CtrlK
BlogDocsLog inGet started
Tessl Logo

social-carousel

A three-card social-media carousel laid out as 1080×1080 squares — three cinematic, on-brand panels with display headlines that connect across the series ("onwards." → "to the next one." → "looking ahead."). Each card has a brand mark, a number / total, a caption, and a "loop" affordance. Use when the brief asks for a "carousel post", "social carousel", "Instagram carousel", "LinkedIn series", "X thread cards", or "三连发".

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

Excellent instruction-only content: concrete, token-efficient, and fully executable for a single-task design skill. The workflow is clearly sequenced with an explicit self-check, and the self-contained structure is appropriately sized for progressive disclosure with no bundle files needed.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: no explanation of HTML/CSS or what a carousel is; every line is instruction or concrete spec ('1080×1080 cinematic still', 'radial-gradient + linear-gradient only — no images', 'stack at < 1100px'). Matches anchor 5 — every token earns its place; not 4 because there is no over-explanation to trim.

5 / 5

Actionability

Fully executable guidance: exact CSS values ('aspect-ratio: 1 / 1', 'width: clamp(280px, 30vw, 380px)', 'rounded 12px corners', '1px border'), per-panel gradient recipes, required data attributes ('data-od-id on stage, each card, each headline'), and a copy-paste output contract template with the artifact wrapper. Matches anchor 5; not 4 because the common case (a 3-card carousel) is completely specified end to end.

5 / 5

Workflow Clarity

Six clearly sequenced steps (read DESIGN.md → pick theme/captions → stage → cards → write → self-check) ending in an explicit 3-point self-check checklist ('The three headlines together form one sentence...', 'no two share a dominant hue'). For this simple, non-destructive single-task skill this matches anchor 5; not 4 because the validation step is explicit and criterion-based, not merely implied.

5 / 5

Progressive Disclosure

The skill is a self-contained ~60-line single-task document with no references/, scripts/, or assets/ bundle and no external file pointers; content is well-organized under clear sections (Workflow, Output contract). Per the simple-skill guidance, this matches anchor 5 — nothing that belongs in a separate file is inlined.

5 / 5

Total

20

/

20

Passed

Description

87%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.

A strong description: concrete about the deliverable and its components, with an explicit, platform-aware 'Use when' clause covering natural synonyms in two languages. Its only soft spot is that it describes the artifact as a noun phrase ('A three-card social-media carousel laid out as...') rather than leading with an explicit action verb, and trigger coverage could add a couple of everyday variants.

Suggestions

Lead with an explicit third-person action verb (e.g., 'Produces a three-card social-media carousel...') so the capability reads as an action, not just an artifact description.

Add one or two more natural trigger variants users might say, such as 'social media post series' or 'multi-image post', to broaden natural-language matching.

Consider trimming the specific headline series example ('onwards.' → 'to the next one.' → 'looking ahead.') from the description — it is instance detail already covered in the body and adds tokens without aiding trigger matching.

DimensionReasoningScore

Specificity

The description enumerates several concrete, checkable artifact details — '1080×1080 squares', 'display headlines that connect across the series', 'brand mark, a number / total, a caption, and a "loop" affordance' — but frames them as one deliverable rather than listing multiple distinct actions, matching anchor 4 ('several specific actions; minor gaps') rather than 5's 'multiple specific concrete actions'.

4 / 5

Completeness

It explicitly answers both questions: the 'what' is concrete ('three cinematic, on-brand panels' with enumerated card elements at a fixed size) and the 'when' is an explicit 'Use when the brief asks for a...' clause with concrete trigger phrases, exactly matching anchor 5. Not 4 because the 'when' clause is not merely present but specific and multi-phrase.

5 / 5

Trigger Term Quality

'Use when the brief asks for a "carousel post", "social carousel", "Instagram carousel", "LinkedIn series", "X thread cards", or "三连发"' gives good natural, platform-specific coverage including a Chinese synonym, but misses common variants like 'social media carousel', 'multi-image post', or 'thread images', fitting anchor 4 ('good keyword coverage; a few natural terms missing').

4 / 5

Distinctiveness Conflict Risk

A clear niche (social-media carousel design, fixed at 'three-card' and '1080×1080') with distinct triggers ('Instagram carousel', 'X thread cards') that would not fire for general design or other format skills — minimal conflict risk, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.