x-image-cards
Create X/Twitter cards that look like images, not marketing banners. Use when asked to "create OG images", "set up X cards", "make social cards", or "twitter card without text".
93
Quality
95%
Does it follow best practices?
Impact
91%
1.78xAverage score across 6 eval scenarios
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 well-crafted description with excellent trigger terms and completeness. The explicit 'Use when...' clause with multiple natural user phrases makes it highly discoverable. The main weakness is that the capability description could be more specific about what actions are performed beyond 'create'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (X/Twitter cards) and describes the style ('look like images, not marketing banners'), but doesn't list multiple concrete actions like creating, configuring, or specific technical capabilities. | 2 / 3 |
Completeness | Clearly answers both what (create X/Twitter cards that look like images) and when (explicit 'Use when...' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'create OG images', 'set up X cards', 'make social cards', 'twitter card without text' - these are realistic user phrases covering multiple variations. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche - X/Twitter cards with a particular aesthetic style. The trigger terms are distinct ('OG images', 'X cards', 'twitter card') and unlikely to conflict with general image or design skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill that demonstrates excellent token efficiency while providing complete, actionable guidance. It assumes Claude's competence with web development concepts, provides copy-paste ready code, and includes a practical checklist for validation. The zero-width space trick and crawler timeout warning add genuine value that Claude wouldn't know otherwise.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every section delivers specific, actionable information without explaining what X cards are or how meta tags work. The table format for specs is particularly token-efficient. | 3 / 3 |
Actionability | Fully executable code examples for multiple frameworks (Vercel OG, Express), complete meta tag snippets ready to copy-paste, and specific values (2400×1200, 50-56px margins) rather than vague guidance. | 3 / 3 |
Workflow Clarity | Clear checklist at the end serves as validation. The two approaches for dynamic routes are well-sequenced with explicit tradeoffs (timeout risk vs instant response). The skill is appropriately simple and doesn't require complex multi-step validation. | 3 / 3 |
Progressive Disclosure | Well-organized sections from specs to implementation to optional advanced features. Content is appropriately sized for a single file without needing external references. Clear section headers enable quick navigation. | 3 / 3 |
Total | 12 / 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
- NeverSight/skills_feed
- Commit
5342bca
- 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.