ai-models

Research, compare, and update AI model configurations. Covers text model tiers, image and video generation models, image tool models, release provenance, 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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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.

A highly actionable, well-organized workflow doc that assumes Claude's competence and includes real validation checkpoints. Its main weakness is monolithic inlining of detailed reference material rather than splitting it into reference files.

Suggestions

Move the provider/model-ID tables, pricing-type definitions, and per-second pricing schema into a references/ file (e.g. references/pricing-and-providers.md) and link to it from SKILL.md to improve progressive disclosure.

Convert the 'Adding a model / route' guidance into numbered sequences with explicit validate-then-proceed checkpoints mirroring the 'After Any Update' checklist.

Fix the dangling scripts/model_info.py symlink (target .tools/model_info.py is absent) or vendor the script so the referenced tool is actually usable.

Dimension	Reasoning	Score
Conciseness	The body is dense but almost entirely project-specific policy Claude would not already know (catalogue discipline, provenance rules, metering); it avoids explaining known concepts, with only minor philosophical prose that could be trimmed.	4 / 5
Actionability	It provides copy-paste commands (`python .../model_info.py`, `pnpm tsc --noEmit`), concrete TS data shapes for release/pricing objects, exact file paths, and per-tier field lists that cover the common update cases.	5 / 5
Workflow Clarity	Sequenced guidance for adding models/routes plus an explicit 'After Any Update' validation checklist (tsc, grep old IDs, page renders) supplies clear checkpoints; some sub-workflows are bulleted rather than numbered, leaving minor gaps.	4 / 5
Progressive Disclosure	Section headers are clear and the one bundle script is referenced cleanly, but ~300 lines of inlined provider/pricing tables and schema detail with no references/ directory means content that would benefit from splitting lives in SKILL.md itself; the symlinked script target is also dangling.	3 / 5
	Total	16 / 20 Passed

Description

87%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: third person, concise, with explicit 'what' and 'when' clauses and concrete triggers tied to a well-scoped domain. The only soft spot is that the lead action verbs are slightly generic despite comprehensive domain coverage.

Dimension	Reasoning	Score
Specificity	Lists concrete verbs ('Research, compare, and update') plus comprehensive domain coverage (text tiers, image/video gen, image tools, provenance, pricing, metering), but the action verbs themselves stay somewhat generic compared to the highly concrete anchor-5 example.	4 / 5
Completeness	It explicitly answers both what ('Research, compare, and update AI model configurations. Covers...') 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 bumping model versions, adding new models, updating pricing, or auditing model specs' clause supplies several natural phrases a user would say, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The niche — managing a codebase's AI model catalogue, pricing, provenance, and prepaid-credit metering — is specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: 03fb751

Reviewed: 3 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.