Name: product-legal
Author: az9713

Claude for Legal

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.

Deep-dive documentation

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

Claude for Legal

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.

Deep-dive documentation

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

Help us improve

Help us improve

Help us improve

product-legal

Popularity

Health & Quality

Confidence

What's Inside

Help us improve

README

Claude for Legal

Deep-dive documentation

Similar Plugins

caveman

claude-mem

ui-design

nanobanana

prompt-improver

human-resources

More by az9713

agent-skills

codebase-singularity

agent-threads

impeccable

andrej-karpathy-skills

Claude for Legal

Deep-dive documentation