banner-creator
Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner.
93
92%
Does it follow best practices?
Impact
92%
1.80xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 what the skill does (AI-powered banner creation with iterative workflow) and when to use it (with an explicit 'Use when' clause containing diverse, natural trigger terms). The description is concise yet comprehensive, listing specific workflow steps and covering multiple common banner types users might request.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: discuss format/style, generate variations, iterate with user feedback, crop to target ratio. These are clear, actionable steps in the banner creation workflow. | 3 / 3 |
Completeness | Clearly answers both 'what' (create banners using AI image generation with discussion, variations, iteration, and cropping) and 'when' (explicit 'Use when' clause listing multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'banner', 'header', 'hero image', 'cover image', 'GitHub banner', 'Twitter header', 'readme banner'. These are specific, varied, and match real user language. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on banner/header image creation. The specific trigger terms like 'GitHub banner', 'Twitter header', 'hero image' clearly distinguish it from general image generation or design skills. | 3 / 3 |
Total | 12 / 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 with clear, actionable workflows and good progressive disclosure. The 6-step process is logical with appropriate validation checkpoints (user confirmation, iteration loops). Minor verbosity in the discovery section and some explanatory content that Claude wouldn't need slightly reduce token efficiency, but overall the skill is effective and practical.
Suggestions
Tighten Step 1 (Discovery) by condensing the style/color/content lists into a compact format rather than expanded bullet lists — Claude can ask these questions naturally without such detailed prompting.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity, such as the detailed list of style preferences and color preferences that Claude could infer. The prompt pattern templates and common targets are useful additions, but the discovery section could be tighter. | 2 / 3 |
Actionability | Provides fully executable commands for each step including generation, batch generation, cropping, and preview creation. Commands include specific flags, naming conventions, and concrete examples with placeholder patterns that are easy to fill in. | 3 / 3 |
Workflow Clarity | Clear 6-step sequential workflow with explicit checkpoints: wait for user confirmation after discovery, iterate with user feedback loop (generate → preview → feedback → regenerate), and only crop after user approval. The feedback loop for iteration is well-defined. | 3 / 3 |
Progressive Disclosure | Well-structured with a clear overview workflow in the main file, references to external files for formats (references/formats.md) and examples (examples/opc-banner-creation.md), and a quick reference section at the bottom. References are one level deep and clearly signaled. | 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
- resciencelab/opc-skills
- Commit
0c048af
- 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.