ai-models

Research, compare, and update AI model configurations. Covers text model tiers, image and video generation models, image tool models, pricing data sourcing, and provider-cost metering against prepaid org credit. Use when bumping model versions, adding new models, updating pricing, or auditing model specs against provider documentation.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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.

An action-oriented, well-structured skill body with executable commands, field-level update guidance, and validation checkpoints. It is slightly verbose in its policy prose and keeps most detail inline rather than in separate reference files.

Suggestions

Tighten the philosophical policy passages (e.g. "What the catalogue is for") into concise rule statements to recover token budget.

Consider moving the large provider pricing tables and video card-shape spec into a separate reference file referenced one level deep from the body.

Verify the scripts/model_info.py symlink target resolves in the packaged bundle (the link target .tools/model_info.py is absent here), so the documented command runs as written.

Dimension	Reasoning	Score
Conciseness	The body is dense with actionable file paths, field lists, and command examples and assumes Claude's competence, but a few philosophical passages ("Price the steady state, not the promotion"; "a stale entry is a wrong answer, not a conservative one") could be trimmed to pure rule statements.	4 / 5
Actionability	Provides copy-paste-ready commands (model_info.py invocations), exact field-by-field update lists per model type, concrete pricing discriminated-union code blocks, and a provider URL table — fully executable guidance across common cases.	5 / 5
Workflow Clarity	Clear per-model-type update sections culminate in an "After Any Update" checklist with explicit validation (pnpm tsc --noEmit, docs/code match, grep for stale IDs); catalogue-invariant tests provide a feedback loop, so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Well-organized with clear headers and one real one-level-deep script reference (scripts/model_info.py, confirmed present in the bundle), but most detailed guidance (pricing tables, video card shape) is inlined rather than split into separate reference files.	4 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong description that is concrete, third-person, and answers both what and when with natural triggers. Its only gap is a lack of synonymous trigger variants, which keeps trigger-term quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Research, compare, and update") plus comprehensive domain coverage across text tiers, image/video generation, image tools, pricing sourcing, and provider-cost metering — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ("Research, compare, and update AI model configurations" with domain scope) and when ("Use when bumping model versions, adding new models, updating pricing, or auditing model specs") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when" clause gives four natural triggers ("bumping model versions", "adding new models", "updating pricing", "auditing model specs against provider documentation"), but it lacks synonyms/variants to reach comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The niche — AI model catalogue maintenance with provider-cost metering against prepaid org credit and spec auditing against provider docs — is distinct with minimal overlap risk from other skills.	5 / 5
	Total	19 / 20 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: gridaco/grida
Path: .agents/skills/ai-models/SKILL.md
Commit: 8ef5e53

Reviewed: about 16 hours 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.