adding-models
Guidance on integrating new LLM models into Letta Code, including model configuration and validation.
Install
mkdir -p .claude/skills/adding-models && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4248" && unzip -o skill.zip -d .claude/skills/adding-models && rm skill.zipInstalls to .claude/skills/adding-models
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update the model configuration. Covers models.json configuration, CI test matrix, and handle validation.Key capabilities
- →Query the Letta API for available model handles
- →Add new model entries to src/models.json
- →Configure model-specific settings like context window and temperature
- →Test new models using a headless command
- →Include models in the CI test matrix for automated testing
- →Understand automatic toolset assignment based on provider prefixes
How it works
The skill guides the user to query the Letta API for valid model handles, then add these details to the models.json configuration file, and optionally update the CI test matrix.
Inputs & outputs
When to use adding-models
- →Add new LLM provider
- →Update model configuration
- →Validate model handle support
- →Add model to CI test matrix
About adding-models
This skill guides the user through the process of registering new LLM models in Letta Code. It covers updating `models.json`, defining model handles, and configuring CI testing.
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update the model configuration. Covers models.json configuration, CI test matrix, and handle validation.
When not to use it
- →When the task involves modifying toolset detection logic for existing providers
Limitations
- →Toolset detection logic modification is rarely needed
- →The skill does not cover adding new providers for toolset detection
How it compares
This skill provides a structured workflow for integrating new LLM models into Letta Code, unlike manually editing configuration files without validation or testing guidance.
Compared to similar skills
adding-models side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| adding-models (this skill) | 1 | 10mo | Review | Beginner |
| skill-creator | 128 | 6mo | Review | Advanced |
| skill-development | 17 | 12mo | Review | Intermediate |
| agent-identifier | 15 | 12mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by letta-ai
View all by letta-ai →You might also like
skill-creator
anthropics
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
skill-development
anthropics
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
agent-identifier
anthropics
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
llama-factory
zechenzhangAGI
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
dify-dsl-generator
wwwzhouhui
专业的 Dify 工作流 DSL/YML 文件生成器,根据用户业务需求自动生成完整的 Dify 工作流配置文件,支持各种节点类型和复杂工作流逻辑
character-generator
Dexploarer
Generate complete elizaOS character configurations with personality, knowledge, and plugin setup. Triggers when user asks to "create character", "generate agent config", or "build elizaOS character"