cli-models

Query available AI models, list model aliases, and browse the full model catalog from the CLI. Filter by provider, search by capability, and resolve model name variants.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/cli-models/SKILL.md

Quality

Content

85%

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

A compact, well-organized CLI skill body that avoids padding and stays lean. Its main weakness is actionability: the flags and several advertised capabilities lack concrete, executable examples.

Suggestions

Add executable examples for each flag, e.g. 'omniroute models openai --search vision --json' and 'omniroute models --json | jq', so the guidance is copy-paste ready.

Demonstrate the advertised capabilities that are currently missing examples — listing aliases and searching by capability — so every claim in the description maps to a concrete command.

Expand beyond the single 'models' subcommand or explicitly state if other subcommands are out of scope, since the body implies a fuller catalog than it documents.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows — 'Quick install', a one-line subcommand, flags, and a single example — and every token earns its place, matching the lean/efficient anchor.	3 / 3
Actionability	The install command is concrete, but the subcommand example 'omniroute models [provider]' is a usage skeleton and flags --search and --json are listed without usage examples, while claimed capabilities like alias listing and capability search are never demonstrated, matching the 'some concrete guidance but incomplete' anchor rather than copy-paste ready.	2 / 3
Workflow Clarity	This is a simple single-purpose skill under 50 lines with no destructive or batch operations, and the Quick install → subcommand path is unambiguous, so per the simple-skills scoring note it scores 3; it is not capped because no risky operations require validation.	3 / 3
Progressive Disclosure	With under 50 lines, no bundle files, and well-organized sections (Overview, Quick install, Subcommands), the simple-skill guideline permits a 3 even without external references.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 specific, third-person description that clearly states capabilities but lacks any explicit 'Use when…' trigger guidance, leaving completeness capped. Trigger terms are relevant but skew toward CLI jargon over natural user phrasing.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks which models are available, wants to list or resolve model aliases, or needs to filter models by provider or capability.'

Add natural-language trigger terms users would actually say (e.g. 'available models', 'model list', 'which models') alongside the current CLI jargon to improve trigger-term coverage and distinctiveness.

Tie the capability list to concrete CLI verbs (e.g. 'omniroute models --search <capability>') to further lock the niche and reduce overlap with generic CLI skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Query available AI models, list model aliases, and browse the full model catalog from the CLI. Filter by provider, search by capability, and resolve model name variants' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	The description clearly states what the skill does but has no 'Use when…' or equivalent explicit trigger guidance, which the judging guidelines cap at 2; it is not a 1 because the 'what' is strong.	2 / 3
Trigger Term Quality	Terms like 'AI models', 'model aliases', 'provider', and 'capability' are relevant but CLI-jargon leaning, and common user phrasings such as 'which models are available' or 'model list' are absent, so it matches the 'some relevant keywords but missing common variations' anchor rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (CLI model browsing) but without explicit triggers and with only generic CLI framing it could still overlap with other general CLI/utility skills, matching the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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/cli-models/SKILL.md
Commit: 3070925

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.