axiom-vision

Use when implementing ANY computer vision feature — image analysis, pose detection, person segmentation, subject lifting, text recognition, barcode scanning.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude-plugin/plugins/axiom/skills/axiom-vision/SKILL.md

Quality

Content

63%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-structured routing/index skill with excellent progressive disclosure and a clear decision tree, but it provides no inline executable guidance and the referenced reference files are not present in the skill bundle. Structural redundancy across four sections also hurts token efficiency.

Suggestions

Bundle or inline the referenced files (skills/vision-framework.md, vision-ref.md, vision-diag.md) so the routing targets actually exist within the skill.

Collapse the redundant routing across the Quick Reference table, Critical Patterns, and Example Invocations into a single lookup structure to reduce tokens.

Add at least one minimal inline code snippet or concrete first step per common task so the skill is actionable without immediately requiring an external file.

Dimension	Reasoning	Score
Conciseness	No concept padding, but the same routing is restated four ways (Quick Reference table, Decision Tree + numbered list, Critical Patterns, Example Invocations), so it could be tightened; not a 4 because the Example Invocations section largely duplicates the table.	3 / 5
Actionability	Routing is concrete (specific symptom -> specific file), but there is no executable code or inline guidance and the referenced files (skills/vision-framework.md etc.) are absent from the bundle, leaving dead ends; not a 2 because the routing itself is specific rather than vague hints.	3 / 5
Workflow Clarity	The dot decision tree plus numbered list give a clear, unambiguous sequence for choosing the right reference; not a 5 because there are no validation/feedback checkpoints, though none are strictly required for pure routing.	4 / 5
Progressive Disclosure	SKILL.md is a lean overview with well-signaled, one-level-deep references organized via a Quick Reference table and Decision Tree, matching the clear-navigation anchor; the missing bundle files are an actionability concern, not a structural one.	5 / 5
	Total	15 / 20 Passed

Description

92%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, specific description that clearly states both capability and trigger conditions with concrete feature names. Minor synonym gaps (OCR, QR code) prevent a perfect trigger_term_quality score.

Dimension	Reasoning	Score
Specificity	Lists six concrete capabilities ("image analysis, pose detection, person segmentation, subject lifting, text recognition, barcode scanning"), matching the comprehensive-coverage anchor; not below because each action is specific rather than generic.	5 / 5
Completeness	Explicitly answers both what (the six listed features) and when ("Use when implementing ANY computer vision feature") with concrete trigger phrases; not below because the when-clause is explicit and specific.	5 / 5
Trigger Term Quality	Strong natural terms ("computer vision", "pose detection", "text recognition", "barcode scanning") but missing common synonyms users say such as "OCR", "QR code", and "image processing"; not a 5 because synonym coverage is incomplete.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Vision-framework computer vision) with distinct, specific triggers and minimal overlap risk; the only adjacency (face clustering) is explicitly redirected to axiom-media in the body.	5 / 5
	Total	19 / 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: .claude-plugin/plugins/axiom/skills/axiom-vision/SKILL.md
Commit: 4ae86a3

Reviewed: 5 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.