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".
90
88%
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 strong description with excellent trigger terms and completeness. It clearly identifies its niche (X/Twitter social cards) and provides explicit 'Use when' guidance with natural user phrases. The main weakness is that the 'what' portion could be more specific about the concrete actions involved beyond just 'create'.
Suggestions
Expand the capability description with more concrete actions, e.g., 'Create X/Twitter cards with proper meta tags, image sizing, and preview optimization that look like images, not marketing banners.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (X/Twitter cards) and gives a qualitative distinction ('look like images, not marketing banners'), but it doesn't list multiple concrete actions like 'generate image tags, configure meta tags, set card dimensions'. The 'what' is a single action: create cards. | 2 / 3 |
Completeness | Clearly answers both 'what' (create X/Twitter cards that look like images) and 'when' (explicit 'Use when' clause with four specific trigger phrases). The when clause is explicit and well-structured. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'OG images', 'X cards', 'social cards', 'twitter card without text'. These are phrases users would naturally say, covering multiple common variations including both 'X' and 'Twitter' naming conventions. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — X/Twitter cards specifically, with the added qualifier of image-like rather than marketing banners. The trigger terms are specific enough ('OG images', 'X cards', 'twitter card without text') to avoid conflicts with general image creation or web development skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, well-structured skill that provides genuinely useful, non-obvious knowledge (zero-width space trick, crawler timeout risks, 2x retina scaling). The content is lean and actionable with executable code examples for multiple frameworks. The only weakness is the lack of an explicit validation workflow integrating the Twitter card validator into a step-by-step testing process.
Suggestions
Expand the checklist into a brief validation workflow: e.g., '1. Deploy → 2. Test with cards-dev.twitter.com/validator → 3. If blank preview, check crawler timeout / image URL extension → 4. Verify on mobile for edge clipping'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place — the table format for specs is efficient, code examples are minimal but complete, and there's no explanation of what OG tags or X cards are (assumes Claude knows). The zero-width space trick and crawler timeout warning are genuinely non-obvious knowledge. | 3 / 3 |
Actionability | Provides fully executable code for both Vercel OG and Express approaches, complete HTML meta tags ready to copy-paste, specific pixel values, and even the exact zero-width space HTML entity and JSX syntax. The dynamic routes section includes concrete implementation patterns. | 3 / 3 |
Workflow Clarity | The checklist at the end provides a good verification step, and the two dynamic route approaches are clearly compared with tradeoffs. However, there's no explicit validation workflow — no 'generate → validate dimensions → test with Twitter validator → deploy' sequence with feedback loops. The Twitter card validator is mentioned only as a checklist item, not integrated into a verification step. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~80 lines of meaningful content), the structure is excellent: specs table up front, then the key trick, then meta tags, then dynamic generation with optional advanced patterns. Content is well-organized with clear headers and the optional section is explicitly marked. No need for external file references at this length. | 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
- NeverSight/skills_feed
- Commit
f772de4
- 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.