CtrlK
BlogDocsLog inGet started
Tessl Logo

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

1.78x
Quality

Does it follow best practices?

Impact

91%

1.78x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

88%

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

A tight, highly actionable skill body — lean spec table, executable code, and a closing checklist — with no token waste. Its only gap is the absence of an explicit validate-the-output checkpoint in the generation workflow, which caps workflow clarity.

Suggestions

Add an explicit validation step to the generation workflow — e.g., after generating, fetch the URL or run the Twitter Card Validator and confirm the preview renders before declaring done — to lift workflow_clarity to 3.

The checklist's validator link (cards-dev.twitter.com) is a deprecated Twitter endpoint; mark it as a legacy option and point to X's current validator tooling to avoid a dead reference.

Clarify the Express example's image handling: `new ImageResponse(/* ... */)` is pseudocode and `image.arrayBuffer()` does not exist on ImageResponse; show the real await/render path so the snippet is copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — a compact spec table, the zero-width-space trick, minimal code blocks, and a checklist — with no padding explaining what an OG image or X card is.

3 / 3

Actionability

Provides copy-paste-ready meta tags, a complete @vercel/og handler with exact dimensions and padding, an Express example, and pre-generation code; all concrete and executable.

3 / 3

Workflow Clarity

Two dynamic-route approaches are sequenced with a risk callout and recommendation, and a checklist closes the loop, but there is no explicit validation/verification checkpoint (e.g., test the rendered card) for the batch/destructive-ish generation steps, capping it at 2.

2 / 3

Progressive Disclosure

Under 50 lines, single-purpose, no external references or bundle files needed; well-organized sections (specs, trick, tags, generation, routes, checklist) per the simple-skills note.

3 / 3

Total

11

/

12

Passed

Description

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.

The description is concise, concrete, and trigger-rich — it names a specific artifact (X/Twitter image-style cards), gives a clear differentiator (images not banners), and lists natural use-when phrases. It cleanly answers both what and when with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and specifics: 'Create X/Twitter cards that look like images, not marketing banners' plus exact trigger phrases, naming a concrete artifact type and a clear visual constraint rather than vague language.

3 / 3

Completeness

Explicitly states what it does ('Create X/Twitter cards that look like images, not marketing banners') and when to use it ('Use when asked to...'), answering both what and when.

3 / 3

Trigger Term Quality

Provides natural phrasings users would say — 'create OG images', 'set up X cards', 'make social cards', 'twitter card without text' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Narrow X/Twitter social-card niche with distinct image-not-banner framing and specific triggers, making it unlikely to fire for unrelated skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NeverSight/skills_feed
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.