Skip to main content
The fireworks-training skill helps coding agents configure, run, and troubleshoot training jobs using current Fireworks best practices.

​
Install

​
Claude Code

Install the auto-updating cookbook plugin:

​
Cursor

​
Codex

​
Other compatible agents

Install to every detected Agent Skills-compatible harness:
Skills installed with npx skills do not update automatically. Refresh them with npx --yes skills update -g -y.

​
Prerequisites

  • Fireworks CLI (firectl) installed. Authenticate with either firectl signin or FIREWORKS_API_KEY.
  • Export FIREWORKS_API_KEY for Training API Python workflows.

​
What it does

Ask in plain language, for example “Fine-tune qwen3-4b on my train.jsonl and deploy it.” The skill configures the job, validates inputs, runs it, and helps troubleshoot failures. Before creating cost or resources, it shows the resolved parameters and estimated cost for confirmation.

​
Usage data and privacy

To improve the skill, authenticated API calls include the skill version and a random session ID. Fireworks uses this metadata with existing account and training job records for internal product analytics. Prompts and datasets are not collected, and usage data is not shared outside Fireworks.
The Fireworks CLI (firectl) may block mutating commands inside an AI-agent environment. When that happens, the skill gives you the exact command to run manually, then resumes monitoring and reporting.
Use managed fine-tuning for standard jobs, or the Training API for custom loops on serverless or dedicated infrastructure.

​
See also

Managed Fine-Tuning

Drive the same training infra directly when you know your config.

Training API

Write your own Python training loop on Fireworks GPUs.

Choose infrastructure

Compare serverless and dedicated training.

CLI reference

Automate managed training with firectl.

API reference

Automate managed training through REST APIs.

Cookbook

Ready-to-run recipes, including the inline-reward RL loop.