Generates a minimum version enforcement system with hard-block and soft-prompt update flows, App Store redirect, and remote config or App Store lookup for version checks. Use when user wants force update, mandatory update, or minimum version check.
Generates guided first-action flows that help users achieve a meaningful result within 60 seconds to boost retention. Use when user wants quick win onboarding, time-to-value optimization, or first success moments.
Generates smart App Store review prompt infrastructure with configurable conditions and platform detection. Use when user wants to add review prompts, request ratings, or implement StoreKit reviews.
Brainstorm and rank iOS/macOS app ideas tailored to developer skills. Use when user says "what should I build", "give me app ideas", "I don't know what to build", "brainstorm app ideas", or "help me find an app idea".
Discover and validate product ideas, analyze markets, scope MVPs, and optimize app store presence for iOS/macOS apps. Use when user asks to discover, validate, assess, scope, or analyze product ideas, market opportunities, or when they mention "product agent", "app idea validation", "should I build this", "MVP", "market analysis", or "ASO".
Platform-agnostic skills including skill creation templates and best practices. Use when creating new skills or improving existing ones.
Audits skills in this repo for consistency, API drift, and structural gaps. Produces a prioritized report grouped by severity (Critical/High/Medium/Low). Use when asked to "audit skills", "check the skill repo for drift", or when planning bulk skill cleanup. Read-only — does not apply fixes.
Guides you through creating well-structured Claude Code skills with proper modularization, templates, and best practices. Use when creating new skills or improving existing ones.