CtrlK
BlogDocsLog inGet started
Tessl Logo

omni-models

Query available AI models across all configured providers. List models, resolve model aliases, and browse the full model catalog including provider-specific variants.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-models/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

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

The body is a clean, concise API reference with executable curl examples and sensible structure. Its main weaknesses are undifferentiated overlapping endpoints and a lack of validation/error-handling guidance for the mutating alias endpoint.

Suggestions

Disambiguate the two list-models endpoints — explain when to use GET /api/v1/models vs GET /api/models (e.g. versioned vs management).

Provide a real example request body for POST /api/models/alias instead of `-d '{}'`, or inline a minimal schema snippet.

Add a brief note on validating alias responses / error codes for the mutating endpoint to establish a feedback checkpoint.

DimensionReasoningScore

Conciseness

Mostly lean curl and endpoint listings with no concept over-explanation, but the Overview section duplicates the frontmatter description and a few endpoint descriptions are slightly redundant.

4 / 5

Actionability

Concrete, mostly copy-pasteable curl commands with auth headers, but the POST /api/models/alias example uses an empty `-d '{}'` body and defers real payloads to the OpenAPI spec.

4 / 5

Workflow Clarity

Endpoints are listed but two 'List models' endpoints (/api/v1/models and /api/models) are not differentiated, and the mutating alias endpoint has no validation or error-handling guidance.

3 / 5

Progressive Disclosure

Well-organized into Overview, Authentication, Endpoints, and Payloads sections with a clearly signaled one-level reference to the OpenAPI spec, though the bulk schema deferral leaves minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

71%Weight 40%Scale 1-5

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 and action-oriented with good trigger keywords, but it omits any 'when to use' guidance, which is the primary gap. It is clearly distinguishable from generic skills.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to list available models, look up model aliases, or browse the model catalog across providers.'

Include a natural synonym such as 'available models' or 'LLM catalog' to broaden trigger term coverage.

Clarify what 'provider-specific variants' means in plain terms so the trigger is recognizable to users unfamiliar with the terminology.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'List models, resolve model aliases, and browse the full model catalog including provider-specific variants' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

The 'what' is clearly stated but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Good natural keyword coverage (AI models, providers, model aliases, model catalog) but misses common synonyms like 'available models' or 'LLM models' a user might say.

4 / 5

Distinctiveness Conflict Risk

Model catalog browsing and alias resolution is a fairly distinct niche, though it could minorly overlap with other model-routing or provider skills.

4 / 5

Total

16

/

20

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
diegosouzapw/OmniRoute
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.