GITHUB AGENT SKILLS / 技能收录

给你的 AI 助手
装上专业技能

我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

qhjqhj00
qhjqhj00/research-skills-pool

ray-train

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

pytorch-lightning

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

pytorch-fsdp2

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

training-llms-megatron

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

deepspeed

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

huggingface-accelerate

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

prompt-guard

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

nemo-guardrails

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

llamaguard

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

constitutional-ai

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

miles-rl-training

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

★ 3
qhjqhj00
qhjqhj00/research-skills-pool

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

★ 3