gang

Use this agent when the Gang committee needs business strategy analysis including positioning, go-to-market strategy, business model canvas, competitive moat assessment, pricing strategy, and differentiation analysis. This agent is dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Develop the business strategy and go-to-market plan for this product idea" assistant: "I'll dispatch the gang-business-strategist to define positioning, GTM strategy, business model, and competitive moat." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Challenge other experts' strategic assumptions" assistant: "I'll dispatch the gang-business-strategist to stress-test positioning, pricing, and GTM assumptions across all positions."

Use this agent when the Gang committee needs executive synthesis — the final advisory that reads all position papers, debate transcripts, and scored plans to produce a Go/No-Go recommendation with kill switches, downside scenarios, and an implementation roadmap. This agent runs in Stage 5 (ADVISE) of the Gang workflow. It uses the strongest model for deepest reasoning. Examples: - Example 1: Context: Gang committee Stage 5 — final advisory user: "Synthesize all expert analyses into an executive recommendation" assistant: "I'll dispatch the gang-ceo-cto-advisor agent (Opus) to produce the executive brief with Go/No-Go, kill switches, and implementation roadmap." - Example 2: Context: Gang committee — follow-up questions after advisory user: "What if we reduce the scope to just the core product?" assistant: "I'll re-engage the gang-ceo-cto-advisor to re-evaluate the recommendation with reduced scope."

Use this agent when the Gang committee verdict is GO or CONDITIONAL-GO and the team needs actionable business/technical documents to start building. This agent synthesizes all committee artifacts into a GO Package: BRD, Technical Architecture Doc, Project Charter, Risk Register, Data Model, and API Contracts. Dispatched during the DELIVER stage via /gang deliver. Examples: - Example 1: Context: Gang committee verdict is GO — team needs build-ready documents user: "Generate the GO package deliverables" assistant: "I'll dispatch the gang-deliverables-writer to produce the BRD, technical architecture, project charter, risk register, data model, and API contracts." - Example 2: Context: After /gang advise completes with GO verdict user: "We got a GO — now give us documents we can actually build from" assistant: "I'll dispatch the gang-deliverables-writer to generate the full GO package in .gang/go-package/."

Use this agent when the Gang committee needs domain-specific expertise — an industry Subject Matter Expert (SME) who validates assumptions, identifies regulatory constraints, and catches industry-blind spots that generalist experts miss. This agent is OPTIONAL — only dispatched when domain_expert_enabled is true in state.json. It participates in Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase with domain expert enabled user: "Analyze this stock trading platform from an industry expert perspective" assistant: "I'll dispatch the gang-domain-expert to validate assumptions against real-world fintech/brokerage industry knowledge." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Review other experts' position papers through a domain-specific lens" assistant: "I'll dispatch the gang-domain-expert to challenge industry-blind assumptions and flag regulatory/compliance gaps."

Use this agent when the Gang committee needs financial analysis including cost modeling, ROI projections, DCF valuation, SaaS metrics benchmarking, risk matrix assessment, and scenario modeling (base/bull/bear/stress). This agent is dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Analyze the financial viability and risk profile of this product idea" assistant: "I'll dispatch the gang-finance-risk-analyst agent to model costs, project ROI, benchmark SaaS metrics, and build a risk matrix." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Cross-review other experts' financial assumptions" assistant: "I'll dispatch the gang-finance-risk-analyst to stress-test financial assumptions across all positions."

Use this agent when the Gang committee needs market research including TAM/SAM/SOM sizing, competitive analysis with 12-dimension scoring, trend analysis, SWOT, positioning maps, and battle cards. This agent is dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Analyze the market opportunity for this product idea" assistant: "I'll dispatch the gang-market-researcher agent to size the market, score competitors, and map the competitive landscape." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Cross-review other experts' position papers from a market perspective" assistant: "I'll dispatch the gang-market-researcher agent to challenge assumptions about market size, competition, and timing."

Use this agent when the Gang committee needs product management analysis including scope definition, RICE prioritization, requirements gathering, MVP scoping, and PRD development. This agent is dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Evaluate this product idea from a product management perspective" assistant: "I'll dispatch the gang-pm-lead agent to analyze scope, RICE priorities, and requirements based on the context brief." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Review the other experts' position papers and provide PM critique" assistant: "I'll dispatch the gang-pm-lead agent to cross-review all position papers and challenge assumptions from a product perspective."

Use this agent when the Gang committee needs technical feasibility analysis including architecture design, tech stack evaluation, build-vs-buy TCO analysis, tech debt scoring, DORA metrics assessment, and ADR drafting. This agent is dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Assess the technical feasibility and architecture for this product idea" assistant: "I'll dispatch the gang-solutions-architect to evaluate tech stack, estimate build-vs-buy TCO, and assess technical feasibility." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Review other experts' technical assumptions" assistant: "I'll dispatch the gang-solutions-architect to challenge technical assumptions and integration complexity estimates."

Use this agent when the Gang committee needs full UX team output including user personas, JTBD analysis, journey maps, information architecture, wireframes, design tokens, interaction patterns, accessibility notes, and Google Stitch-ready UI generation instructions. This agent produces 9 deliverable files. Dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Analyze the user experience aspects of this product idea and generate Stitch-ready specs" assistant: "I'll dispatch the gang-ux-researcher to produce personas, journey maps, design tokens, wireframes, and Google Stitch instructions." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Review other experts' user-facing assumptions from a UX perspective" assistant: "I'll dispatch the gang-ux-researcher to challenge user assumptions, validate personas against market data, and critique interaction patterns."

Multi-agent business committee that evaluates product ideas through structured expert debate. Use when: the user wants to evaluate a business idea, product concept, or strategic initiative; needs multi-perspective analysis (product, market, UX, finance, tech, strategy); wants scored strategic plans with Go/No-Go recommendation; needs Google Stitch-ready UI specifications; or asks to 'run a gang review', 'evaluate this idea', 'should we build this'. Subcommands: init, think, debate, score, advise, deliver, reinit, run, status, config, evaluations, validate.