card-twitter

Twitter quote or data card designed to pair with a post.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/card-twitter/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

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

The body is an exemplar of lean template specification: every token is a concrete, buildable design instruction with zero filler. The only gaps are minor — no starter markup or explicit color/typography values, and a couple of implicit decisions (light/dark choice, avatar placeholder) that keep actionability and workflow clarity just below perfect.

Dimension	Reasoning	Score
Conciseness	Every line is a concrete design token — `w-[1600px] h-[900px]`, "text-6xl, font-semibold, 限 2-3 行", "grid 网格 / noise / dot pattern", element placements (左上角标签, 右下角水印) — with no concept explanations or padding. Lean and efficient; assumes Claude's competence.	5 / 5
Actionability	Concrete, buildable guidance: exact container dimensions, Tailwind classes, line limits, tag enums ("Insight" / "Data" / "Quote"), and texture options. Score 5 is withheld because there is no starter markup or example HTML, and key details like the color palette and font family are left implicit; not 3 because the guidance is specific and directly executable for a design task rather than pseudocode.	4 / 5
Workflow Clarity	A simple, single-purpose skill where the bullet checklist makes the one action (produce the card) largely unambiguous, per the simple-skill exception. Score 5 is withheld because a few decisions are left implicit — dark vs. light "根据内容情绪", the avatar is a bare "占位", and the output format (HTML per the frontmatter preview) is never stated in the body; not 3 because no risky or batch operations exist that would require validation checkpoints.	4 / 5
Progressive Disclosure	The skill is 8 lines, single-purpose, references no external files, and no bundle directories exist — nothing needs splitting out, and the single coherent list is well-organized for this size. The simple-skill exception applies: under 50 lines with no need for external references, well-organized content scores 5.	5 / 5
	Total	18 / 20 Passed

Description

48%Weight 40%Scale 1-5

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 states a clear, distinct artifact (a Twitter quote/data card) but reads as a product tagline rather than a capability description: it lists no actions, includes no use-when trigger guidance, and misses the most natural user phrasing ("tweet"). It is serviceable but below the standard of the good examples, which pair an action list with explicit triggers.

Suggestions

Add concrete capabilities to the description, e.g. "Creates a 1600×900 Twitter quote or data card from user content, with hero quote, author attribution, category tag, and brand watermark" — currently no actions are listed at all.

Append an explicit trigger clause such as "Use when the user wants a tweet-ready share image, social media card, or Twitter/X graphic for their post" — the missing when-clause currently caps completeness at 3.

Include natural synonyms users would say — "tweet", "X", "share image", "social media graphic" — rather than only "Twitter" and "post".

Dimension	Reasoning	Score
Specificity	"Twitter quote or data card designed to pair with a post" names the artifact type but lists no concrete actions — "designed to pair with a post" is descriptive filler rather than a capability. It fits anchor 2 (names the domain, actions minimal/generic); score 3 would require 1-2 concrete actions, which are absent.	2 / 5
Completeness	The "what" is clear (a Twitter quote or data card paired with a post), but there is no "when" — no "Use when..." clause or equivalent trigger guidance, which the guidelines cap at 3. Not 4 because the when-clause is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	Relevant keywords are present ("Twitter", "quote", "data card", "post") but common variations users naturally say are missing — most notably "tweet", plus "X", "share image", or "social media graphic". This matches anchor 3 (some relevant keywords, missing synonyms); anchor 4 would require good coverage with only a few natural terms missing.	3 / 5
Distinctiveness Conflict Risk	The Twitter-specific framing ("Twitter quote or data card") carves a distinct niche with minimal conflict against unrelated skills. Score 5 is withheld because other social-platform share-card skills would be close cousins and the description gives no disambiguating trigger phrases; score 3 would imply broader overlap than this niche has.	4 / 5
	Total	12 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/card-twitter/SKILL.md
Commit: 1b47e60

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.