business-evaluation

Codex compatibility note:

• Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. Author .claude/**; mirrors are generated.
• Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
• Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Preserve protocol order unless the user approves a deviation. Workflows use $start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.

[BLOCKING] Execute declared steps in order. NEVER skip, reorder, or merge without explicit user approval. [BLOCKING] Before each step/sub-skill call, update todo tracking: set in_progress at start, completed at end. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools unavailable, maintain equivalent step tracker with same status transitions.

Quick Summary

Goal: Evaluate business idea viability; deliver evidence-backed viability verdict—score, confidence, Pursue/Pivot/Pause/Pass recommendation—grounded in complete 9-block BMC, 3-year financials + assumptions, 5+ risks with mitigation + residual risk, phased execution + GTM plan, so go/no-go rests on traced evidence, never optimism.

Summary:

• Order: Seven evaluation steps, preceded by a market-evidence precondition: load market evidence first, then run ALL 7 evaluation steps in order — detect idea/scope/evidence completeness; (1) capture idea (problem/solution/target), (2) 9-block BMC, (3) 3-year financials + assumptions, (4) 5+ risks + mitigation/residual risk, (5) phased execution, (6) GTM, (7) verdict. NEVER skip, reorder, or merge — why: partial evaluation invalidates the decision.
• Market gate: In workflow parent, read exact MARKET_ANALYSIS_PATH ({plan-dir}/research/market-analysis.md only copy fallback); standalone, use supplied path. If absent, state $market-analysis did not run, mark TAM/SAM/SOM, share, and segment size N/A, cap verdict confidence at 60%; NEVER re-derive sizing.
• Evidence gate: all 9 BMC blocks cite proof; every financial number has assumption + source; each 5+ risk has mitigation + residual risk; unbacked artifact fails.
• Decision/output: verdict = 1-10 score + confidence tier (95/80/60/<60%) + basis + Pursue/Pivot/Pause/Pass + key success condition; write to docs/knowledge/strategy/business/{descriptive-slug}.md via enforced .claude/templates/business-evaluation-template.md, then ask user question tool for next route (domain-analysis recommended); NEVER auto-decide, favor skepticism.

Workflow:

Before evaluation — detect + reason: classify supplied idea, scope, and market evidence as present, missing, or ambiguous; for each step run focused Think: evidence / economics / execution / decision passes. Derive concerns from idea + evidence; required blocks/categories guide coverage, not checklist recitation.

Precondition — load market analysis: In workflow-research business-eval mode, read exact parent-provided MARKET_ANALYSIS_PATH ({plan-dir}/research/market-analysis.md only copy fallback); in another workflow, read the exact path market-analysis returned in this run (or its {plan-dir}/research/market-analysis.md copy); standalone, use explicitly supplied path. Absent → do NOT re-derive: state $market-analysis did not run; mark every market-sizing figure (TAM/SAM/SOM, share, segment size) N/A with that reason; cap verdict confidence at 60%.