recipe-prototype-prompt
Skill7 starsChanged 3 months agoMITView on GitHub
Exports an evidence-grounded prompt for Lovable, v0, or a similar external prototype generator. Use when the desired artifact is a reusable generator prompt rather than an internally generated HTML prototype.
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-discoverSkill
- recipe-personaSkill
- recipe-refine-visualsSkill
- recipe-reflectSkill
- recipe-validateSkill
- recipe-visionSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Use the hypothesis path and target platform supplied with the explicit skill invocation.
- Distinctive: line 22
Read the target hypothesis and extract the decision under test, scenario, and observable success/failure criteria.
- Very specific: line 23
Read the loaded prototype-guide skill's references/prototype-quality.md and acquire only product/design sources that can change the …
- Very specific: line 24
Read the loaded prototype-guide skill's references/prototype-prompt-guide.md and the selected platform template when one exists.
- Very specific: line 26
Write the machine-executable prompt to docs/discovery/prototypes/hypo-{id}-{platform}-prompt.md.
≈ “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
Prototype Prompt Export
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
prototype-guide— prototype quality and external prompt construction - [LOAD IF NOT ACTIVE]
design-perspective— product design decisions, persona context, and accessibility
Input
Use the hypothesis path and target platform supplied with the explicit skill invocation. If either cannot be inferred unambiguously, ask for the missing value.
Process
- Read the target hypothesis and extract the decision under test, scenario, and observable success/failure criteria.
- Read the loaded
prototype-guideskill'sreferences/prototype-quality.mdand acquire only product/design sources that can change the generated prototype or its evaluation. - Read the loaded
prototype-guideskill'sreferences/prototype-prompt-guide.mdand the selected platform template when one exists. - Materialize the decision-relevant product, design, component, and data context in the prompt unless the target generator has verified repository access.
- Write the machine-executable prompt to
docs/discovery/prototypes/hypo-{id}-{platform}-prompt.md.
Output Contract
Return the prompt path, target platform, decision under test, and source paths used. Source paths provide traceability and become generator instructions only when the target has verified access to them. The prompt contains only instructions consumed by the external generator; add a separate guide only when a named human consumer needs information that would degrade the executable prompt.
Scope Boundary
This recipe does not generate the HTML prototype, execute validation, or update the hypothesis record. Use recipe-validate for the context-separated generation and validation lifecycle.
Completion
The workflow is complete when docs/discovery/prototypes/hypo-{id}-{platform}-prompt.md exists at the reported path and its content carries the applicable prototype quality criteria and decision-relevant product context.
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.

