CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

74%

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 well-structured, token-efficient API reference with executable curl examples for every endpoint and details correctly deferred to the OpenAPI specification. Its weaknesses are the undifferentiated cluster of four list-models endpoints with no usage guidance, and POST examples with empty bodies that give no model for constructing real requests. No bundle files (references/, scripts/, assets/) exist, so all content lives appropriately in the single file.

Suggestions

Disambiguate the four list-models endpoints with one line each on when to choose it (e.g. v1 vs management vs full catalog vs openrouter catalog), since that choice is the skill's real workflow.

Show a representative request body for the POST endpoints instead of `-d '{}'` — e.g. a /api/v1/models/query body using the documented capability/min_context/kind/q filters and an alias-creation body with its required fields.

Drop or repurpose the Overview section that duplicates the frontmatter description verbatim to save tokens.

DimensionReasoningScore

Conciseness

The body is efficient — terse per-endpoint notes and compact curls with no padding, and the dense health-endpoint paragraph documents real semantics rather than explaining known concepts — but the Overview section repeats the frontmatter description verbatim and could be trimmed.

4 / 5

Actionability

Every endpoint has a copy-paste-ready curl with the auth header, but the four POST endpoints ship empty `-d '{}'` bodies with no sample payload demonstrating the documented filters or alias fields, which are minor gaps rather than the fully-covered common cases of the top anchor.

4 / 5

Workflow Clarity

Endpoints are organized with informative one-line descriptions, but four overlapping list-models endpoints (/api/v1/models, /api/models, /api/models/catalog, /api/models/openrouter-catalog) get no guidance on when to use which, so endpoint selection — this reference skill's implicit workflow — remains implicit.

3 / 5

Progressive Disclosure

Good structure: clear per-endpoint sections with appropriately overview-level content and a clearly signaled "Payloads" section deferring schemas to the OpenAPI spec. No bundle files exist, and the deferred target (docs/openapi.yaml, GET /api/openapi/spec) is an out-of-bundle pointer, which are minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

66%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, third-person, and concrete, naming several distinct capabilities with natural trigger keywords. Its main weakness is the absence of any "Use when..." trigger guidance, which leaves the "when should I use this" question unanswered and caps completeness. Coverage also omits a few capabilities documented in the body (testing, health state).

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks which models are available, wants to list or compare models across providers, or needs to resolve a model alias."

Mention the remaining capabilities from the body (per-model health/pause state, model connectivity testing) so the description comprehensively covers the skill.

Include common user phrasings and synonyms such as "available models", "which models", or "model names" to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ("List models, resolve model aliases, and browse the full model catalog including provider-specific variants"), which matches the several-specific-actions-with-minor-gaps anchor rather than the comprehensive-coverage anchor, since capabilities present in the body (model testing, per-model health/pause state) are not surfaced.

4 / 5

Completeness

The "what" is clearly answered with three named capabilities, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"List models", "model aliases", and "model catalog" are natural phrases a user would say, giving good keyword coverage, but common variations like "available models", "which models", or "LLM" are missing, keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

"across all configured providers", "model aliases", and "model catalog" carve a distinct model-discovery niche with minimal conflict risk; only minor overlap with closely related routing/API-reference skills keeps it below the clear-niche anchor.

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

diegosouzapw/OmniRoute

Path

skills/omni-models/SKILL.md

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.