CtrlK
BlogDocsLog inGet started
Tessl Logo

screenshot-optimization

When the user wants to design, optimize, or evaluate App Store screenshots and preview videos. Also use when the user mentions "screenshots", "app preview", "product page design", "screenshot design", "creative assets", or "what should my screenshots show". For A/B testing screenshots, see ab-test-store-listing. For full ASO audit, see aso-audit.

67

Quality

80%

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

82%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.

A well-crafted advisory skill: dense with conversion heuristics Claude doesn't already know, highly actionable via slot formulas, do/don't tables, and output templates, and clearly sequenced from assessment to deliverable. The only meaningful gaps are the absence of self-validation checkpoints and a monolithic structure that could offload detail sections to reference files.

DimensionReasoningScore

Conciseness

Mostly domain-specific conversion heuristics Claude would not reliably know ("Users spend 3-6 seconds", "first 3 screenshots… determine 80% of the conversion decision", "min 60px" fonts, slot-by-slot strategy), delivered in terse tables and lists. Not 5 because of minor trimmable padding — the "You are an expert…" role preamble and a few self-evident Do/Don't rows like "High contrast text" / "Consistent color scheme"; well above anchor 3's noticeable over-explanation.

4 / 5

Actionability

Concrete, executable guidance throughout: the slot formula "[Benefit Headline] + [Feature UI] + [Supporting Detail]", worked pattern examples ("Sleep Better Tonight" + sleep tracking screen, "Tired of [problem]?"), a fill-in output template per slot, and a competitor audit table. As an instruction-only skill this matches anchor 5 — specific examples cover the common cases and the output format is directly usable.

5 / 5

Workflow Clarity

"Initial Assessment" gives a numbered input-gathering sequence (check app-marketing-context.md, ask for App ID, audience, top features, designer) that flows into the strategy framework and defined output formats. Not 5 because there are no validation checkpoints (e.g., verifying captions meet the 4-6 word or contrast rules before finalizing the plan); not 3 because the sequence itself is coherent and complete for an advisory skill with no destructive operations.

4 / 5

Progressive Disclosure

No bundle files exist, and the single ~160-line SKILL.md is well-sectioned with clear headers and easy navigation, with no nested or dangling bundle references. Not 5 because at this length sections like the preview video guide, localization notes, and competitor audit template are candidates for separate reference files; clearly better organized than anchor 3's inlined content with unclear signaling.

4 / 5

Total

17

/

20

Passed

Description

78%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 with an explicit what/when structure, natural trigger phrases, and unusually good boundary routing to related skills. Its main weakness is capability specificity — the verbs are generic and don't enumerate the concrete deliverables the body supports.

Suggestions

Enumerate concrete capabilities in the description, e.g. 'Create 10-slot screenshot plans, write benefit-driven captions, and audit competitor product pages' instead of the generic 'design, optimize, or evaluate'.

Add one or two more trigger synonyms users naturally say, such as 'app store listing' or 'store page', to round out keyword coverage.

Qualify the bare 'screenshots' trigger with context (e.g. 'App Store screenshots') to avoid firing for generic screenshot-capture requests.

DimensionReasoningScore

Specificity

"design, optimize, or evaluate App Store screenshots and preview videos" names the domain plus three actions, but the verbs are generic and the concrete deliverables the skill actually produces (screenshot slot plans, captions, competitor audits, design briefs) are not listed. This matches anchor 3 rather than anchor 4's 'several specific actions' — not anchor 2 because the domain is named and more than one action is given.

3 / 5

Completeness

Explicitly answers both: what ("design, optimize, or evaluate App Store screenshots and preview videos") and when ("When the user wants to…" plus "Also use when the user mentions…" with concrete trigger phrases). Matches anchor 5's pattern of both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Natural quoted phrases like "screenshots", "app preview", "product page design", "screenshot design", "creative assets", and "what should my screenshots show" give good coverage. Not 5 because common variations such as "app store listing", "creative set", or "store page" are missing; clearly above 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

Clear App Store creative niche with explicit boundary routing ("For A/B testing screenshots, see ab-test-store-listing. For full ASO audit, see aso-audit") minimizes conflict with sibling skills. Not 5 because the bare trigger term "screenshots" could also fire for generic screenshot-capture requests; well above anchor 3's broad overlap risk.

4 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Eronred/aso-skills
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.