kiln-check-deprecation

Audit Kiln's model list for deprecated or sunset models across all providers.

5.0k|376|Updated Jul 23, 2024
One-click install
npx skills add https://github.com/Kiln-AI/Kiln --skill kiln-check-deprecation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kiln-check-deprecation
Source: https://github.com/Kiln-AI/Kiln/tree/main/.agents/skills/kiln-check-deprecation
Command: npx skills add https://github.com/Kiln-AI/Kiln --skill kiln-check-deprecation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

AI providers regularly deprecate, remove, or sunset models, leaving stale entries in Kiln's model registry that break user workflows. This Skill automates the audit of ml_model_list.py against live provider APIs to find and flag outdated models.

Core Features & Use Cases

  • Multi-Provider Availability Checks: Queries model-listing endpoints for OpenRouter, OpenAI, Anthropic, Gemini, Fireworks, Together, SiliconFlow, Cerebras, Groq, and Vertex AI, handling each provider's API quirks automatically.
  • Expiration and Lifecycle Detection: Surfaces OpenRouter models with upcoming expiration dates and Bedrock models with LEGACY lifecycle status, plus LiteLLM deprecation_date cross-referencing.
  • Safe Deprecation Marking: Sets deprecated=True on confirmed-removed provider entries only after user confirmation, never deleting models.
  • Use Case: Before a Kiln release, run the audit to discover that gemini-1.5-pro was removed from the Gemini API, then mark its provider entries deprecated so users stop selecting a dead model.

Quick Start

Ask the AI to check Kiln's model list for deprecated or sunset models across all providers and report which entries should be marked deprecated.

Frequently Asked Questions about kiln-check-deprecation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check which AI models have been deprecated by providers?

Run the extraction script to pull Kiln's published model list, then run check_provider.py with a provider name or 'all' to compare each model_id against the provider's live model-listing API. Missing models are reported as candidates for deprecation.

How to detect expiring models on OpenRouter?

The check script reads OpenRouter's public model API, which includes expiration_date fields, and reports any Kiln models expiring within the near term. Expiring models are flagged for user review but not automatically marked deprecated.

Does the deprecation check require API keys for every provider?

Most providers need their API key set as an environment variable sourced from .env, such as OPENAI_API_KEY or ANTHROPIC_API_KEY. OpenRouter is public and needs no key, while Vertex AI requires gcloud CLI authentication; providers without credentials are skipped.

Can this skill check Amazon Bedrock model deprecation?

Bedrock is not covered by the automated script and must be checked manually using the aws CLI list-foundation-models command. Models with LEGACY lifecycle status or approaching endOfLifeTime should be marked deprecated.

Why are some providers like Ollama skipped during the audit?

Providers such as ollama, docker_model_runner, kiln_fine_tune, openai_compatible, and azure_openai are skipped because they are local, user-managed, internal, or mirror other providers, so they have no meaningful upstream deprecation signal to check.