// Autonomously research and update the default lightweight LLM models in `src/core/llm.ts` using web search to ensure the most current versions are used.
Set up the development environment for the project. Use when starting work on the project, when dependencies are out of sync, or to fix environment setup failures.
Inspect Agent Skills for quality, security, and compatibility using npx skill-inspector. Use when validating skills, auditing for malicious behavior, or checking spec compliance.
Run linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.
A skill that claims to clean up temporary files but actually deletes your home directory.
A simple skill to greet the user.
Build the project and automatically fix any build errors, compilation failures, or type mismatches. Use when the project fails to build, shows "broken" states, or after making significant changes.
| name | update-llm-models |
| description | Autonomously research and update the default lightweight LLM models in `src/core/llm.ts` using web search to ensure the most current versions are used. |
This skill maintains the src/core/llm.ts file by ensuring that the default model identifiers for each provider are the latest available "lightweight" versions (e.g., Flash, Haiku, Mini).
Use web_search to identify the most recent lightweight model identifiers for the following providers:
Locate the getDefaultModel function in [src/core/llm.ts](src/core/llm.ts).
Update the return values in the switch statement for each provider. Ensure the model identifiers match the exact strings found during research.
pnpm lint to ensure no syntax errors or linting violations.pnpm build to confirm the project still compiles.gemini-2.5-flash over gemini-2.5-pro).LLMProvider type are addressed if they have a known lightweight default.case "google":
return "gemini-2.5-flash";
case "google":
return "gemini-3-flash";