CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

57

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

The body is structured but largely generic and non-actionable: it describes capabilities at a high level without any executable code, concrete commands, or validation checkpoints, and it fails to navigate to the bundled scripts and references that exist alongside it.

Suggestions

Replace the descriptive "The skill will: Generate code..." examples with concrete, copy-paste-ready Python snippets (or a worked /process-vision invocation with real arguments) so Claude knows exactly what to run.

Cut the redundant restatement of capabilities across Overview, When to Use, and Examples, and trim generic boilerplate (Prerequisites, Instructions, Output, Error Handling, Resources) to only skill-specific guidance.

Link the actual bundle files in the body — e.g., point to scripts/image_analyzer.py for the analysis script and references/ for model/format details — instead of the placeholder "Project documentation / Related skills and commands" entries.

DimensionReasoningScore

Conciseness

Overview, When to Use, and Examples repeat the same high-level description, and generic boilerplate sections (Best Practices, Prerequisites, Instructions, Output, Error Handling, Resources) add little — but it does not explain concepts Claude already knows, so it is above the score-1 verbosity anchor.

2 / 3

Actionability

No executable code or concrete commands appear anywhere; phrases like "The skill will: Generate code to perform object detection" describe rather than instruct, matching the score-1 vague/abstract anchor.

1 / 3

Workflow Clarity

"How It Works" lists a 3-step sequence (analyze request, generate code, execute via /process-vision) but provides no concrete commands or validation checkpoints, matching the score-2 anchor of steps present but checkpoints missing.

2 / 3

Progressive Disclosure

The body is organized into sections (not a monolithic wall), but real bundle files such as scripts/image_analyzer.py and the references/assets folders are never linked or signaled — the "Resources" section lists only "Project documentation / Related skills and commands" with no paths.

2 / 3

Total

7

/

12

Passed

Description

100%

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, third-person imperative in voice, and explicitly pairs capabilities with natural trigger terms, covering both what and when. It is a strong description with only minor filler in the final sentence.

DimensionReasoningScore

Specificity

Lists three concrete actions — "object detection, classification, and segmentation" — matching the score-3 anchor of multiple specific concrete actions, not the score-2 anchor of naming only some actions.

3 / 3

Completeness

Clearly answers both what ("Process images using object detection, classification, and segmentation") and when ("Use when requesting ..."), matching the score-3 anchor with explicit triggers rather than the score-2 anchor where when is only implied.

3 / 3

Trigger Term Quality

Explicit natural terms a user would say ("analyze image", "object detection", "image classification", "computer vision") give good coverage; the trailing "Trigger with relevant phrases based on skill purpose" is filler but does not undercut the explicit keywords.

3 / 3

Distinctiveness Conflict Risk

The computer-vision niche with distinct CV-specific triggers is unlikely to fire for unrelated skills, matching the score-3 anchor rather than the score-2 anchor of overlap with similar skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.