add-model
Standardizes adding and registering new LLMs in the Giselle codebase.
Install
mkdir -p .claude/skills/add-model && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2480" && unzip -o skill.zip -d .claude/skills/add-model && rm skill.zipInstalls to .claude/skills/add-model
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.
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.Key capabilities
- →Register new LLM providers and models
- →Configure pricing and token limits
- →Implement SDK transformations
- →Update UI properties panels
How it works
The skill provides a sequential checklist to update registries, pricing tables, and SDK transformations, followed by a mandatory validation suite.
Inputs & outputs
When to use add-model
- →Integrating a new GPT model
- →Adding support for an Anthropic Claude version
- →Configuring pricing and token limits for a new model
About this skill
Add Language Model
Add a new language model to the Giselle codebase with full system consistency.
Quick Start
- Gather model specifications (or search web for official docs)
- Update files in order listed below
- 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:
- Add to the enum (e.g.,
OpenAILanguageModelId) - Add regex catch for dated versions in
.catch()block - Create model instance and add to
modelsarray
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):
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)
When not to use it
- →Skipping validation tests
- →Adding models without provider-specific registry updates
Prerequisites
Limitations
- →Must pass all build, format, and test commands in order
- →Requires manual collection of model specifications
How it compares
It requires bidirectional node conversion and specific UI property panel updates, ensuring the model is fully integrated into the workflow designer.
Compared to similar skills
add-model side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| add-model (this skill) | 1 | 4mo | Review | Intermediate |
| unsloth | 15 | 8mo | No flags | Intermediate |
| llm-application-dev | 3 | 4mo | Review | Intermediate |
| book-sft-pipeline | 3 | 3mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
unsloth
zechenzhangAGI
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
llm-application-dev
skillcreatorai
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
book-sft-pipeline
muratcankoylan
This skill should be used when the user asks to "fine-tune on books", "create SFT dataset", "train style model", "extract ePub text", or mentions style transfer, LoRA training, book segmentation, or author voice replication.
fine-tuning-with-trl
davila7
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
huggingface-tokenizers
davila7
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
massgen-develops-massgen
massgen
Guide for using MassGen to develop and improve itself. This skill should be used when agents need to run MassGen experiments programmatically (using automation mode) OR analyze terminal UI/UX quality (using visual evaluation tools). These are mutually exclusive workflows for different improvement goals.