recipe-discover
Skill7 starsChanged 3 months agoMITView on GitHub
Frames product Opportunities and creates decision-relevant hypotheses from available evidence. Use when exploring a problem, market opportunity, or user need.
In this repository15 other files it gives its agents.
- blueprint-standardsSkill
- business-contextSkill
- design-perspectiveSkill
- hypothesis-disciplineSkill
- prd-standardsSkill
- product-principlesSkill
- prototype-guideSkill
- recipe-blueprintSkill
- recipe-defineSkill
- recipe-personaSkill
- recipe-prototype-promptSkill
- recipe-refine-visualsSkill
- recipe-reflectSkill
- recipe-validateSkill
- recipe-visionSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
WHEN the request or available evidence raises a business-model, market, or viability decision: [LOAD IF NOT ACTIVE] business-context
- Distinctive: line 40
When business context can change the Opportunity decision, select the relevant business-context framework:
- Distinctive: line 46
Read the selected business-context reference for its decision boundary and evidence requirements.
- Distinctive: line 48
Web search: Use web search for market research — industry reports, competitor analysis, trend data.
- Very specific: line 54
Journey Mapping: Create a journey map using references/journey-template.md when sequence or handoff evidence is needed to locate the …
- Distinctive: line 61
3+ Solutions Test: Use the ability to identify meaningfully different Solutions as a diagnostic.
- Distinctive: line 85
Write the confirmed Opportunities and their decision-relevant hypotheses.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Context: Discover Opportunities and generate hypotheses by combining business analysis (BMC/VPC/market) with user analysis (JTBD/pains/gains). Outputs Opportunity files and hypothesis files.
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
hypothesis-discipline— hypothesis lifecycle, evidence, and stopping conditions - [LOAD IF NOT ACTIVE]
product-principles— Opportunity hierarchy, 4 Risks, and framing rules
Conditional Skills [LOAD WHEN TRIGGERED]
- WHEN the request or available evidence raises a business-model, market, or viability decision: [LOAD IF NOT ACTIVE]
business-context
Delegate code analysis when a separate repository reading can change the discovery decision.
Execution Decision Flow
1. Context Assessment
Input: Use the path or text supplied with the explicit skill invocation. If no input was supplied and the target cannot be inferred unambiguously, ask for it.
Assess the starting point:
| Situation | Action |
| Greenfield (no existing product) | Gather the business and user evidence needed to frame the requested outcome |
| Existing codebase | Invoke codebase-analyzer when current behavior can change the Opportunity framing |
| Specific market opportunity | Focus on market analysis + VPC |
| User feedback / support tickets | Focus on user analysis + journey mapping |
Vision exists (docs/product/vision.md) | Align discovery with Product Outcomes |
2. Business Context Analysis
When business context can change the Opportunity decision, select the relevant business-context framework:
- BMC: Understand the business model — especially Customer Segments, Value Propositions, Revenue Streams
- VPC: Map Customer Profile (jobs/pains/gains) to Value Map (products/pain relievers/gain creators)
- Market Analysis: TAM/SAM/SOM, competitive landscape, market gaps
Read the selected business-context reference for its decision boundary and evidence requirements.
Web search: Use web search for market research — industry reports, competitor analysis, trend data. Market research benefits from hypothesis context (unlike code analysis).
3. User Context Analysis
- Personas: Reference existing personas (
docs/product/personas/) or delegate to recipe-persona for full persona work - JTBD: Identify functional, social, and emotional jobs from VPC Customer Profile
- Journey Mapping: Create a journey map using
references/journey-template.mdwhen sequence or handoff evidence is needed to locate the Opportunity
4. Opportunity Identification
Synthesize business and user analysis into Opportunities:
- Draft Opportunity files using product-principles skill
references/opportunity-template.md - 3+ Solutions Test: Use the ability to identify meaningfully different Solutions as a diagnostic. If the framing supports fewer than three, report that signal without generating filler alternatives
- Link Opportunities to Product Outcomes (if vision exists)
- Assess impact (frequency x severity x breadth)
Present Opportunities to the user for the product-scope decision:
- Opportunity summaries with impact assessment
- Evidence supporting each Opportunity
- 3+ Solutions test results
- Recommended priority order
End the current turn with the Opportunity summaries as the workflow output. Generate hypotheses only for the Opportunities the user confirms in a later turn.
5. Hypothesis Generation
For confirmed Opportunities, generate hypotheses:
- Draft hypothesis files using hypothesis-discipline skill
references/hypothesis-template.md - Assign appropriate level (outcome / opportunity / solution / assumption)
- Set initial confidence scores (typically 0-2 for new hypotheses)
- Define a stopping condition; add a time budget or deadline only when it changes the validation decision
- Suggest validation methods
6. File Output
Write the confirmed Opportunities and their decision-relevant hypotheses. Create only the artifacts produced by this discovery:
- Opportunity files in
docs/discovery/opportunities/ - Hypothesis files in
docs/discovery/hypotheses/ - Journey maps in
docs/discovery/journeys/when journey evidence was required
Present the created hypotheses, proposed validation methods or stopping conditions, and recommended priority.
Sub-agent Usage
| Agent | When | Why (context separation benefit) |
| codebase-analyzer | Current implementation can change the Opportunity or persona decision | Objective fact-gathering without hypothesis bias |
Scope Boundaries
Included: Opportunity discovery, hypothesis generation, market research, journey mapping Not included: Hypothesis validation (→ recipe-validate), PRD creation (→ recipe-define), persona deep-dive (→ recipe-persona)
Completion
The workflow is complete when the confirmed Opportunities and their decision-relevant hypotheses exist, and the user has received the proposed validation methods, stopping conditions, and priority.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

