# Fireworks 发布了 Training Skill，使编码代理能通过自然语言配置、运行和故障排除训练作业

- 来源：Fireworks AI
- 发布时间：2026-08-11 04:07
- AIWatch 分数：64
- AIWatch 标记：未精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01kzppt0dgja6sjc3pjxrywand
- 原文链接：https://x.com/FireworksAI_HQ/status/2086907308106535400

## 精选理由

常规快讯，保留列表

## AI 摘要

Fireworks 发布了 Training Skill，使编码代理能通过自然语言配置、运行和故障排除训练作业。

## 正文

Training

Install the Fireworks training skill for your coding agent.

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:

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.

Use managed fine-tuning for standard jobs, or the Training API for custom loops on serverless or dedicated infrastructure.

See also