CtrlK
BlogDocsLog inGet started
Tessl Logo

cv-classification

Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 content is a concise, well-organized reference that provides concrete and actionable guidance for image classification without unnecessary padding or redundant explanations. It is appropriately self-contained for a skill of this scope.

DimensionReasoningScore

Conciseness

The body is lean bullet-point guidance with specific numeric values and no padding or explanation of concepts Claude already knows (e.g., what a CNN or ViT is), matching anchor 3 for token efficiency.

3 / 3

Actionability

It gives concrete, specific guidance — architectures per scale tier and exact ranges for optimizer/lr, weight decay, augmentation, warmup, and batch size. As an instruction-only skill with actionable guidance, absence of executable code is not penalized per the rubric scoring notes; it matches anchor 3.

3 / 3

Workflow Clarity

This is a single-purpose reference skill under 50 lines with no destructive or batch operations requiring validation checkpoints; the content is clear and well-organized into sections, so it scores 3 under the simple-skills scoring note.

3 / 3

Progressive Disclosure

The skill is self-contained, under 50 lines, and organized into well-signaled sections (Architecture selection, Training recipe, Standard benchmarks) with no need for external references — verified that no references/, scripts/, or assets/ bundle files exist — matching anchor 3 for a simple skill.

3 / 3

Total

12

/

12

Passed

Description

90%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.

The description has a clear niche with strong natural trigger terms and an explicit Use-when clause, making it distinct and complete. Its only weakness is that the stated action ("best practices") is abstract rather than enumerating concrete capabilities.

Suggestions

Replace the abstract "Best practices for image classification tasks" with concrete actions, e.g. "Select architectures and configure training recipes (optimizer, augmentation, batch size) for image classification tasks".

Optionally name an additional capability category in the description (e.g. benchmark/expected-accuracy guidance) so the what clause lists multiple specific actions.

DimensionReasoningScore

Specificity

The description names the concrete domain ("image classification tasks") but the stated action is the abstract phrase "Best practices for", rather than a list of concrete actions like architecture selection or training-recipe configuration. It is above anchor 1 ("Helps with documents") because the domain is specified, but below anchor 3 because no multiple specific concrete actions are enumerated.

2 / 3

Completeness

It states what it provides ("Best practices for image classification tasks") and includes an explicit "Use when working on CIFAR, ImageNet, or other classification benchmarks" trigger clause, satisfying both what and when per anchor 3.

3 / 3

Trigger Term Quality

"image classification", "CIFAR", "ImageNet", and "classification benchmarks" are natural terms a user would say when they need this skill, giving good coverage of relevant trigger variations matching anchor 3.

3 / 3

Distinctiveness Conflict Risk

The combination of "image classification" with CIFAR/ImageNet benchmark triggers carves a clear niche that is unlikely to conflict with other skills, matching anchor 3.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aiming-lab/AutoResearchClaw
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.