Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

hugging-face-cli-workflows

Estrelas63

Forks16

Atualizado15 de junho de 2026 às 13:42

Use when working with Hugging Face CLI or Hub workflows for TRL training, including auth, repositories, uploads, downloads, Jobs, buckets, model persistence, dataset checks, Space links, and remote artifact movement.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

burtenshaw

burtenshaw/training-agents

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

Explorador de arquivos

4 arquivos

SKILL.md

readonly

name	hugging-face-cli-workflows
description	Use when working with Hugging Face CLI or Hub workflows for TRL training, including auth, repositories, uploads, downloads, Jobs, buckets, model persistence, dataset checks, Space links, and remote artifact movement.

Hugging Face CLI Workflows

Use this skill for Hub, CLI, Jobs, buckets, and artifact workflows around TRL training.

Workflow

Check auth with hf auth whoami before remote actions.
Identify the target type: model repo, dataset repo, Space, Job, or bucket.
Keep scripts portable: remote Jobs cannot read local files unless the script is uploaded, inlined, or available by URL.
Ensure ephemeral runners push or upload artifacts before completion.
Summarize exact repo ids, job ids, paths, and commands.

Safety

Never print HF_TOKEN or credentials.
Use private repos or buckets for non-public data by default.
Confirm before deleting or overwriting Hub artifacts.
Keep large checkpoints outside this context repository.

References

references/hub-workflows.md: auth, repos, upload/download, and artifacts.
references/jobs-workflows.md: HF Jobs conventions for TRL runs.

Mais deste repositório

mesmo repositório

agentic-self-distillation

burtenshaw/training-agents

Use when designing or reviewing self-distillation workflows for agentic models, including trace collection, teacher or judge feedback, rejection sampling, critique, conversion to SFT or preference data, iterative TRL training loops, and safeguards against self-reinforcing errors.

2026-06-1563

openenv-agentic-rl

burtenshaw/training-agents

Use when designing, reviewing, or implementing OpenEnv-style environment interfaces for agentic RL with TRL, including reset/step/state contracts, tasksets, Docker or HTTP/WebSocket serving, MCP compatibility, reward separation, and GRPO environment rollouts.

2026-06-1563

trackio-observability

burtenshaw/training-agents

Use when instrumenting or inspecting TRL training runs with Trackio, run names, metric schemas, dashboards, logs, grep or ripgrep, SFTP, Hugging Face Job logs, remote artifacts, or experiment result summaries.

2026-06-1563

trl-post-training

burtenshaw/training-agents

Use when building, reviewing, or editing TRL post-training workflows for agentic applications, including SFT, DPO, GRPO, RLOO, reward modeling, dataset formats, chat templates, assistant/completion-only losses, tool-calling data, reward functions, and challenge progression from SFT to environment-based RL.

2026-06-1563

trl-sft

burtenshaw/training-agents

Use when designing, implementing, reviewing, or debugging supervised fine-tuning with TRL SFTTrainer or `trl sft`, especially for agentic models trained on chat messages, prompt/completion data, tool-calling examples, assistant-only loss, completion-only loss, LoRA/PEFT adapters, Trackio logging, or agent trace datasets such as `julien-c/synthtraces`.

2026-06-1563

name	hugging-face-cli-workflows
description	Use when working with Hugging Face CLI or Hub workflows for TRL training, including auth, repositories, uploads, downloads, Jobs, buckets, model persistence, dataset checks, Space links, and remote artifact movement.

Hugging Face CLI Workflows

Use this skill for Hub, CLI, Jobs, buckets, and artifact workflows around TRL training.

Workflow

Check auth with hf auth whoami before remote actions.
Identify the target type: model repo, dataset repo, Space, Job, or bucket.
Keep scripts portable: remote Jobs cannot read local files unless the script is uploaded, inlined, or available by URL.
Ensure ephemeral runners push or upload artifacts before completion.
Summarize exact repo ids, job ids, paths, and commands.

Safety

Never print HF_TOKEN or credentials.
Use private repos or buckets for non-public data by default.
Confirm before deleting or overwriting Hub artifacts.
Keep large checkpoints outside this context repository.

References

references/hub-workflows.md: auth, repos, upload/download, and artifacts.
references/jobs-workflows.md: HF Jobs conventions for TRL runs.