axiom-validate-screenshots

Use when the user mentions App Store screenshot validation, screenshot review, checking screenshots before submission, or verifying screenshot dimensions and content.

1.47x

Quality

78%

Does it follow best practices?

Impact

75%

1.47x

Average score across 2 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-validate-screenshots/SKILL.md

Quality

Content

78%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 thorough, highly actionable validation workflow with concrete commands, exact requirements, and ready-to-use report templates. The main gaps are monolithic structure with no progressive disclosure via bundle files and somewhat long inlined report templates.

Suggestions

Move the two full report templates (Step 5 and "When No Issues Found") into a references/ file (e.g., report-templates.md) and reference it from the body to reduce inline length and enable progressive disclosure.

Add an explicit per-image verification checkpoint (e.g., confirm the Read tool successfully loaded each screenshot before judging it) to strengthen the batch workflow's validation loop.

Consider extracting the device dimension table and the issue taxonomy into a reference file so the SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and focused on domain-specific value Claude does not reliably know (exact pixel dimensions, guideline numbers, specific placeholder strings, status-bar override commands); not a 5 because the two full inlined report templates add length that could be trimmed or externalized.	4 / 5
Actionability	Fully executable guidance: concrete Glob patterns, a real sips dimension-check command, an exact device-size table, a specific issue taxonomy with named examples (Lorem ipsum, STAGING, "Carrier"), and copy-paste-ready report templates covering both the issues-found and no-issues cases.	5 / 5
Workflow Clarity	Clear Steps 1–5 sequence with explicit checkpoints (0 images → stop, >20 → cap, dimension matching, issue categorization) and a re-run feedback loop in Next Steps; not a 5 because some checkpoints are implicit (e.g., handling unreadable images) and the batch path lacks an explicit per-image read-verification step.	4 / 5
Progressive Disclosure	Well-organized into clear sections, but the skill is a single ~200-line monolith with no bundle files in references/scripts/assets, and large inlined report templates and dimension tables that could live in separate reference files; the one external reference (axiom-tools device-control-ref.md) is not a bundled file.	3 / 5
	Total	16 / 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 well-constructed, trigger-heavy description that clearly signals when to invoke the skill and carves out a distinct niche. Its main weakness is that the capability ("what") is implicit within the trigger clause rather than stated as an explicit standalone statement.

Suggestions

Lead with a short explicit capability clause (e.g., "Validates App Store screenshots for compliance, dimensions, and content issues.") before the "Use when..." trigger list to fully separate "what" from "when".

Add a few more natural synonyms such as "App Store screenshots" or "screenshot submission review" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions/contexts — "screenshot validation, screenshot review, checking screenshots before submission, or verifying screenshot dimensions and content" — with only minor gaps in coverage; not a 5 because the actions are framed as triggers rather than a comprehensive capability list.	4 / 5
Completeness	Explicit "Use when..." trigger guidance is present and detailed, and the "what" is conveyed through the activity nouns (validation/review/checking/verifying); not a 5 because the capability statement is folded into the trigger clause rather than stated as a standalone, explicit "what does this do".	4 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ("App Store screenshot validation", "screenshot review", "checking screenshots before submission", "verifying screenshot dimensions"), though a few common variants like "App Store screenshots" or submission-related synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	"App Store screenshot validation" is a clear niche with distinct, specialized triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-validate-screenshots/SKILL.md
Commit: 69ffef6

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.