Guides Claude from idea to working prototype using frameworks from OpenAI, Figma, and Airbnb. Use when starting new product features, planning MVP scope, making build-vs-buy decisions, or guiding users from concept to shippable prototype. Applies AI-first thinking (Kevin Weil), simplicity forcing functions (Dylan Field), and complete experience design (Brian Chesky).
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 description with excellent trigger terms and completeness. The explicit 'Use when...' clause covers multiple relevant scenarios, and the named frameworks/thought leaders create distinctiveness. The main weakness is that the actual capabilities are somewhat abstract (guiding, planning, deciding) rather than concrete deliverables.
Suggestions
Add specific concrete outputs like 'creates product requirement documents', 'generates feature prioritization matrices', or 'produces MVP scope documents' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (product development/prototyping) and references frameworks and thought leaders, but the actual concrete actions are somewhat vague - 'guides', 'planning', 'making decisions' are process-oriented rather than specific deliverables like 'creates PRDs' or 'generates wireframes'. | 2 / 3 |
Completeness | Clearly answers both what (guides from idea to prototype using specific frameworks) and when (explicit 'Use when...' clause covering starting features, MVP planning, build-vs-buy decisions, concept-to-prototype work). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'new product features', 'MVP scope', 'build-vs-buy', 'prototype', 'concept to shippable'. These are phrases product managers and developers naturally use when starting projects. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific framework attributions (OpenAI, Figma, Airbnb) and named thought leaders (Kevin Weil, Dylan Field, Brian Chesky). The combination of product strategy + specific methodologies creates a clear niche unlikely to conflict with generic coding or design skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides strong actionable guidance with excellent templates, checklists, and decision frameworks for product development. However, it's overly verbose with unnecessary explanations, extensive quotes, and real-world examples that pad the content without adding proportional value. The structure is good but the file would benefit from being more concise and splitting detailed examples into reference files.
Suggestions
Remove or drastically shorten the 'Real-World Examples from Episodes' section - Claude doesn't need case study narratives to apply the frameworks
Cut the 'Key Quotes from Episodes' section entirely - the quotes are already embedded where relevant in the frameworks
Move the detailed framework explanations to reference files and keep only the actionable templates and checklists in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful frameworks but is verbose with explanatory text Claude doesn't need (e.g., explaining what simplicity means, extensive context about the source leaders). The quotes and real-world examples add bulk without proportional value. | 2 / 3 |
Actionability | Provides concrete templates, checklists, decision trees, and specific examples with clear apply-this-framework patterns. The MVP Scope Definition template and Build Decision Framework table are copy-paste ready and actionable. | 3 / 3 |
Workflow Clarity | Clear decision tree for sequencing, explicit checklists for before/during/after build phases, and well-structured templates guide Claude through the multi-step process from idea to prototype with clear checkpoints. | 3 / 3 |
Progressive Disclosure | References external files (references/kevin-weil-openai.md, etc.) appropriately, but the main file itself is monolithic with extensive inline content that could be split. The 'Related Skills' section is good but the core content is too long. | 2 / 3 |
Total | 10 / 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.
53530ef
Table of Contents
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.