claudecodex

fireworks-training

Skills for research, configuration, debugging, and migration of Tinker training loops to Fireworks.

241 on GitHubby Fireworks AIv2.3.0Apache-2.0updated today
/

Plugin fireworks-training from marketplace fw-ai-cookbook in fw-ai-external/cookbook. Commands read from the repo's manifest — today.

What it installs

Skills (8)

  • configure

    Plan, run, and monitor Fireworks training from a coding agent. Covers managed SFT, DPO, ORPO, and RFT plus Training API serverless and dedicated workflows, complete cost and parameter confirmation, active monitoring, checkpoints, deployment, resume, and teardown. Use for explicit train, fine-tune, d

  • debug

    Diagnose Fireworks training and deployment issues, including stuck or failed jobs, error messages, poor quality, checkpoint and resume problems, LoRA adapter load mismatches, and deployments that are ready but not serving. Use for systematic read-only triage before retrying. Use configure for a new

  • discover

    Deprecated redirect — use research instead. Renamed in v2.2.0 to match Tinker cookbook conventions. For exploring method, data, eval, and cookbook entries use research; for training execution use configure; for failures use debug.

  • fireworks-training

    Compatibility redirect and shared reference carrier for the Fireworks training skills. Use research to choose method, data, evaluation, and a cookbook entry; use configure to plan and run training; use debug for stuck, failed, or low-quality runs; use migrate-tinker to port an existing Tinker loop.

  • migrate-tinker

    Port a Tinker SDK or Tinker Cookbook training loop to the native Fireworks Training SDK. Adapt clients, data types, loss inputs, sampling, checkpoints, and cleanup while preserving the experiment. Use configure to launch or resume training and debug to investigate a running Fireworks job.

  • research

    Plan Fireworks post-training from a task-shaped goal — recommend a method, cookbook entry, data plan, and eval from what the user already said, ask only decision-critical questions, and hand off to configure when ready to train. Use when the user describes a problem in plain language, is unsure whic

  • caveman

    Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

  • design-taste-frontend

    tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict n

View source on GitHub docs.fireworks.ai

Similar plugins

ruflo-ruvllm

claude

RuVLLM local inference with chat formatting, MicroLoRA fine-tuning, and SONA adaptation

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

huggingface-skills

claude

Build, train, evaluate, and use open source AI models, datasets, and spaces.

26 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

llm-finetuning

claudecodex

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

wshobson/agents 42,461

DataRobot Agent Skills

claudecodex

DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and external agent monitoring.

19 skills

anthropics/knowledge-work-plugins 35,601

deep-learning-book

claude

Study companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.

1 skill · 3 commands · 1 agent

alirezarezvani/claude-skills 29,725

data-processing

claude

Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.

98 skills

Orchestra-Research/AI-Research-SKILLs 14,502

Maintain fireworks-training?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted