processing-computer-vision-tasks

Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/computer-vision-processor/skills/processing-computer-vision-tasks/SKILL.md

Quality

Content

35%Weight 40%Scale 1-3

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

The body reads as a generic marketing-style overview: it describes what the skill does in the abstract but provides no executable code, no concrete commands, and no links to the bundled script that would make it actionable. Workflow steps lack validation checkpoints and the bundle files are not surfaced from the body.

Suggestions

Add a concrete, runnable example that actually invokes scripts/image_analyzer.py with real arguments and shows expected output, instead of 'Generate the appropriate Python code'.

Link to the bundle files from the body (e.g. 'See [scripts/image_analyzer.py](scripts/image_analyzer.py)') so progressive disclosure is one level deep and navigable.

Insert a validation/verification checkpoint into the workflow (e.g. confirm the image format is supported before processing, and verify detections are non-empty before reporting).

Cut the generic 'Best Practices', 'Prerequisites', 'Output', and 'Resources' sections that restate what Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient prose, but sections like 'Overview', 'Best Practices', 'Prerequisites', 'Output', and 'Resources' add generic guidance Claude already knows; it could be tightened considerably.	2 / 3
Actionability	No executable code or concrete commands appear — it 'describes rather than instructs' ('Generate the appropriate Python code', 'executed using the /process-vision command'), and the bundled scripts/image_analyzer.py is never referenced or shown.	1 / 3
Workflow Clarity	The 'How It Works' steps provide a sequence (analyze → generate code → execute) but there are no validation checkpoints or error-recovery feedback loops despite image processing being a fallible operation.	2 / 3
Progressive Disclosure	Section structure exists, but the body never links to the real bundle files (scripts/image_analyzer.py, references/, assets/), and those references are placeholder READMEs rather than signaled one-level-deep materials.	2 / 3
	Total	7 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 solid third-person description that names concrete capabilities and provides an explicit 'Use when' trigger clause. Its main weakness is trigger-term naturalness, where the phrases are somewhat technical and the generic trigger guidance adds nothing.

Suggestions

Replace the filler line 'Trigger with relevant phrases based on skill purpose' with additional natural user phrasings such as 'detect objects in an image' or 'segment an image'.

Add common-sense synonyms users actually say (e.g. 'count objects', 'identify what's in a photo') alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'object detection, classification, and segmentation' — matching the highest anchor rather than just naming the domain.	3 / 3
Completeness	Explicitly answers both what ('Process images using object detection, classification, and segmentation') and when ('Use when requesting...') with a clear trigger clause.	3 / 3
Trigger Term Quality	Includes relevant phrases like 'analyze image' and 'image classification' but they lean technical and omit common variations users might say; the meta-instruction 'Trigger with relevant phrases based on skill purpose' adds no real coverage.	2 / 3
Distinctiveness Conflict Risk	The computer-vision niche with specific triggers ('object detection', 'image classification', 'computer vision') is distinct and unlikely to collide with unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/computer-vision-processor/skills/processing-computer-vision-tasks/SKILL.md
Commit: bddba3c

Reviewed: 1 day 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.