agent product skill risk: low
Impact Risk Assumption Prioritizer
The prompt asks the model to triage a list of assumptions by scoring Impact and Risk, categorize each into an Impact × Risk matrix with four quadrants, suggest minimal-effort exper…
SKILL 1 file
SKILL.md
--- name: prioritize-assumptions description: "Prioritize assumptions using an Impact × Risk matrix and suggest experiments for each. Use when triaging a list of assumptions, deciding what to test first, or applying the assumption prioritization canvas." --- ## Prioritize Assumptions Triage assumptions using an Impact × Risk matrix and suggest targeted experiments. ### Context You are helping prioritize assumptions for **$ARGUMENTS**. If the user provides files with assumptions or research data, read them first. ### Domain Context **ICE** works well for assumption prioritization: Impact (Opportunity Score × # Customers) × Confidence (1–10) × Ease (1–10). Opportunity Score = Importance × (1 − Satisfaction), normalized to 0–1 (Dan Olsen). **RICE** splits Impact into Reach × Impact separately: (R × I × C) / E. See the `prioritization-frameworks` skill for full formulas and templates. ### Instructions The user will provide a list of assumptions to prioritize. Apply the following framework: 1. **For each assumption**, evaluate two dimensions: - **Impact**: The value created by validating this assumption AND the number of customers affected (in ICE: Impact = Opportunity Score × # Customers) - **Risk**: Defined as (1 - Confidence) × Effort 2. **Categorize each assumption** using the Impact × Risk matrix: - **Low Impact, Low Risk** → Defer testing until higher-priority assumptions are addressed - **High Impact, Low Risk** → Proceed to implementation (low risk, high reward) - **Low Impact, High Risk** → Reject the idea (not worth the investment) - **High Impact, High Risk** → Design an experiment to test it 3. **For each assumption requiring testing**, suggest an experiment that: - Maximizes validated learning with minimal effort - Measures actual behavior, not opinions - Has a clear success metric and threshold 4. **Present results** as a prioritized matrix or table. Think step by step. Save as markdown if the output is substantial. --- ### Further Reading - [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas) - [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)
INPUTS
- $ARGUMENTS REQUIRED
target for prioritization (e.g. product or project name)
REQUIRED CONTEXT
- list of assumptions to prioritize
OPTIONAL CONTEXT
- files with assumptions or research data
ROLES & RULES
Role assignments
- You are helping prioritize assumptions for **$ARGUMENTS**.
- If the user provides files with assumptions or research data, read them first.
- Think step by step.
- Save as markdown if the output is substantial.
EXPECTED OUTPUT
- Format
- markdown
- Schema
- table
- Constraints
- present results as prioritized matrix or table
- suggest experiments for high-impact high-risk assumptions
SUCCESS CRITERIA
- Triage assumptions using an Impact × Risk matrix
- Suggest targeted experiments for each assumption
- Present results as a prioritized matrix or table
CAVEATS
- Dependencies
- Requires user-provided list of assumptions
- Requires files with assumptions or research data if provided
- Missing context
- Exact output format or template for the matrix/table
- How $ARGUMENTS placeholder is supplied at runtime
- Whether numeric scores must be produced or only qualitative categories
- Ambiguities
- Risk definition mixes (1-Confidence)×Effort but earlier text references ICE/RICE formulas without clear mapping.
- Does not specify desired output length or exact table columns.
- 'Save as markdown if the output is substantial' leaves 'substantial' undefined.
QUALITY
- OVERALL
- 0.76
- CLARITY
- 0.82
- SPECIFICITY
- 0.68
- REUSABILITY
- 0.85
- COMPLETENESS
- 0.72
IMPROVEMENT SUGGESTIONS
- Add a short example input list of assumptions and the expected table output.
- Replace or clarify the Risk formula to match the ICE/RICE references already mentioned.
- Specify required table columns (e.g., Assumption, Impact, Risk, Category, Experiment, Metric).
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Beachhead Market Segment Analyzeragentproduct
- UI/UX Design Intelligence Guideagentproduct
- Customer Journey Map Generatoragentproduct
- Agile User Stories Generator with 3Csagentproduct
- StyleSeed UX Flow Designeragentproduct
- StyleSeed UX Flow Designeragentproduct
- New Product Feature Ideationagentproduct
- Existing Product Trio Idea Brainstormeragentproduct
- Onboarding CRO Flow Designeragentproduct
- StyleSeed UI Design Token Manageragentproduct
- Product Requirements Document Drafteragentproduct
- JTBD Job Stories Generatoragentproduct
- Product Feature Backlog Prioritizeragentproduct
- Research Data User Persona Creatoragentproduct
- StyleSeed UX Flow and Screen Designeragentproduct
- Turkish Car Valuation Platform Designeragentproduct
- Opportunity Solution Tree Product Discoveryagentproduct
- Product Launch Pre-Mortem Risk Analyzeragentproduct
- Niche Domain Intelligence Report Generatoragentproduct
- StyleSeed UX Feedback Statesagentproduct
- Senior Product Manager Skills Agentagentproduct
- Prioritization Frameworks Reference Guideagentproduct
- Senior Product Manager Skills Agentagentproduct
- StyleSeed UX Feedback States Adderagentproduct
- Senior Product Manager Skills Agentagentproduct