CtrlK
BlogDocsLog inGet started
Tessl Logo

clip

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is highly actionable with executable, copy-paste-ready examples but is undercut by redundancy against the references bundle and missing validation on batch operations. Progressive disclosure suffers because the existing reference file is neither signaled nor meaningfully differentiated from the inline content.

Suggestions

Link references/applications.md from the body (e.g. a 'See applications.md for additional use cases' pointer) and de-duplicate the overlapping zero-shot, search, and moderation examples so the reference adds depth rather than repetition.

Add validation checkpoints to the batch-processing and vector-database workflows (e.g. verifying embedding norms, checking result counts, or asserting confidence thresholds) to lift workflow clarity.

Remove time-sensitive trivia like the GitHub star count and the 'Metrics' block, or move version/date-sensitive details into a clearly marked section, to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is largely lean and code-forward, but it duplicates content also present in references/applications.md and carries time-sensitive fluff such as '25,300+ GitHub stars' and a version number outside any deprecated/old-patterns section.

2 / 3

Actionability

Every section provides complete, copy-paste-ready executable code (e.g. the zero-shot classification and image-text similarity blocks) with concrete imports and commands, matching the top anchor.

3 / 3

Workflow Clarity

Single-task recipes are unambiguous, but the batch-processing and vector-database sections perform batch operations without any validation or verification checkpoints, which caps this dimension at 2 per the rubric guidance.

2 / 3

Progressive Disclosure

A references/applications.md bundle exists but is never linked or signaled from the body, and its content largely repeats what is already inline — content that should be split out is duplicated rather than clearly delegated.

2 / 3

Total

9

/

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.

A strong, third-person description that concisely states what CLIP does and gives an explicit 'Use for...' trigger with both natural and technical terms. It covers capabilities, triggers, and a distinct niche without fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'zero-shot image classification, image-text matching, and cross-modal retrieval' — matching the anchor for naming several specific capabilities rather than vague language.

3 / 3

Completeness

Clearly answers both 'what' ('Enables zero-shot image classification...') and 'when' with an explicit 'Use for image search, content moderation, or vision-language tasks' trigger clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

Includes natural user-facing terms like 'image search', 'content moderation', and 'image classification' alongside the technical vocabulary, giving good coverage of phrases a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Names a specific model (CLIP) with a clear vision-language / zero-shot niche and distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.