Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By az9713
Triages proposed AI use cases against your registry, runs impact assessments across the regimes in scope, reviews vendor AI terms for training-on-data and liability gaps, and keeps your AI policy current with practice.
npx claudepluginhub az9713/claude-for-legal-tutorial --plugin ai-governance-legalEU AI Act per-system inventory — track each AI system's role (provider, deployer, importer, distributor, authorized representative, product manufacturer) and risk tier (prohibited, high-risk, limited, minimal, GPAI, GPAI+systemic). Role and tier are assessed per system, not per company. Use when the user says "ai inventory", "add an ai system", "what systems do we have", "classify this ai system", "eu ai act register", or "ai system registry".
Run an AI impact assessment — structured intake, risk analysis, regulatory classification per regime in scope, policy consistency diff, and recommendation with conditions. Uses the house-style structure learned from the seed impact assessment in `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`. Use when user says "impact assessment for", "assess this AI use case", "run an AIA", "generate an AIA", "we need to document this AI system", "AI risk assessment for X", or follows a conditional triage result.
Run the cold-start interview — learns your AI governance practice and writes `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` from your AI policy, a reference impact assessment, and key vendor AI agreements. Use when the practice profile is missing or contains `[PLACEHOLDER]` markers, or when user says "set up ai governance plugin", "onboard me", "configure ai governance".
Guided customization of your AI governance practice profile — change one thing without re-running the whole cold-start interview. Adjust risk posture, escalation contacts, use-case registry entries, vendor AI positions, AI policy commitments, impact-assessment house style, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my config", "tune my playbook", or "customize".
Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when any substantive skill needs to know which matter it's working in.
External network access
Connects to servers outside your machine
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Write SQL, explore datasets, and generate insights faster. Build visualizations and dashboards, and turn raw data into clear stories for stakeholders.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Full agentic layer framework implementing the Codebase Singularity concept - enabling AI agents to operate your codebase autonomously through planning, building, reviewing, and fixing workflows. Implements Class 1-3 with orchestration capabilities.
Thread-Based Engineering examples - demonstrates Base, Parallel, Chained, Fusion, Big, Long, and Zero-Touch thread patterns for agentic coding
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
This is a tutorial fork of anthropics/claude-for-legal. The plugins and skills are identical to the original. This fork adds a
docs/directory with deep-dive documentation that dissects how every plugin and skill is constructed — surfacing the design patterns, best practices, and architectural decisions behind the system. If you want to understand how to build on this, extend it, or replicate the patterns in your own plugins, start with the docs.
| Doc | What it covers |
|---|---|
| Overview: what is this? | Mental model, ASCII architecture diagram, end-to-end session narrative, scope boundaries |
| Key concepts glossary | 38-term glossary — every concept used across plugins and skills defined precisely |
| Quickstart | Working in under 15 minutes — dual path for Claude Cowork and Claude Code |
| Onboarding guide | Zero-to-confident: the linter analogy, the three things you must understand, a full NDA walkthrough |
| Plugin anatomy | Every file in a plugin directory dissected — plugin.json, CLAUDE.md, skills/, agents/, hooks/, .mcp.json |
| Skill anatomy | SKILL.md structure, frontmatter fields, all 8 recurring design patterns, skill design checklist |
| Practice profile | Config path contract, shared company profile, every CLAUDE.md section and its reasoning |
| Guardrails | All 18 shared guardrails dissected — no-silent-supplement, citation hygiene, destination check, cross-skill severity floor, and more |
| Agents | Scheduled agent anatomy, how agents call skills, managed-agent cookbook deployment |
| Connectors | MCP connector config, full connector table by practice area, the four behavior requirements |
| Hooks | hooks.json format, all hook events, practical legal-context examples |
| Build a skill | Step-by-step guide to authoring a SKILL.md that follows all 9 design principles |
| Build a plugin | Full plugin creation guide — directory layout, required files, 3 mandatory skills, CLAUDE.md construction |
| Customize a plugin | Three-level customization: cold-start interview, customize skill, direct editing |
| SKILL.md frontmatter reference | Every frontmatter field with valid values, defaults, and source examples |
| plugin.json reference | plugin.json and marketplace.json fields, version bump rules, author vs. owner distinction |
| Tag vocabulary reference | All 20+ inline tags — factual accuracy, source provenance, judgment, severity, cell states |
| System design | Full ASCII architecture diagram, 5 data flows, component breakdown, scaling characteristics |
| ADR 001: Two-layer instruction architecture | Why SKILL.md + CLAUDE.md — alternatives analyzed, trade-offs, consequences |
| ADR 002: Practice profile as plain text | Why markdown over YAML/JSON/database — alternatives analyzed, trade-offs, consequences |
| commercial-legal deep-dive | Sales vs. purchasing playbook, GREEN gate, scope check, dual severity, playbook monitor |
| corporate-legal deep-dive | Modular profile, typed column schema, verbatim enforcement, fan-out pattern |
| employment-legal deep-dive | Jurisdiction-first analysis, worker classification, investigation four-skill pattern |
| privacy-legal deep-dive | Three-tier triage, DPA auto-detection, DSAR statutory timelines, policy drift monitoring |
| product-legal deep-dive | Proportionality-first is-this-a-problem, risk calibration, launch tracker integration |
| regulatory-legal deep-dive | Materiality filter, Monday digest format, policy diff, gap tracker |
| ai-governance-legal deep-dive | Per-system classification, use-case registry, red lines, intentional no-auto-derive design |
| ip-legal deep-dive | Triage vs. opinion distinction, DMCA three-way, enforcement posture, OSS license classification |
| litigation-legal deep-dive | Dual-surface pattern, FRE 408 gate, chronology builder, privilege log review |