model-thaiLLM

Route Thai language tasks to specialized ThaiLLM models by detecting task intent.

1|Updated May 24, 2026

Search Tags:#telemetry #model routing #keyword matching #prompting #task classification #thaiLLM #api invocation

Ready to run

npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill model-thaillm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-thaiLLM
Source: https://github.com/tinner-deinno/innova-skills-lib/tree/main/core/model-thaiLLM
Command: npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill model-thaillm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of sending a task to the most suitable ThaiLLM model automatically, so you don’t waste time picking manually and you get better task-appropriate outputs.

Core Features & Use Cases

Auto-routing by task type: Routes requests to the correct model using a routing matrix based on keywords (e.g., code/debug vs. laws/regulations vs. business/reporting vs. academic/research).
Four specialized ThaiLLM models: Uses openthaigpt for technical/code logic, pathumma for legal/government language, typhoon for business/reporting summarization, and thalle for academic/thesis-style analysis.
Operational execution with telemetry: Calls the ThaiLLM API through the provided runner while logging token usage to a telemetry file for later auditing.

Quick Start

Use /model-thaiLLM to send your Thai task in natural language and let the skill select the best model automatically.

Frequently Asked Questions about model-thaiLLM

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

FAQPage Schema

How do I automatically route Thai language tasks to the right LLM model?▼

Auto-routing assigns Thai language tasks to the correct model by detecting keywords across code, legal, business, and academic scenarios. It matches task intent to specialized models, eliminating manual selection for better task-appropriate outputs.

Which ThaiLLM models are best suited for legal versus technical code tasks?▼

OpenThaiGPT handles technical code logic, while Pathumma processes legal and government language. Typhoon summarizes business reporting, and Thalle performs academic thesis-style analysis, ensuring the right model handles each specific domain.

What do I need to set up before calling the ThaiLLM API for task classification?▼

You need a THAILLM_TOKEN, network access to a reachable ThaiLLM API endpoint, and the configured runner script located at ~/Jit/limbs/thaillm.sh. This environment enables automatic routing and telemetry logging to token_log.jsonl.

Can I select a specific ThaiLLM model instead of using automatic task routing?▼

Yes, the skill supports explicit model selection alongside automatic routing. You can bypass the keyword matching matrix and directly invoke a specific model, or list all available models to choose the best fit for your task.

How does ThaiLLM telemetry logging track my API token usage?▼

Telemetry logging records API token usage to a token_log.jsonl file during execution. The runner script automatically logs consumption metrics for each invoked model, providing an audit trail for later analysis and operational tracking.

What happens if my Thai text prompt contains mixed business and academic keywords?▼

The routing matrix classifies mixed intent prompts using keyword matching across business, academic, code, and legal scenarios. It selects the dominant task category to route the request to the most appropriate specialized ThaiLLM model available.