Agent skill

add-model

Add a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system.

Stars 510
Forks 119

Install this agent skill to your Project

npx add-skill https://github.com/giselles-ai/giselle/tree/main/.claude/skills/add-model

SKILL.md

Add Language Model

Add a new language model to the Giselle codebase with full system consistency.

Quick Start

  1. Gather model specifications (or search web for official docs)
  2. Update files in order listed below
  3. Run validation: pnpm format && pnpm build-sdk && pnpm check-types && pnpm tidy && pnpm test

Required Information

Before starting, collect:

  • Provider: openai, anthropic, or google
  • Model ID: e.g., "gpt-5.3", "claude-opus-5"
  • Context window: Maximum input tokens
  • Max output tokens: Maximum output tokens
  • Knowledge cutoff: Date of training data cutoff
  • Pricing: Input/output cost per million tokens
  • Capabilities: Reasoning, image input, web search, etc.
  • Configuration options: Reasoning effort levels, verbosity, temperature, etc.

Files to Update (In Order)

1. Language Model Registry (Primary Definition)

File: packages/language-model-registry/src/{provider}.ts

Add the model definition. See REGISTRY.md for detailed examples.

2. Language Model Package

File: packages/language-model/src/{provider}.ts

Update three locations:

  1. Add to the enum (e.g., OpenAILanguageModelId)
  2. Add regex catch for dated versions in .catch() block
  3. Create model instance and add to models array

See LANGUAGE-MODEL.md for detailed examples.

3. Model Pricing

File: packages/language-model/src/costs/model-prices.ts

Add pricing entry to the appropriate table. See PRICING.md.

4. AI SDK Transformation

File: packages/giselle/src/generations/v2/language-model/transform-giselle-to-ai-sdk.ts

Add model ID to the switch case for the provider.

5. Node Conversion

File: packages/node-registry/src/node-conversion.ts

Add bidirectional conversion:

  • Short to full: case "model-id": return "provider/model-id";
  • Full to short: case "provider/model-id": return "model-id";

6. UI Configuration (If Needed)

File: internal-packages/workflow-designer-ui/src/editor/properties-panel/text-generation-node-properties-panel/model/{provider}.tsx

Update if model has unique configuration options. See UI-CONFIG.md.

Validation Checklist

Run these commands in order (all must pass):

bash
pnpm format      # Format code
pnpm build-sdk   # Build SDK packages
pnpm check-types # Verify types
pnpm tidy        # Check for unused code
pnpm test        # Run all tests

Provider-Specific Patterns

See detailed patterns for each provider:

  • OPENAI.md - OpenAI models (GPT-5.x family)
  • ANTHROPIC.md - Anthropic models (Claude family)
  • GOOGLE.md - Google models (Gemini family)

Expand your agent's capabilities with these related and highly-rated skills.

davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore
davila7/claude-code-templates

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

23,776 2,298
Explore
davila7/claude-code-templates

Claude Code Guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

23,776 2,298
Explore
davila7/claude-code-templates

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

23,776 2,298
Explore
davila7/claude-code-templates

behavioral-modes

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results