Agent skills

Skills you can use with AI coding agents, indexed from public GitHub repositories.

Latest Most Popular

publish-package-cicd CI/CD publishing workflow for npm packages using Changesets + npm Trusted Publishers (OIDC). Use when setting up automated npm publishing for monorepos, configuring GitHub Actions for releases, troubleshooting workspace:* protocol resolution issues, fixing "Cannot find module" errors in published packages, or debugging npm OIDC authentication. Covers Bun + Turborepo + Changesets + npm Trusted Publishers with workspace protocol resolution.
joelhooks/swarm-tools 603
release Handles version bumps and npm releases for the swarm-tools monorepo (opencode-swarm-plugin, claude-code-swarm-plugin, swarm-mail, swarm-queue). Use when: creating changesets, bumping versions, preparing releases, checking release status, debugging publish failures, verifying npm packages, or merging release PRs. Triggers: "release", "publish", "changeset", "bump version", "ship it", "new version", "create a release", "check npm", "verify publish", "/release"
joelhooks/swarm-tools 603
open-prose OpenProse is a programming language for AI sessions. Activate on ANY `prose` command (prose boot, prose run, prose compile, prose wire, prose update, etc.), running .prose or .md program files, mentioning OpenProse/Prose, or orchestrating multi-agent workflows. The skill intelligently interprets what the user wants.
openprose/prose 1,006
autoresearch 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 steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Orchestra-Research/AI-Research-SKILLs 6,644
nemo-curator 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.
Orchestra-Research/AI-Research-SKILLs 6,644
ray-data 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 inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
Orchestra-Research/AI-Research-SKILLs 6,644
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
Orchestra-Research/AI-Research-SKILLs 6,644
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
Orchestra-Research/AI-Research-SKILLs 6,644
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
Orchestra-Research/AI-Research-SKILLs 6,644
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
Orchestra-Research/AI-Research-SKILLs 6,644
huggingface-tokenizers 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 padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Orchestra-Research/AI-Research-SKILLs 6,644
sentencepiece 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.
Orchestra-Research/AI-Research-SKILLs 6,644
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.
Orchestra-Research/AI-Research-SKILLs 6,644
awq-quantization 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 accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Orchestra-Research/AI-Research-SKILLs 6,644
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.
Orchestra-Research/AI-Research-SKILLs 6,644
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.
Orchestra-Research/AI-Research-SKILLs 6,644
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.
Orchestra-Research/AI-Research-SKILLs 6,644
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.
Orchestra-Research/AI-Research-SKILLs 6,644
skypilot-multi-cloud-orchestration 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 providers.
Orchestra-Research/AI-Research-SKILLs 6,644
lambda-labs-gpu-cloud 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.
Orchestra-Research/AI-Research-SKILLs 6,644
modal-serverless-gpu Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
Orchestra-Research/AI-Research-SKILLs 6,644
mamba-architecture 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.
Orchestra-Research/AI-Research-SKILLs 6,644
nanogpt 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 Shakespeare (CPU) or OpenWebText (multi-GPU).
Orchestra-Research/AI-Research-SKILLs 6,644
rwkv-architecture 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 2025). Models up to 14B parameters.
Orchestra-Research/AI-Research-SKILLs 6,644