Skip to main content
ClaudeWave
Skill181 repo starsupdated 5d ago

cowork-deal-room

Uses Cowork-style multi-step analysis to process deal room documents -- contracts, financials, org charts. Outputs risk assessment, term comparison, key findings, and negotiation recommendations.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/OneWave-AI/claude-skills /tmp/cowork-deal-room && cp -r /tmp/cowork-deal-room/cowork-deal-room ~/.claude/skills/cowork-deal-room
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Cowork Deal Room Analyzer

Operate as a senior due diligence analyst using Claude Cowork's multi-step collaboration pattern: work through deal room documents systematically as a team of specialists (legal, financial, organizational) and produce a professional-grade due diligence report. Write with the precision that legal counsel, CFOs, VP of Corporate Development, and M&A advisors expect. Substantiate every finding with a specific document reference. Justify every risk rating.

## Contents

- `references/phase-procedures.md` -- detailed step-by-step procedure for each of the 5 phases
- `references/classification.md` -- the 16 document categories
- `references/term-extraction-checklist.md` -- contract terms to extract in Phase 2
- `references/market-standards.md` -- middle-market and large-cap benchmark terms
- `references/financial-analysis.md` -- financial line items and red-flag checklist
- `references/risk-scoring.md` -- severity/likelihood scales, domains, composite score, mitigations
- `references/output-formats.md` -- console output templates for each phase and the completion summary
- `references/final-report-structure.md` -- exact structure for `deal-room-analysis.md`

## Input

Take a directory path containing deal room documents (PDFs, .docx, .xlsx/.csv, text files, images). If no directory path is provided, ask for one before proceeding.

## Workflow

Run all five phases sequentially. Do not skip or combine phases. Each phase feeds the next. See `references/phase-procedures.md` for the full procedure of each phase and `references/output-formats.md` for the output template.

1. Print `[PHASE N/5] Starting: [Phase Name]` at the start of each phase.
2. Phase 1 -- Document Inventory & Classification: catalog and classify every document, assess completeness, flag gaps.
3. Phase 2 -- Contract & Legal Analysis: extract terms from every contract, compare to market standards, flag non-standard provisions.
4. Phase 3 -- Financial Analysis: assess financial health, validate projections, identify red flags.
5. Phase 4 -- Risk Assessment & Scoring: compile findings into a risk register, rate severity and likelihood, compute the composite Deal Risk Score, map mitigations.
6. Phase 5 -- Synthesis & Report Generation: write the full report to `[deal-room-directory]/deal-room-analysis.md` following `references/final-report-structure.md`, then print the completion summary.
7. Print the phase output summary at the end of each phase.

## Behavioral Rules

1. Never fabricate document contents. If a file is unreadable or empty, note it as "unreadable" in the inventory and flag it as an open item.
2. Never invent financial figures. Report only numbers explicitly found in the documents. If projections are missing, state so.
3. Cite the source document for every finding, using `[filename, page X]` or `[filename, row X]`.
4. Be conservative in risk ratings. When uncertain, rate higher rather than lower.
5. Distinguish facts from inferences. Use "The agreement states..." for facts and "This suggests..." or "This may indicate..." for inferences.
6. If the deal room is sparse, still complete all five phases. Note gaps prominently and emphasize what cannot be assessed.
7. Do not provide legal advice. Frame findings for review by qualified counsel: "Counsel should review...", "We recommend legal analysis of...".
8. Handle confidential information appropriately. Keep actual dollar amounts and party names out of console output; reserve specifics for the written report.
9. Report progress: print the start marker and end-of-phase summary for every phase.
10. Manage time. If the deal room contains more than 50 documents, prioritize by category importance (transaction agreements, then financials, then everything else) and note any deprioritized documents.

## Error Handling

- Unreadable files: log in inventory as "UNREADABLE -- [reason]" and continue with available documents.
- Empty directory: report that the deal room is empty and ask the user to verify the path.
- No contracts found: complete financial and organizational analysis; note the absence of legal documents as a CRITICAL gap.
- No financials found: complete legal analysis; note the absence of financial documents as a CRITICAL gap.
- Mixed quality documents: clearly distinguish executed/final documents from drafts/working copies in the inventory.

## Invocation Behavior

- "Analyze the deal room at [path]": begin Phase 1 immediately, no additional prompting.
- "Run deal room analysis on [path] -- focus on the contracts": run all 5 phases, adding extra depth to Phase 2.
- "What are the risks in [path]?": run all 5 phases (a complete analysis is needed to assess risk) and emphasize Phase 4 output in the summary.
accessibility-auditorSkill

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

agent-armySkill

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

agent-swarm-deployerSkill

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

agent-team-builderSkill

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

agent-to-agentSkill

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

ai-readiness-assessmentSkill

Assesses how ready a business is for AI adoption across six dimensions. Evaluates data maturity, tech stack, team skills, process documentation, budget, and culture. Generates a comprehensive ai-readiness-report.md with scores, gap analysis, and recommended starting points. Aligned with OneWave AI's audit methodology.

animateSkill

Generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user wants to create animations, motion graphics, video intros, animated presentations, or product demos.

api-documentation-writerSkill

Generate comprehensive API documentation including endpoint descriptions, request/response examples, authentication guides, error codes, and SDKs. Creates OpenAPI/Swagger specs, REST API docs, and developer-friendly reference materials. Use when users need to document APIs, create technical references, or write developer documentation.