git:20260718.7cc9d66 to git:20260718.188cd11

7 added, 5 removed. Audit A to A.

---

name: alternatives-explore

- description: Generate and evaluate genuinely different approaches to a product, workflow, or system problem. Use when the user asks for a bold, contrarian, experimental, or non-incremental alternative and wants a testable recommendation rather than ordinary optimization.

+ description: Generate and evaluate genuinely different approaches to a product, workflow, or system problem. Use when the user explicitly wants a bold, contrarian, experimental, or non-incremental alternative and a testable recommendation.

---

# Alternative Ideation

- Find a useful abstraction shift without confusing novelty with value.

+ Recommend one useful abstraction shift and a bounded experiment without turning ideation into architecture or implementation.

## Workflow

1. State the core problem, current assumptions, constraints, and outcome that must remain valuable.

- 2. Generate several materially different bets by changing ownership, workflow, abstraction, distribution, architecture, or a supposedly necessary component. Do not produce cosmetic variants.

+ 2. Generate several materially different bets by changing ownership, workflow, abstraction, distribution, architecture, or a supposedly necessary component.

3. Evaluate each bet for user value, distinctness, feasibility, reversibility, and testability.

4. Select the strongest bet and explain which default assumption it rejects, why that matters, and where it could fail.

- 5. Define the smallest prototype or experiment with a falsifiable success signal and a bounded cost.

+ 5. Define the smallest experiment with bounded cost and a falsifiable success signal.

- Prefer a sharp, testable idea over fashionable terminology or speculative infrastructure. Present the alternatives briefly, then develop only the selected bet.

+ Do not produce cosmetic variants, settle final architecture, research unresolved technical facts, write an implementation plan, or implement the experiment. Use `architecture-refine` for architectural convergence, `technical-spike` for blocking technical evidence, and `plan-create` for implementation planning.

+ Finish after recommending one experiment and its success signal. A recommendation does not authorize implementation.