Agent skill · data analytics · aiskillstore
model-discovery
Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/heavy), and detect new models. Use when needing up-to-date model IDs for API calls or when other skills reference model names.
Why this skill is useful
Adds domain-specific commands for fetching and classifying AI model names from multiple providers that the AI wouldn't reliably generate on its own.
What it needs
Requires uv installed locally. Requires anthropic, google, ollama, openai account access. About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Model Discovery Skill Fetch the most recent model names from AI providers using their APIs. Includes tier classification (fast/default/heavy) for routing decisions and automatic detection of new models. Variables Variable Default Description ---------- --------- ------------- CACHETTLHOURS 24 How long to cache model lists before refreshing ENABLEDANTHROPIC true Fetch Claude models from Anthropic API ENABLEDOPENAI true Fetch GPT models from OpenAI API ENABLEDGEMINI true Fetch Gemini models from Google API ENABLEDOLLAMA true Fetch local models from Ollama OLLAMAHOST http://localhost:11434 Ollama API endpoint AUTOCLASSIFY true Auto-classify new models using pattern matching Instructions MANDATORY - Follow the Workflow steps below in order. Do not skip steps. Before referencing model names in any skill, check if fresh data exists Use tier mappings to select appropriate models (fast for speed, heavy for capability) Check for new models periodically and classify them Red Flags - STOP and Reconsider If you're about to: Hardcode a model version like gpt-5.2 or claude-sonnet-4-5 Use model names from memory without checking current availability Call APIs without checking if API keys are configured Skip new model classification when prompted STOP -> Read the appropriate cookbook file -> Use the fetch script Workflow Fetching Models 1. [ ] Determine which provider(s) you need models from 2. [ ] Check if cached model list exists: cache/models.json 3. [ ] If cache is fresh (< CACHETTLHOURS old), use cached data 4. [ ] If stale/missing, run: uv run python scripts/fetchmodels.py --force 5. [ ] CHECKPOINT: Verify no API errors in output 6. [ ] Use the model IDs as needed Checking for New Models 1. [ ] Run: uv run python scripts/checknewmodels.py --json 2. [ ] If new models found, review the output 3. [ ] For auto-classification: uv run python scripts/checknewmodels.py --auto 4. [ ] For interactive classification: uv run python scripts/checknewmodels.py 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/model-discovery