fireworks-training

Name: fireworks-training
Author: fw-ai-external

github.com/fw-ai-externalDevelopment239149 installsUpdated 1d ago

About fireworks-training

fireworks-training is a collection of skills for routing Fireworks training work to research, configuration, or debugging guidance. It directs users to the appropriate skill rather than executing a training workflow itself.

Key features

01Separate research, configure, and debug skills
02Guidance for selecting methods and evaluation
03Training planning and run monitoring guidance
04Troubleshooting failed or low-quality runs

Use cases

01Choose a training method and evaluation approach
02Plan, run, or resume a training job
03Monitor or deploy a training run
04Diagnose a stuck or poor-quality run

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/fw-ai-external/cookbook --skill fireworks-training

After installing, type/fireworks-trainingin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/

deploy-and-troubleshoot.md

choose-method.md

async-rl-metrics.md

client-phase-tracing.md

execution-notes.md

cookbook-code.md

error-reference.md

getting-started.md

managed-rft-operations.md

models-shapes-and-cost.md

preference-data-and-evaluators.md

renderer.md

rft-agent-tracing.md

rl-dynamic-filter.md

renderer-verification.md

rl-concurrency.md

rl-gradient-accumulation.md

rl-custom-loss.md

rl-async.md

rl-agentic.md

rl-hotload.md

sdk-examples.md

sdk-setup.md

sdk-shapes.md

sdk-distillation.md

rl-sampling-timeouts.md

sdk-recipes.md

sdk-migrate.md

run-state-and-reporting.md

sdk-checkpoints.md

Details

From the project README

Fireworks training

This workflow is split into three focused skills:

Goal	Skill
Choose method, data, evaluation, and cookbook entry	`research`
Plan, run, monitor, deploy, or resume training	`configure`
Diagnose a failed, stuck, or low-quality run	`debug`

Do not execute a training workflow from this file. Route to the matching skill.

This directory also carries shared detailed references used by configure and debug. Cursor and Codex installs must include fireworks-training alongside the three entry skills.

Comments

Markdown supported

Details

Author: fw-ai-external
Repository: fw-ai-external/cookbook
Category: Development
Installs: 149
GitHub stars: 239

Report

More skills

All skills

remotion-render

github.com/inference-sh

1.6M

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

design-mobile-apps

github.com/designed-by-ai

1.3M

Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML

improve-codebase-architecture

github.com/mattpocock

1.2M

Scan a codebase for architecture improvement opportunities, present them as a visual HTML report, then dive deep into whichever one you pick.

vercel-react-best-practices

github.com/vercel-labs

876.8k

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.