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

Dicklesworthstone
Dicklesworthstone/pi_agent_rust

chroma

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

文档处理后端与接口
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

outlines

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

开发工程师Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

instructor

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

数据分析师Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

资料检索与研究Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

dspy

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

开发工程师Skill与智能体开发
★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

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.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

grpo-rl-training

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

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

hqq-quantization

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

gptq

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

optimizing-attention-flash

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

★ 2.0k
Dicklesworthstone
Dicklesworthstone/pi_agent_rust

quantizing-models-bitsandbytes

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

★ 2.0k