aso-appstore-screenshots

Generate high-converting App Store screenshots by analyzing your app's codebase, discovering core benefits, and creating ASO-optimized screenshot images using Nano Banana Pro.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

77%

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

The body is highly actionable with a well-sequenced, checkpoint-rich workflow, but it is verbose (duplicated spec across templates) and monolithic rather than progressively disclosed into reference files.

Suggestions

Extract the two large prompt templates and the full Screenshot Format Specification into a reference file (e.g. references/GENERATION_PROMPTS.md) and link to it from SKILL.md to remove duplication and reduce token cost.

Dedupe the breakout-element rules so they are stated once and referenced by the prompt templates rather than repeated verbatim.

Ensure the referenced compose.py and showcase.py are bundled (or note their location explicitly) so the inline file paths resolve against the actual bundle structure.

Dimension	Reasoning	Score
Conciseness	The full breakout-element spec (~700 words) is restated nearly verbatim inside two large prompt templates, and many "DO NOT" rules repeat across sections, inflating tokens — matching the score-2 anchor of mostly efficient but could be tightened rather than the lean score-3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: exact compose.py/showcase.py invocations, a working sips/python3 crop-resize loop, App Store dimension tables, and concrete prompt templates — matching the score-3 anchor.	3 / 3
Workflow Clarity	Clear phased sequence with explicit validation checkpoints (Gemini MCP availability check, confirm-before-proceed gates, immediate crop/resize before showing the user, incremental memory saves) and feedback loops, matching the score-3 anchor for a batch generation workflow.	3 / 3
Progressive Disclosure	Bundle structure has only assets/device_frame.png; the referenced compose.py and showcase.py scripts and any reference docs are not bundled, and the large prompt templates and full format spec are inline in SKILL.md rather than split into one-level-deep reference files — matching the score-2 anchor of content that should be separate being inline.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and occupies a distinct niche, but it lacks an explicit "Use when..." trigger clause and omits common user-facing phrasings, which caps completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants App Store screenshots, app store listing images, or ASO marketing screenshots."

Broaden natural trigger terms to include "App Store Optimization", "app store listing", and "marketing screenshots" for better recall.

Keep the concrete three-action pipeline — it is the description's strongest dimension.

Dimension	Reasoning	Score
Specificity	Lists three concrete, distinct actions — "analyzing your app's codebase", "discovering core benefits", and "creating ASO-optimized screenshot images using Nano Banana Pro" — matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does but provides no explicit "Use when..." trigger guidance, so "when" is only implied — the rubric caps completeness at 2 for a missing explicit trigger clause.	2 / 3
Trigger Term Quality	Includes natural terms like "App Store screenshots" and "ASO-optimized" but misses common variations users would say ("app store listing", "marketing screenshots", "App Store Optimization"), matching the score-2 anchor of partial coverage rather than the score-3 broad coverage.	2 / 3
Distinctiveness Conflict Risk	The App Store ASO + Nano Banana Pro niche is specific and unlikely to trigger the wrong skill, matching the score-3 anchor for a clear niche with distinct triggers.	3 / 3
	Total	10 / 12 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
skill_md_line_count	SKILL.md is long (557 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: adamlyttleapps/claude-skill-aso-appstore-screenshots
Path: SKILL.md
Commit: 87e1c80

Reviewed: about 5 hours 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.