AIPM
Theme

Claude Code, Codex, and Cursor

Agent skills for Claude Code, Codex, and Cursor

Find skills that work in Claude Code, Codex, and Cursor. See what each one does, look at its files, then install it with one command.

Browse all skills

Category
Tool
Intent

20 skills loaded

Microsoft/airunway-aks-setup

Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: \"setup AI Runway\", \"onboard AKS cluster\", \"install AI Runway\...

Published by Microsoft

skillScanned · no issues★ 1.6KImported · UnverifiedAll toolsOct 14, 2026, 1:18 AM9.53 KBMIT

Imported from source. Claim this skill

Orchestra Research/slime

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.

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:18 AM10.3 KBMIT

Imported from source. Claim this skill

Orchestra Research/skypilot

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.

Published by Orchestra Research

skillScanned · flagged★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:18 AM10.2 KBMIT

Imported from source. Claim this skill

Orchestra Research/simpo

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 simpl...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:17 AM11.1 KBMIT

Imported from source. Claim this skill

Orchestra Research/sglang

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 sharing....

Published by Orchestra Research

skillScanned · flagged★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:17 AM15.5 KBMIT

Imported from source. Claim this skill

Orchestra Research/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 p...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:17 AM6.14 KBMIT

Imported from source. Claim this skill

Orchestra Research/sentence-transformers

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 generating...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:17 AM4.14 KBMIT

Imported from source. Claim this skill

Orchestra Research/segment-anything

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.

Published by Orchestra Research

skillScanned · flagged★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:16 AM13.5 KBMIT

Imported from source. Claim this skill

Orchestra Research/saelens

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 studying...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:16 AM10.1 KBMIT

Imported from source. Claim this skill

Orchestra Research/rwkv

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...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:16 AM12.8 KBMIT

Imported from source. Claim this skill

Orchestra Research/rigor-reviewer

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 rigor) and p...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:16 AM9.25 KBMIT

Imported from source. Claim this skill

Orchestra Research/research-manager

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 the ara/ di...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:16 AM12.0 KBMIT

Imported from source. Claim this skill

Orchestra Research/ray-train

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models acr...

Published by Orchestra Research

skillScanned · flagged★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:15 AM8.96 KBMIT

Imported from source. Claim this skill

Orchestra Research/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 p...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:15 AM4.93 KBMIT

Imported from source. Claim this skill

Orchestra Research/qdrant

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 per...

Published by Orchestra Research

skillScanned · flagged★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:15 AM12.4 KBMIT

Imported from source. Claim this skill

Orchestra Research/pyvene

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 causal hypo...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:15 AM9.36 KBMIT

Imported from source. Claim this skill

Orchestra Research/pytorch-lightning

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 training loops w...

Published by Orchestra Research

skillScanned · flagged★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:15 AM13.3 KBMIT

Imported from source. Claim this skill

Orchestra Research/pytorch-fsdp2

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 with Device...

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:14 AM9.55 KBMIT

Imported from source. Claim this skill

Orchestra Research/prompt-guard

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). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Published by Orchestra Research

skillScanned · flagged★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:14 AM4.94 KBMIT

Imported from source. Claim this skill

Orchestra Research/presenting-conference-talks

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 conferences.

Published by Orchestra Research

skillScanned · no issues★ 14KImported · UnverifiedAll toolsOct 14, 2026, 1:14 AM9.57 KBMIT

Imported from source. Claim this skill