Lean, competence-assuming prose with tables and tight field lists; no explaining of basic concepts Claude already knows. Not level 2 because there is no padded or unnecessary explanation to tighten.

Provides executable commands ('python .agents/skills/ai-models/scripts/model_info.py <model_id>'), exact file paths, concrete pricing-union code shapes, and provider URLs — copy-paste ready guidance rather than pseudocode.

Sequenced multi-step processes ('Adding a model / route') plus an explicit 'After Any Update' validation checklist (tsc --noEmit, docs match, page renders, grep for stale IDs) and a budget checkpoint before wiring video; not level 2 because validation checkpoints are explicit, not implicit.

Well-sectioned overview (When to Use, Key Files, Tools, per-domain sections) with the referenced script (scripts/model_info.py) confirmed as a real file and no deeply nested reference chains; not level 2 because structure and signaled references are clear rather than merely present.

Lists multiple concrete actions ('Research, compare, and update AI model configurations', 'bumping model versions, adding new models, updating pricing, or auditing model specs') matching the multi-specific-action anchor; not level 2 because it goes beyond naming a domain plus a couple actions.

Explicitly answers both what ('Research, compare, and update AI model configurations' plus coverage of tiers, image/video, pricing, budget) and when ('Use when bumping model versions, adding new models, updating pricing, or auditing model specs'), meeting the both-what-and-when anchor.

Uses natural phrasings a user would actually say ('bumping model versions', 'adding new models', 'updating pricing', 'auditing model specs'), giving good coverage rather than the partial/jargon anchor at level 2.

Targets a clearly bounded niche (internal AI model catalogue config) with distinct, specific triggers unlikely to fire for unrelated skills; not level 2 because it is far more specific than 'Works with document files'.