⌁ MCP Servers ⌁ Agent Skills ⌁ Plugins ⌁ Repos

Agent Skills

Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.

✦ Standalone skills4,642

Self-contained. Install one into any project and it works on its own — no other software needed.

🧰 Tool add-ons1,006

Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.

Overview All Cloud Service Cloud Storage Communication Database Design Development File System Finance Marketing Memory Other Productivity Search Version Control Web Scraping

microsoft · Official

2,091 standalone skills

evaluating-code-models

by firecrawl

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

🔥🔥🔥FreeQuick setup

nemo-evaluator-sdk

by firecrawl

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

🔥🔥🔥FreeQuick setup

optimizing-attention-flash

by firecrawl

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.

🔥🔥🔥FreeQuick setup

qdrant-vector-search

by firecrawl

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

🔥🔥🔥FreeQuick setup

speculative-decoding

by firecrawl

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

🔥🔥🔥FreeQuick setup

deepspeed

by firecrawl

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

🔥🔥🔥FreeQuick setup

llama-factory

by 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

🔥🔥🔥FreeQuick setup

pinecone

by firecrawl

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

🔥🔥🔥FreeQuick setup

audiocraft-audio-generation

by firecrawl

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

🔥🔥🔥FreeQuick setup

axolotl

by firecrawl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

🔥🔥FreeQuick setup

evaluating-llms-harness

by firecrawl

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

🔥🔥🔥FreeQuick setup

faiss

by firecrawl

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

🔥🔥🔥FreeQuick setup

lambda-labs-gpu-cloud

by firecrawl

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

🔥🔥🔥FreeQuick setup

llama-cpp

by 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 unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

🔥🔥🔥✓ VerifiedFreeAdvanced setup

miles-rl-training

by firecrawl

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.

🔥🔥🔥FreeQuick setup

ml-paper-writing

by firecrawl

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

🔥🔥🔥FreeQuick setup

nemo-curator

by firecrawl

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

🔥🔥🔥✓ VerifiedFreeNeeds API keys

segment-anything-model

by firecrawl

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

🔥🔥🔥FreeQuick setup

sentencepiece

by firecrawl

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

🔥🔥🔥✓ VerifiedFreeNeeds API keys

transformer-lens-interpretability

by firecrawl

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

🔥🔥🔥FreeQuick setup

verl-rl-training

by firecrawl

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.

🔥🔥🔥FreeQuick setup

autogpt-agents

by firecrawl

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

🔥🔥🔥FreeQuick setup

clip

by firecrawl

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

🔥🔥🔥FreeQuick setup

crewai-multi-agent

by firecrawl

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

🔥🔥🔥FreeQuick setup

gguf-quantization

by firecrawl

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.

🔥🔥🔥FreeQuick setup

grpo-rl-training

by firecrawl

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

🔥🔥🔥FreeQuick setup

guidance

by firecrawl

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

🔥🔥🔥FreeQuick setup

hqq-quantization

by firecrawl

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.

🔥🔥🔥FreeQuick setup

knowledge-distillation

by firecrawl

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

🔥🔥🔥FreeQuick setup

mamba-architecture

by firecrawl

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

🔥🔥🔥FreeQuick setup

← PrevPage 67 of 70Next →