prototype
Build a throwaway prototype to flush out a design before committing. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates its purpose, provides concrete actions, and includes an explicit 'Use when...' clause with natural trigger phrases. The two-branch routing concept (terminal app vs. UI variations) is well-articulated. The only minor weakness is potential overlap with general UI design or scaffolding skills, though the prototyping focus helps differentiate it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: building a throwaway prototype, routing between two branches (runnable terminal app for state/business-logic questions, or radically different UI variations toggleable from one route). These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (build throwaway prototypes with two branches: terminal app or UI variations) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios and quoted user phrases). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'prototype', 'sanity-check', 'data model', 'state machine', 'mock up a UI', 'explore design options', 'prototype this', 'let me play with it', 'try a few designs'. Excellent coverage of natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | While the prototyping niche is fairly specific, terms like 'mock up a UI' and 'explore design options' could overlap with general UI design or wireframing skills. The 'throwaway prototype' framing and the two-branch routing approach help distinguish it, but there's still moderate overlap risk with UI generation or app scaffolding skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that efficiently routes between two distinct prototype types with clear decision criteria. Its main strength is the concise, opinionated rules that add genuine value beyond what Claude would default to. The primary weakness is the lack of concrete code examples or templates in the main file, though this may be addressed in the referenced LOGIC.md and UI.md files.
Suggestions
Add a brief concrete example of prototype file naming conventions (e.g., `prototype-checkout-flow.tsx` or `_prototype_state_machine.py`) to make rule #1 more actionable.
Include one minimal example command for each branch (e.g., `pnpm dev` with a URL, or `python prototype_checkout.py`) to make rule #2 concrete.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what prototyping is in general terms Claude would already know. Every rule earns its place by providing specific, non-obvious constraints (e.g., 'no persistence by default', 'surface the state'). The decision tree is tight and well-structured. | 3 / 3 |
Actionability | The skill provides clear decision criteria and concrete rules, but lacks executable code examples. The guidance is specific ('name it so a casual reader sees it's a prototype') but stops short of showing concrete file naming patterns, example commands, or template code. It delegates to LOGIC.md and UI.md for the actual implementation details. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced: identify the question → pick a branch → follow branch-specific guide → apply universal rules → capture the answer → delete. The decision tree for branch selection includes a fallback heuristic for ambiguous cases. The 'When done' section provides a clear exit procedure with knowledge capture. | 3 / 3 |
Progressive Disclosure | The SKILL.md serves as a clear overview and decision router, with well-signaled one-level-deep references to LOGIC.md and UI.md for branch-specific details. Content is appropriately split — universal rules stay in the main file while implementation specifics are delegated. Navigation is intuitive. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- belchman/claude-skills
- Commit
be88d6c
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.