prototype-prompt-generator

This skill should be used when users need to generate detailed, structured prompts for creating UI/UX prototypes. Trigger when users request help with "create a prototype prompt", "design a mobile app", "generate UI specifications", or need comprehensive design documentation for web/mobile applications. Works with multiple design systems including WeChat Work, iOS Native, Material Design, and Ant Design Mobile.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, well-validated workflow and real reference files. Its weaknesses are verbosity from restating general UI knowledge and inline duplication of content that already lives in the reference files.

Suggestions

Trim the Common Patterns and Best Practices sections to design-system-specific details Claude would not already know, or defer them to references/design-systems.md.

Replace the inline 9-section prompt-structure detail in Step 3 with a brief summary that points to references/prompt-structure.md for the full template, keeping SKILL.md a lean overview.

Cut general-knowledge reminders (safe areas, 44px touch targets, Material elevation) that duplicate what is in the design-systems reference.

Dimension	Reasoning	Score
Conciseness	The ~497-line body is mostly efficient in the core workflow, but Best Practices and Common Patterns restate general UI knowledge Claude already has (Material elevation/ripples, iOS safe areas, 44px touch targets) and Step 3 duplicates the prompt-structure reference inline, fitting the 'mostly efficient but includes unnecessary explanation' anchor rather than the lean score-3 anchor.	2 / 3
Actionability	Provides concrete code blocks (Tailwind config), fillable prompt templates, and specific ❌/✅ replacements with exact hex codes and px values, matching the 'fully executable... copy-paste ready' anchor rather than the pseudocode anchor at 2.	3 / 3
Workflow Clarity	A clearly sequenced 6-step workflow includes explicit validation checkpoints (the Step 5 quality-assurance checklists) and a feedback loop (Step 6 iterate then re-verify against the checklist), matching the 'clear sequence with explicit validation steps; feedback loops' anchor rather than the missing-checkpoints anchor at 2.	3 / 3
Progressive Disclosure	Both references are real, one level deep, and well signaled with 'When to reference' notes, but the body duplicates substantial reference content inline (the full 9-section prompt structure and the Common Patterns) instead of staying a lean overview, fitting the 'content that should be separate is inline' anchor rather than the appropriately-split score-3 anchor.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is strong overall, clearly stating what the skill does and when to trigger it with natural user phrasing and named design systems. Its main weakness is a broad trigger ('design a mobile app') that risks overlap with skills that build actual apps rather than generate prototype prompts.

Suggestions

Tighten the 'design a mobile app' trigger to something scoped to prompt/spec generation (e.g., 'generate a prototype prompt for a mobile app') to reduce conflict with actual app-design skills.

Lead with the core action in third person (e.g., 'Generates detailed, structured prompts...') before the trigger clause to keep the what/when split crisp.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('generate detailed, structured prompts', 'generate UI specifications', 'comprehensive design documentation') and names four specific design systems, matching the 'multiple specific concrete actions' anchor rather than the partial-coverage anchor at 2.	3 / 3
Completeness	Clearly states the 'what' (generate structured prompts for UI/UX prototypes) and an explicit 'when' trigger clause ('Trigger when users request help with...'), satisfying the both-what-and-when anchor rather than the implied-when anchor at 2.	3 / 3
Trigger Term Quality	Explicit quoted phrases users would naturally say ('create a prototype prompt', 'design a mobile app', 'generate UI specifications') give good coverage of natural terms, matching the score-3 anchor rather than the 'some relevant keywords' anchor at 2.	3 / 3
Distinctiveness Conflict Risk	The trigger 'design a mobile app' is broad and would also fire for users wanting an actual app designed or built, creating overlap with general design/build skills; it is somewhat specific but not clearly conflict-free, fitting the score-2 anchor rather than the distinct-niche anchor at 3.	2 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stellarlinkco/myclaude
Path: skills/prototype-prompt-generator/SKILL.md
Commit: f2e75c1

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.