design-prompt-generator-v2
Advanced 7-step hierarchical design prompt generator for AI web development tools (Lovable, Cursor, Bolt). Generates domain-aware, user-journey-based design prompts with emotional design considerations. Triggers on "디자인 프롬프트", "웹 디자인", "Lovable 프롬프트", "랜딩페이지 만들어줘", or any AI web builder prompt requests.
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 description has strong completeness with explicit trigger terms and clear 'when to use' guidance. The main weakness is the use of buzzword-heavy language ('7-step hierarchical', 'emotional design considerations') that sounds impressive but doesn't convey concrete actions. The Korean trigger terms and specific tool names provide excellent distinctiveness.
Suggestions
Replace abstract terms like '7-step hierarchical' and 'emotional design considerations' with concrete actions (e.g., 'creates landing page layouts, defines user flows, specifies color schemes and typography')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI web development tools) and mentions some actions ('generates domain-aware, user-journey-based design prompts'), but the specific capabilities are described with buzzwords like 'hierarchical', '7-step', and 'emotional design considerations' rather than concrete actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (generates design prompts for AI web development tools) and 'when' with explicit 'Triggers on' clause listing specific trigger phrases and conditions. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms in both Korean ('디자인 프롬프트', '웹 디자인', 'Lovable 프롬프트', '랜딩페이지 만들어줘') and English references to specific tools (Lovable, Cursor, Bolt), covering natural variations users would say. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting AI web builder prompt generation with named tools (Lovable, Cursor, Bolt) and Korean-language triggers, making it highly unlikely to conflict with other 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 is a well-structured, highly actionable skill for generating design prompts with clear sequential workflow and concrete templates. The 7-step framework provides excellent guidance with specific examples and fill-in templates. Main weaknesses are moderate verbosity in reference tables and lack of content splitting for this longer skill file.
Suggestions
Consider moving the domain-specific pattern tables (Step 1) and emotional keyword matrix (Step 3) to separate reference files to reduce main skill length
Condense the component specs section by providing one detailed example and noting that the same pattern applies to other components
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy in the domain pattern tables and template structures. While mostly efficient, some sections like the emotional design matrix could be more condensed without losing utility. | 2 / 3 |
Actionability | Provides highly concrete, copy-paste ready templates with specific formats, tables, and structured outputs. The 7-step framework with explicit templates, example values, and fill-in-the-blank structures makes this immediately actionable. | 3 / 3 |
Workflow Clarity | Clear 7-step sequential framework with explicit progression from domain research through micro-interactions. Each step builds on previous ones, and the quality checklist at the end provides validation checkpoints. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers and logical flow, but everything is in a single monolithic file. For a skill of this length (~300 lines), some content like domain-specific patterns or component templates could be split into reference files. | 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.
- Repository
- bear2u/my-skills
- Commit
1be5394
- 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.