prototype-guide
/prototype-guide
Defines evidence-grounded prototype quality and external-generator prompt construction. Use when generating or evaluating a prototype, or exporting a prompt for Lovable, v0, or a similar tool.
- Author
- shinpr ↗
- Repository
- nautilus ↗
- Licence
- MIT
- Last repository change
- 23.10.2026
Assessment and security
- Files in this package
- 5
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 23.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Defines evidence-grounded prototype quality and external-generator prompt construction. Use when generating or evaluating a prototype, or exporting a prompt for Lovable, v0, or a similar tool.
Original author description
Defines evidence-grounded prototype quality and external-generator prompt construction. Use when generating or evaluating a prototype, or exporting a prompt for Lovable, v0, or a similar tool.
How it works
- Purpose
- Required Context
- Shared Prototype Contract
- Reference Routing
- Scope Boundary
SKILL.md preview
--- name: prototype-guide description: Defines evidence-grounded prototype quality and external-generator prompt construction. Use when generating or evaluating a prototype, or exporting a prompt for Lovable, v0, or a similar tool. --- # Prototype Guide ## Purpose A prototype makes one product decision observable before delivery. Apply product evidence and design decisions that affect that observation; leave unrelated implementation choices to the generator. ## Required Context Start from: 1. the hypothesis and its success/failure criteria; 2. the persona and scenario when they change behavior or evaluation; 3. the product and design sources selected by `references/prototype-quality.md`. Classify a missing input as blocking only when it controls the tested flow or interpretation. Name the missing decision and the evidence that would resolve it. ## Shared Prototype Contract - Focus on one validation decision. Combine hypotheses only when the same interaction and evidence resolve them together. - Make the critical flow, consequences, and relevant recovery behavior observable. - Use domain-realistic content and data rather than generic placeholders. - Apply the highest-priority available design source instead of re-inferring existing decisions. - Implement the states that can occur and affect the validation decision. Report each implemented trigger and any non-obvious exclusion whose absence could change evaluation. - Keep the visible UI product-native; carry test setup and evaluation evidence in the completion report. - Preserve the artifacts needed to evaluate, reproduce, or reuse the result. ## Reference Routing - WHEN generating or evaluating a prototype artifact: read `references/prototype-quality.md` and apply every applicable criterion. - WHEN exporting a prompt for an external generator: also read `references/prototype-prompt-guide.md` and the selected platform template. - WHEN product-specific usability, persona, state, or accessibility decisions are needed: load `design-perspective`. ## Scope Boundary This skill owns prototype quality and prompt construction. `recipe-validate` owns the validation lifecycle and hypothesis record. `recipe-prototype-prompt` owns explicit external prompt export. The prototype generator owns the HTML artifact.
Files in this package (5)
- SKILL.md 2 KB
- references/lovable-template.md 4 KB
- references/prototype-prompt-guide.md 8 KB
- references/prototype-quality.md 6 KB
- references/v0-template.md 4 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · shinpr/nautilus | 90 | MIT |
| shinpr/claude-code-discover | 90 | MIT |
Database snapshot: 13.11.2026 · package version f312aef45fbe (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90recipe-prototype-prompt
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. - 90prototype-design-interview
Guide a user from a vague idea to a buildable prototype design through structured interview questioning, then emit DESIGN_SPEC.md + PROMPT.md and hand off to prototype-workflow. Use this skill whenever the user wants a prototype but cannot yet describe it — e.g.… - 91lovable
Read, create, edit, and deploy web apps and projects in Lovable. Use to turn a product brief into a working website or prototype, inspect existing project code, update pages and features, and publish changes through Lovable's official MCP server. - 100ai-prototype
Turns an idea into a working, user-testable prototype with AI builders (Lovable, v0, Bolt, Replit, Cursor, Claude Code) and gets you unstuck when the tool breaks. Produces a Prototype Brief with a build-prompt pack, a debugging log and a user-test plan. Use for 'vibe coding',… - 100uxd-prototype-export
Export a prototype page or journey step as static HTML, a React component tree, or a PatternFly implementation spec, and install the Prototype Bar (Sources, Prototype|Eval, State, Export). Use when capturing the current view, batch-exporting journey screens and page scenarios,… - 100arn-spark-prototype-lock
This skill should be used when the user says "prototype lock", "lock prototype", "arn prototype lock", "freeze prototype", "preserve prototype", "snapshot prototype", "protect prototype", "archive prototype", "save the prototype", "don't overwrite the prototype", "lock the…