recipe-blueprint
Skill7 starsChanged 3 months agoMITView on GitHub
Selects and defines the structural design context needed by a prototype or PRD. Use when shared information architecture, flows, content, brand, Visual Tokens, or AI interaction decisions are missing.
In this repository15 other files it gives its agents.
- blueprint-standardsSkill
- business-contextSkill
- design-perspectiveSkill
- hypothesis-disciplineSkill
- prd-standardsSkill
- product-principlesSkill
- prototype-guideSkill
- recipe-defineSkill
- 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
10 rules. About 0 are common, 3 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Context: Create or update structural design artifacts in docs/product/design/ so prototype generation and PRD authoring reuse the same …
- Very specific: line 17
WHEN the selected artifacts define user-facing states, persona-sensitive behavior, or accessibility boundaries: [LOAD IF NOT ACTIVE] …
- Very specific: line 18
WHEN the selected artifacts require state-design or product-confidence rules: [LOAD IF NOT ACTIVE] product-principles
- Distinctive: line 28
When missing evidence leaves the design outcome materially ambiguous, name the exact product decision required from the user.
- Distinctive: line 36
When navigation or task sequence affects the consumer, capture:
- Very specific: line 44
When entity shape or lifecycle affects the consumer, use references/content-model-template.md to define:
- Very specific: line 52
When visual consistency affects the consumer, use references/brand-direction-template.md to define:
- Very specific: line 60
When Visual Tokens are needed, derive them using the Derived From rules in the template and mark Source as auto-derived unless a design …
- Very specific: line 64
If AI behavior affects the current prototype or PRD, use references/ai-interaction-model-template.md to define:
- Distinctive: line 76
After that confirmation, write only the artifacts produced for the current consumer:
≈ “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: Create or update structural design artifacts in docs/product/design/ so prototype generation and PRD authoring reuse the same design context.
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
blueprint-standards— artifact selection and templates
Conditional Skills [LOAD WHEN TRIGGERED]
- WHEN the selected artifacts define user-facing states, persona-sensitive behavior, or accessibility boundaries: [LOAD IF NOT ACTIVE]
design-perspective - WHEN the selected artifacts require state-design or product-confidence rules: [LOAD IF NOT ACTIVE]
product-principles
A blueprint may contain any subset of the defined artifacts.
Execution Decision Flow
1. Context Reading
Identify the prototype or PRD decision that needs shared design context. Read only the available vision, principles, personas, Opportunities, journeys, and learnings that can change that decision.
When missing evidence leaves the design outcome materially ambiguous, name the exact product decision required from the user. Otherwise proceed with the available evidence and mark the assumption in the affected artifact.
2. IA and Key Flow Definition
Use blueprint-standards references:
references/ia-template.mdreferences/flow-template.md
When navigation or task sequence affects the consumer, capture:
- page hierarchy
- navigation model
- labeling and taxonomy
- the critical user flows needed by the consumer, with entry, success, and relevant recovery paths
3. Content Model Definition
When entity shape or lifecycle affects the consumer, use references/content-model-template.md to define:
- core entities
- relationships
- lifecycle states when relevant
- where those entities appear in the product
4. Brand Direction and Visual Tokens
When visual consistency affects the consumer, use references/brand-direction-template.md to define:
- tone and voice
- color and typography direction
- motion and density choices
- reference products
- Visual Tokens for prototype consistency
Visual Tokens are concrete prototype values, not final production tokens.
When Visual Tokens are needed, derive them using the Derived From rules in the template and mark Source as auto-derived unless a design expert later refines the values.
5. AI Interaction Model
If AI behavior affects the current prototype or PRD, use references/ai-interaction-model-template.md to define:
- interaction patterns
- disclosure and confidence communication
- guardrails
- error taxonomy
Present the blueprint decisions that were created to the user for confirmation.
End the current turn with the blueprint draft as the workflow output. Write artifacts only after the user confirms those decisions in a later turn.
6. File Output
After that confirmation, write only the artifacts produced for the current consumer:
docs/product/design/information-architecture.mdwhen IA was neededdocs/product/design/content-model.mdwhen a content model was neededdocs/product/design/brand-direction.mdwhen brand direction or Visual Tokens were neededdocs/product/design/ai-interaction-model.mdwhen AI interaction decisions were neededdocs/product/design/flows/flow-{name}.mdfor each required flow
Scope Boundaries
Included: structural design artifacts for reusable prototype and PRD context Not included: pixel-perfect specs, final production design system, implementation details
Completion
The workflow is complete when the confirmed artifacts needed by the current consumer exist, or a no-change result identifies the reusable artifacts and any unresolved design 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.

