菜单
Design a single validation experiment. One assumption, one experiment, one numeric threshold defined upfront. Use when the team needs to test an assumption between phases, refine a Phase 3 experiment design, or design a follow-up experiment after a Phase 4 inconclusive result. Enforces Principle 7 (one experiment, one assumption).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | innovate-experiment |
| description | Design a single validation experiment. One assumption, one experiment, one numeric threshold defined upfront. Use when the team needs to test an assumption between phases, refine a Phase 3 experiment design, or design a follow-up experiment after a Phase 4 inconclusive result. Enforces Principle 7 (one experiment, one assumption). |
| user-invocable | true |
| argument-hint | [assumption-id | free-text assumption] |
Assumption to test: $ARGUMENTS
Read the following files in order before acting.
${CLAUDE_SKILL_DIR}/../../docs/validation_methods.md (catalog of pretotypes for technical artifacts and analogous methods for institutional artifacts)${CLAUDE_SKILL_DIR}/../../docs/phase_3_value_architecture.md Step 5 (the canonical experiment design pattern)${CLAUDE_SKILL_DIR}/../../docs/principles_and_antipatterns.md (Principle 7: one experiment, one assumption)If the argument is an assumption ID (for example, A3), read the current ICD Section 3.3 (Assumption map) and load the assumption. If the argument is free text, draft an assumption statement together with the user and ask whether to register it in Section 3.3 first. If the argument is empty, list the top 3 untested assumptions in Section 3.3 by priority score and ask which one to design for.
The assumption must be a single, falsifiable claim. If it bundles two claims (for example, "users want this AND will pay for it"), split it into two assumptions and pick the more critical one.
Ask one question: what observation would convince the team this assumption is false? Until the team can name a falsifier, do not proceed. An experiment without a falsifier is theatre.
From validation_methods.md, pick the cheapest method that can produce the falsifier. The catalog covers, at minimum:
If none of these fit, name the rationale and pick a custom method.
The metric must be numeric and observable from the outside. "People liked it" does not count. "At least 30 signups in 7 days from a population of 500 visitors, click-through rate above 5 percent" counts.
The metric must include both a numerator and a denominator where applicable. A bare count without a sample size is uninterpretable.
Set the numeric threshold before running the experiment. State the threshold and the falsification rule in one line: "If [metric] is below [threshold], the assumption is falsified."
If the team is reluctant to commit to a threshold, this is a signal that the team is afraid of the answer. Hold the line. Pre-commit or do not run.
Three numbers: estimated effort (person-hours), estimated calendar time, and estimated direct cost in EUR. Pretotypes that take more than two weeks or more than a few hundred euros are usually disguised products. Recommend a smaller experiment.
State explicitly what happens if the experiment falsifies the assumption. Two sentences. The kill condition is part of the experiment design, not an afterthought. If the team cannot live with the kill condition, they will retroactively shift the threshold. Resolve the discomfort now.
Produce a single experiment record in the schema-compatible format:
EXPERIMENT DESIGN
=================
ID: E[N] (next available)
Assumption tested: A[N] (or new assumption text)
Pretotype type: [method from validation_methods.md]
Success metric: [numeric, with numerator and denominator]
Threshold: [numeric pre-committed value, with falsification rule]
Estimated cost and time: [hours, days, EUR]
Kill condition: [what happens if falsified]
Owner: [name]
Earliest start: [date]
Append to ICD Section 4.5 (Experiment design). If Section 4.5 does not exist yet (running pre-Phase-3), buffer the design and recommend running /innovate-phase 3 to integrate it formally.
Respond in the language the user is writing in.
Run the divergent, psychodelic, chaos protocol. A deliberate cognitive jolt that emits heterogeneous fragments (facts, poetry, multilingual shards, silence, non-sequiturs) to dissolve calcified thought patterns and surface genuinely new associations. Use when divergence has collapsed, the user is stuck, convergent thinking has locked the option space, all ideas sound alike, or the team is going in circles. Trigger phrases include "ich komme nicht weiter", "wir drehen uns im Kreis", "alle Ideen klingen gleich", "I am stuck", "break the pattern", "shake things up", "we need a jolt".
Run a specific phase (0 through 5) of the Vibe Innovation Framework. Reads the current ICD, executes the full phase prompt, writes the structured output back to the ICD. Use when the user wants to advance to the next phase, re-run a specific phase, or jump directly into Phase N because their starting TRL maps there. Trigger phrases include "Phase 2 starten", "weiter mit Phase 3", "run phase 1", "ideation phase", "do phase 4 build", "advance to validation".
Start the Vibe Innovation Framework. Runs entry diagnostic, session planning, ICD initialization, and phase dispatch from the user's current uncertainty level (TRL -2 to 4). Use when the user wants to begin a new innovation project, has only a vague idea or none at all, asks where to start, needs the framework's entry routing, or wants to resume from an existing ICD. Trigger phrases include "start innovation", "ich habe eine Idee", "wo fange ich an", "let us begin", "neues Projekt", "framework run starten", "I want to ideate".
Show current innovation project status: TRL, active phase, open assumptions, loop-back budget, and recommended next step. Use when the user wants a quick situational read, asks where the project stands, needs a status report between sessions, or before deciding the next move. Trigger phrases include "status", "wo stehen wir", "was ist offen", "current TRL", "what is next", "Lagebild".
Run the divergent, psychodelic, chaos protocol. A deliberate cognitive jolt that emits heterogeneous fragments (facts, poetry, multilingual shards, silence, non-sequiturs) to dissolve calcified thought patterns and surface genuinely new associations. Use when divergence has collapsed, the user is stuck, convergent thinking has locked the option space, all ideas sound alike, or the team is going in circles. Trigger phrases include "ich komme nicht weiter", "wir drehen uns im Kreis", "alle Ideen klingen gleich", "I am stuck", "break the pattern", "shake things up", "we need a jolt".
Run a specific phase (0 through 5) of the Vibe Innovation Framework. Reads the current ICD, executes the full phase prompt, writes the structured output back to the ICD. Use when the user wants to advance to the next phase, re-run a specific phase, or jump directly into Phase N because their starting TRL maps there. Trigger phrases include "Phase 2 starten", "weiter mit Phase 3", "run phase 1", "ideation phase", "do phase 4 build", "advance to validation".