AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Paper Figure

  by @wanshuiyin

  Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

• Mermaid Diagram

  by @wanshuiyin

  Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.

• Monitor Experiment

  by @wanshuiyin

  Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

• Paper Poster

  by @wanshuiyin

  DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.

• Auto Tmux

  by @tradecatlabs

  tmux 自动化操控：用 scripts/auto-tmux.sh 安全读取、发送、巡检、救援、录制 session|window|pane，用 swarm-state.sh 管理蜂群任务/锁/状态，并基于 oh-my-tmux 组织多 AI 终端协作。触发：capture-pane、send-keys、批量巡检、蜂群 AI 协作、卡死救援、tmux 工作台初始化。

• Auto Skill

  by @tradecatlabs

  Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.

• Auditing Foundry Smart Contract Security

  by @tradecatlabs

  Pre-deployment security audit of Solidity smart contracts in a Foundry project. Combines static analysis (Slither, Aderyn), symbolic execution (Mythril), and property-based testing (forge fuzz + invariant tests with handlers) to…

• Web3 Hunt Zksync Era

  by @tradecatlabs

  ZKsync Era (Immunefi) completed hunt — 0 findings after exhaustive 5-session audit. Use as a DEFENSE STUDY — learn what makes a protocol unhuntable, which patterns block all 10 bug classes, and when to abandon a target. Contains…

• Web3 Bug Classes

  by @tradecatlabs

  Complete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation,…

• Web3 Triage Report

  by @tradecatlabs

  Bug triage validation system, Immunefi report format, and 20 real paid bounty examples dissected. Use this when validating a finding before submitting, writing an Immunefi report, checking if a bug is actually valid, or studying…

• Web3 Solidity Audit Mcp

  by @tradecatlabs

  MCP server integrating Slither + Aderyn + SWC patterns into Claude Code for smart contract auditing. Use when analyzing Solidity files, running DeFi-specific detectors, or generating invariants. 10 MCP tools, 86 SWC detectors,…

• Web3 Methodology Research

  by @tradecatlabs

  External research synthesis from Trail of Bits, SlowMist, ConsenSys, Immunefi, and Cyfrin. Use this for advanced audit methodology, Echidna/Medusa fuzzing setup, Slither custom detector writing, attack pattern deep dives, or the…

• Web3 Poc Foundry

  by @tradecatlabs

  Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for…

• Web3 Hunt Foundation

  by @tradecatlabs

  Hunter mindset, recon setup, and target scoring for Web3 bug bounty. Use at the START of any new protocol hunt - scoring targets, setting up environment, understanding architecture.

• Web3 Grep Arsenal

  by @tradecatlabs

  Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific vulnerability classes.

• Web3 Ai Tools

  by @tradecatlabs

  AI-powered tools for Web3 bug bounty automation. Use when you want to automate recon, run autonomous audits, or use AI agents for vulnerability discovery.

• Web3 Case Study Role Misconfig

  by @tradecatlabs

  Case study - role misconfiguration bug class applied to a yield aggregator protocol. Use as a template for applying all 10 bug classes to a single target.

• Web3 Start Here

  by @tradecatlabs

  Master index for the web3 smart contract security knowledge base. Use this to navigate the skill chain. Read files in order — each ends with NEXT.

• Guided Tour

  by @wasp-lang

  Take a guided tour of Open SaaS — walks you through step-by-step through the project structure, features, and customization checklist.

• Getting Started

  by @wasp-lang

  Get started with your Open SaaS project — fetches docs, checks Wasp installation, and helps you start your database and app.

• Add Wasp Skills

  by @wasp-lang

  Install Wasp agent skills (plugins) that add Wasp knowledge and best practices to your AI coding tools.

• Videocaptioner

  by @WEIFENG2333

  Process video subtitles — transcribe speech, optimize/translate text, burn styled subtitles into video. Use when you need to add subtitles to a video, transcribe audio, translate subtitles, or customize subtitle styles.

• Wiki Retrieve

  by @AgriciDaniel

  Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic…

• Skill Builder

  by @yusufkaraaslan

  Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

• Release Announcement

  by @NanmiCoder

  从本项目最新的 release-notes Markdown 制作微信群发布短文案与竖版长图，核验贡献者 GitHub ID 并嵌入真实头像。用于版本发布宣传，不负责创建或发布 GitHub Release。

• Verify

  by @NanmiCoder

  Verify a code change does what it should by running the app.

• Drive Mimo

  by @XiaomiMiMo

  Use when developing or testing the MiMoCode repository and you need to programmatically drive another MiMoCode (mimo) process. Supports headless `mimo run` with JSON events and interactive TUI via tmux for behavior, integration,…

• Effect

  by @XiaomiMiMo

  Answer questions about the Effect framework

• Ml Paper Writing

  by @Orchestra-Research

  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. For systems venues…

• Systems Paper Writing

  by @Orchestra-Research

  Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates,…

• Fine Tuning Serving Openpi

  by @Orchestra-Research

  Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom…

• Fine Tuning Openvla Oft

  by @Orchestra-Research

  Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when…

• Ara Compiler

  by @Orchestra-Research

  Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical…

• Ara Research Manager

  by @Orchestra-Research

  Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into…

• Academic Plotting

  by @Orchestra-Research

  Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results…

• Outlines

  by @Orchestra-Research

  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…

• Instructor

  by @Orchestra-Research

  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

• Guidance

  by @Orchestra-Research

  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

• Dspy

  by @Orchestra-Research

  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

• Evaluating Cosmos Policy

  by @Orchestra-Research

  Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference…

• Qdrant Vector Search

  by @Orchestra-Research

  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…

• Ara Rigor Reviewer

  by @Orchestra-Research

  Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological…

• Sentence Transformers

  by @Orchestra-Research

  Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for…

• Faiss

  by @Orchestra-Research

  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…

• Chroma

  by @Orchestra-Research

  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…

• Pinecone

  by @Orchestra-Research

  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…

• Presenting Conference Talks

  by @Orchestra-Research

  Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems…

• Creative Thinking For Research

  by @Orchestra-Research

  Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint…

• Brainstorming Research Ideas

  by @Orchestra-Research

  Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.

• Prompt Master

  by @nidhinjs

  Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not…

• Pytorch Fsdp2

  by @Orchestra-Research

  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…

• Deepspeed

  by @Orchestra-Research

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

• Autoresearch

  by @Orchestra-Research

  Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and…

• Evolving Ai Agents

  by @Orchestra-Research

  Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or…

• Ml Training Recipes

  by @Orchestra-Research

  Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed…

• Llama Factory

  by @Orchestra-Research

  Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

• Huggingface Tokenizers

  by @Orchestra-Research

  Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle…

• Training Llms Megatron

  by @Orchestra-Research

  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…

• Evaluating Llms Harness

  by @Orchestra-Research

  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…

• Nemo Evaluator Sdk

  by @Orchestra-Research

  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…

• Implementing Llms Litgpt

  by @Orchestra-Research

  Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production…

• Fine Tuning With Trl

  by @Orchestra-Research

  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…

• Distributed Llm Pretraining Torchtitan

  by @Orchestra-Research

  Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile,…

• Openrlhf Training

  by @Orchestra-Research

  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…

• Axolotl

  by @Orchestra-Research

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

• Unsloth

  by @Orchestra-Research

  Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

• Crewai Multi Agent

  by @Orchestra-Research

  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…

• Evaluating Code Models

  by @Orchestra-Research

  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…

• Gptq

  by @Orchestra-Research

  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×…

• Tensorrt Llm

  by @Orchestra-Research

  Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with…

• Sglang

  by @Orchestra-Research

  Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix…

• Quantizing Models Bitsandbytes

  by @Orchestra-Research

  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…

• Huggingface Accelerate

  by @Orchestra-Research

  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…

• Simpo Training

  by @Orchestra-Research

  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…

• Nanogpt

  by @Orchestra-Research

  Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on…

• Pytorch Lightning

  by @Orchestra-Research

  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…

• Llama Cpp

  by @Orchestra-Research

  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…

• Rwkv Architecture

  by @Orchestra-Research

  RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March…

• Mamba Architecture

  by @Orchestra-Research

  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).…

• Weights And Biases

  by @Orchestra-Research

  Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

• Tensorboard

  by @Orchestra-Research

  Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

• Mlflow

  by @Orchestra-Research

  Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

• Nemo Curator

  by @Orchestra-Research

  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…

• Sentencepiece

  by @Orchestra-Research

  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…

• Optimizing Attention Flash

  by @Orchestra-Research

  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…

• Awq Quantization

  by @Orchestra-Research

  Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better…

• Peft Fine Tuning

  by @Orchestra-Research

  Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for…

• Ray Data

  by @Orchestra-Research

  Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch…

• Transformer Lens Interpretability

  by @Orchestra-Research

  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…

• Sparse Autoencoder Training

  by @Orchestra-Research

  Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or…

• Nnsight Remote Interpretability

  by @Orchestra-Research

  Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU…

• Pyvene Interventions

  by @Orchestra-Research

  Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing…

• Hqq Quantization

  by @Orchestra-Research

  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…

• Torchforge Rl Training

  by @Orchestra-Research

  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…

• Miles Rl Training

  by @Orchestra-Research

  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…

• Skypilot Multi Cloud Orchestration

  by @Orchestra-Research

  Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across…

• Lambda Labs Gpu Cloud

  by @Orchestra-Research

  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.

• Slime Rl Training

  by @Orchestra-Research

  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.

• Gguf Quantization

  by @Orchestra-Research

  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.

• Autogpt Agents

  by @Orchestra-Research

  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.