Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills2,933
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons726
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
axolotl
✓★ 11by firecrawl
axolotl — an installable skill for AI agents, published by firecrawl/ai-research-skills.
llama-cpp
✓★ 11by firecrawl
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is…
ray-data
✓★ 11by firecrawl
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch,…
speculative-decoding
✓★ 11by firecrawl
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…
tensorrt-llm
✓★ 11by firecrawl
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need…
pytorch-lightning
✓★ 11by firecrawl
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from…
llamaindex
✓★ 11by firecrawl
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices,…
llamaguard
✓★ 11by firecrawl
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm,…
langchain
✓★ 11by firecrawl
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct…
chroma
✓★ 11by firecrawl
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function…
clip
✓★ 11by firecrawl
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M…
deepspeed
✓★ 11by firecrawl
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
dspy
✓★ 11by firecrawl
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's…
gptq
✓★ 11by firecrawl
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…
grpo-rl-training
✓★ 11by firecrawl
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
guidance
✓★ 11by firecrawl
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance…
instructor
✓★ 11by firecrawl
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream…
knowledge-distillation
✓★ 11by firecrawl
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance,…
llama-factory
✓★ 11by firecrawl
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
llava
✓★ 11by firecrawl
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language…
long-context
✓★ 11by firecrawl
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+…
mlflow
✓★ 11by firecrawl
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML…
model-merging
✓★ 11by firecrawl
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific…
model-pruning
✓★ 11by firecrawl
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50%…
moe-training
✓★ 11by firecrawl
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense…
outlines
✓★ 11by firecrawl
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize…
pinecone
✓★ 11by firecrawl
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces.…
prompt-guard
✓★ 11by firecrawl
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).…
pytorch-fsdp2
✓★ 11by firecrawl
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when…
sentence-transformers
✓★ 11by firecrawl
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval.…