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.
48
37%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ai-ml/computer-vision-processor/skills/processing-computer-vision-tasks/SKILL.mdQuality
Discovery
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 adequately covers the what and when, earning full marks for completeness. However, it suffers from somewhat generic capability descriptions and includes meaningless filler text ('Trigger with relevant phrases based on skill purpose'). The trigger terms are decent but could include more natural user phrasings.
Suggestions
Remove the vague filler sentence 'Trigger with relevant phrases based on skill purpose' - it adds no value and wastes space.
Add more natural user phrasings to trigger terms, such as 'what's in this image', 'identify objects', 'recognize faces', 'label this photo'.
Make capabilities more concrete by specifying outputs, e.g., 'identify and label objects in images, classify image content into categories, segment image regions with bounding boxes'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (images) and lists some actions (object detection, classification, segmentation), but these are high-level categories rather than concrete specific actions like 'identify objects in photos' or 'label image regions'. | 2 / 3 |
Completeness | Explicitly answers both what (process images using detection, classification, segmentation) and when (Use when requesting specific trigger phrases). Has a clear 'Use when...' clause with explicit triggers. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords ('analyze image', 'object detection', 'image classification', 'computer vision') but the final sentence 'Trigger with relevant phrases based on skill purpose' is vague filler that adds no value. Missing common variations like 'detect objects', 'what's in this image', 'identify', 'recognize'. | 2 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to computer vision tasks, but 'analyze image' is quite broad and could overlap with other image-related skills. The generic 'computer vision' term could cause conflicts with more specialized vision skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is largely placeholder text that describes what a computer vision skill should do rather than providing actionable instructions. It lacks any executable code, concrete command syntax, or specific parameters despite being about a code-generation task. The content is padded with generic best practices and vague instructions that provide no value to Claude.
Suggestions
Add actual executable code examples showing the exact syntax for '/process-vision' command with real parameters (e.g., model selection, confidence thresholds, output format)
Replace abstract 'How It Works' descriptions with concrete input/output examples showing actual JSON or command structures
Remove generic sections like 'Prerequisites', 'Instructions', and 'Best Practices' that contain only vague platitudes, or replace them with specific, actionable content
Show the actual output format (bounding box coordinates, confidence scores, segmentation masks) with concrete examples rather than describing them abstractly
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with unnecessary explanations of concepts Claude already knows (what computer vision is, how to validate input). The 'How It Works' section explains obvious steps, and sections like 'Prerequisites' and 'Instructions' are vague filler that add no actionable value. | 1 / 3 |
Actionability | No executable code anywhere despite claiming to 'generate code'. Examples describe what the skill 'will do' abstractly rather than showing actual commands or code. The '/process-vision' command is mentioned but never demonstrated with actual syntax or parameters. | 1 / 3 |
Workflow Clarity | The workflow steps are vague abstractions ('Invoke this skill when trigger conditions are met', 'Provide necessary context'). No concrete sequence, no validation checkpoints, and no actual parameters or command syntax for the computer vision operations. | 1 / 3 |
Progressive Disclosure | Content is organized into sections with headers, but it's a monolithic document with no references to external files. The structure exists but contains mostly filler content that could be condensed significantly. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
0c08951
- 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.