From cocounsel-legal
Use this skill when a user wants to analyze a contract using CoCounsel's contract analysis capabilities — clause extraction, risk identification, term comparison, or obligation mapping. Use when the user says "analyze this contract", "what are the risks in this agreement", "extract the key terms", or "compare these contracts." This capability is planned and will be available when the CoCounsel Legal MCP server exposes contract analysis tools.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cocounsel-legal:contract-analysisThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Status: stub** — This skill is ready for activation when the
Status: stub — This skill is ready for activation when the CoCounsel Legal MCP server adds contract analysis endpoints. The workflow below documents the intended behavior.
Analyze contracts using CoCounsel's AI-powered contract analysis, with research backing from Westlaw for enforceability and risk assessment.
The cocounsel-legal MCP server must expose contract analysis tools.
These tools are not yet available in the current MCP server version.
commercial-legal:contract-review)cocounsel-legal:deep-researchcocounsel-legal:document-draftingAccept the contract via:
Identify and extract:
For each extracted clause:
Output a structured analysis with:
| Clause | Market position | Contract position | Risk level | Notes |
|---|---|---|---|---|
| Liability cap | 12 months fees | 3 months fees | High | Below market; vendor-favorable |
cocounsel-legal:deep-research)cocounsel-legal:citation-verification)npx claudepluginhub chgreer1070/claude-for-legal --plugin cocounsel-legalGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.