create-intent-map
Train LoRA adapters for converting natural language queries into structured QuerySpec JSON.
npx skills add majiayu000/claude-skill-registry --skill create-intent-map --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
--- name: create-intent-map description: > Train LoRA intent mappers for structured query generation using GRPO with execution feedback. Uses DeepSeek-R1-Distill-Qwen-7B as base model. Supports SFT warmup, GRPO training with ArangoDB rewards, and iterative improvement with automatic retry on eval failure. allowed-tools: Bash, Read triggers: - train intent mapper - intent map training - create intent model - lora training - query spec training - train query mapper - grpo training - execution feedback training metadata: short-description: GRPO training for intent mapping with execution feedback provides: - create-intent-map composes: [, task-monitor] --- # Create Intent Map Train LoRA adapters for converting natural language queries into structured QuerySpec JSON. Uses GRPO (Group Relative Policy Optimization) with execution feedback from ArangoDB. ## Training Approaches | Approach | Description | Use When | |----------|-------------|----------| | **GRPO (Recommended)** | RL with execution feedback | Production training | | **SFT Only** | Supervised fine-tuning | Quick baseline | | **Docker SFT** | Dockerized training | RunPod deployment | ## Quick Start (GRPO with Execution Feedback
- Training Approaches
- Quick Start (GRPO with Execution Feedback)
- Quick Start (Docker SFT - for RunPod)
- GRPO Training Pipeline
- Reward Functions
- Evaluation Thresholds
- Architecture
- Training Data Format
- Commands
- Data Preparation
- GRPO Training (Recommended)
- Docker SFT Training
- Utilities
- Configuration
cd .pi/skills/create-intent-map cp .env.example .env Edit .env with HF_TOKEN, CHUTES_API_KEY, ARANGO_* credentials View training progress TensorBoard (if enabled)
What does the create-intent-map skill do?
Train LoRA adapters for converting natural language queries into structured QuerySpec JSON.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill create-intent-map --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.