recipe-define
Skill7 starsChanged 3 months agoMITView on GitHub
Creates a delivery-ready PRD from validated hypotheses with material 4 Risks evidence and necessary traceability. Use when turning validation results into requirements or user stories.
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-discoverSkill
- 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
9 rules. About 0 are common, 5 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
WHEN the PRD contains user-facing interaction, Design Context, or accessibility requirements: [LOAD IF NOT ACTIVE] design-perspective
- Distinctive: line 30
Read relevant Opportunity and hypothesis files
- Distinctive: line 32
Check confidence against the product-principles cost, risk, and reversibility criteria
- Distinctive: line 38
All key hypotheses validated enough → Proceed to PRD drafting
- Very specific: line 46
Use prd-standards skill references/prd-template.md to create the PRD:
- Very specific: line 57
Use prd-standards skill references/user-story-guide.md for the user stories:
- Distinctive: line 59
Write in persona-grounded format (As a [persona name], I want to...)
- Distinctive: line 62
Document a remaining risk at story level only when it differs from the shared assessment
- Very specific: line 83
Write PRD to docs/prd/[feature-name]-prd.md
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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: Transform validated hypotheses into a PRD with 4 Risks confidence scores, hypothesis traceability, and user stories. The PRD follows a standard structure that can be consumed by downstream implementation workflows.
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
prd-standards— PRD structure, user stories, and acceptance criteria - [LOAD IF NOT ACTIVE]
product-principles— 4 Risks, confidence thresholds, and MVP scope
Conditional Skills [LOAD WHEN TRIGGERED]
- WHEN the PRD contains user-facing interaction, Design Context, or accessibility requirements: [LOAD IF NOT ACTIVE]
design-perspective
Delegate the completed draft to doc-reviewer for bias-free quality assessment before asking for final product approval.
Execution Decision Flow
1. Readiness 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 whether hypotheses are "validated enough" for PRD creation:
- Read relevant Opportunity and hypothesis files
- For each hypothesis intended for the PRD:
- Check confidence against the product-principles cost, risk, and reversibility criteria
- Assess cost x risk x reversibility
- Determine: validated enough / needs more validation
- See product-principles skill
references/mvp-definition.mdfor scope determination
Decision:
- All key hypotheses validated enough → Proceed to PRD drafting
- Some hypotheses below threshold → Present to user with options:
- Lower threshold (add risk mitigation like feature flags)
- Validate further (→ recipe-validate)
- Proceed with documented remaining risks
2. PRD Drafting
Use prd-standards skill references/prd-template.md to create the PRD:
- Overview: Link to Opportunity and validated hypotheses
- User Stories: Record material 4 Risks evidence at the smallest scope that changes delivery readiness
- Functional Requirements: Derive from validated hypotheses with testable ACs. Use EARS patterns when they clarify the trigger, state, or condition. Assign stable AC IDs when an implementation, test, or planning consumer references individual ACs; keep criteria unnumbered when no such consumer exists
- Design Context: Include the project design decisions and validation artifacts needed by delivery; link the source instead of copying unrelated sections
- Success Criteria: Tie to Product Outcomes from
docs/product/vision.md - Assumptions (Unvalidated): Explicitly list hypotheses NOT yet validated that the PRD proceeds with
3. User Story Generation
Use prd-standards skill references/user-story-guide.md for the user stories:
- Write in persona-grounded format (As a [persona name], I want to...)
- Assess the risk dimensions that can change the story's delivery decision, reusing shared evidence instead of repeating it
- Determine delivery readiness per story
- Document a remaining risk at story level only when it differs from the shared assessment
4. Quality Review
Invoke doc-reviewer for bias-free assessment:
- doc-reviewer operates in a separate context
- It checks: completeness, internal consistency, evidence backing
- It identifies gaps the author might have missed
For each finding:
- apply it when it corrects an approved requirement, accepted decision, repository rule, observable correctness, or necessary evidence;
- decline it with evidence when it adds scope, reverses an exclusion, duplicates proof, or has no justified effect on the PRD consumer; or
- return it to the user when resolving it changes the product outcome or a major approved decision.
Re-run doc-reviewer only when an applied change can invalidate its assessment. Present the reviewed PRD, remaining risks, declined findings, and approval recommendation to the user for final product approval.
End the current turn with the reviewed draft as the workflow output. Write the PRD only after the user confirms that draft in a later turn.
5. File Output
After that confirmation:
- Write PRD to
docs/prd/[feature-name]-prd.md
Sub-agent Usage
| Agent | When | Why (context separation benefit) |
| doc-reviewer | PRD quality review | Eliminates author's self-review bias |
PRD Structure
The PRD uses the sections and nautilus extensions needed by its delivery consumer and is stored in docs/prd/. Shared evidence belongs at feature scope; story sections contain only story-specific decisions or differences.
Scope Boundaries
Included: PRD creation, user story generation, quality review Not included: Hypothesis validation (→ recipe-validate), Design Doc/ADR creation, implementation
Completion
The workflow is complete when the confirmed PRD exists at its target path and the user has received the remaining risks, declined findings, and any unresolved product decision.
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.

