Kit Export Training — Data skill for Claude Code
OPT-IN export of your Claude Code sessions to redacted training JSONL — pick sessions, run the dataset builder with redaction ON, and get JSONL ready for the fine-tuning pipeline.
How to install Kit Export Training
Installs to ~/.claude/skills/jeiemgi-cckit-kit-export-training/SKILL.md
mkdir -p ~/.claude/skills/jeiemgi-cckit-kit-export-training && curl -fsSL https://raw.githubusercontent.com/jeiemgi/cckit/HEAD/commands/kit-export-training.md -o ~/.claude/skills/jeiemgi-cckit-kit-export-training/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Kit Export Training does
description: OPT-IN export of your Claude Code sessions to redacted training JSONL — pick sessions, run the dataset builder with redaction ON, and get JSONL ready for the fine-tuning pipeline. argument-hint: "[--match KEY ...] | [--sessions FILE ...] (default: current project)" allowed-tools: Bash, Read, AskUserQuestion
/kit-export-training — export sessions as redacted training data
Fine-tuning a local model on your own work only helps if the data leaves the machine clean. This is
Alternatives in Data
- Archify — Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self 17.2k ★
- Dummy Dataset — Generate realistic dummy datasets in CSV, JSON, or SQL 7.8k ★
- Pipeline Feature — Add a feature to the FFmpeg transcode pipeline following Tunarr's pipeline builder pattern 2.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Generate More Training Data
This command analyzes patterns in existing data files (CSV, JSONL) and generates additional synthetic training
Suganthans BigQuery MCP Server
BigQuery MCP server for Claude — query any BigQuery dataset in natural language, with built-in SEO analysis to
Faostat Export Dataset
Export clean, documented FAOSTAT data as xlsx + csv + data dictionary
Claude Code Tips
Provide ready-to-use plugins, hooks, and commands to enhance Claude Code sessions with data mining, automation
V Status
Render the state of a Compound V orchestrator run — pipeline phase plus a per-job status table — by reading st
Oddyssey Publish
Cut a release - inspect the last pushed tag, pick the bump (patch, minor, or major), then tag and push; the ta
Related Agents
ML Engineer
Use for ML/AI model work — training, fine-tuning, evaluation, RAG, agents, embeddings, evals, deployment, MLOp
Scaffold Torchtune
Sets up torchtune fine-tuning configurations for all runs in a designed experiment. Reads experiment_summary.y
Aiml Engineer
AI/ML integration specialist. Designs model pipelines (inference, fine-tuning, LoRA adapters), selects infrast