Top Rated

The most starred skills loved by the community. Quality guaranteed!

Showing 2353-2376 of 52147 skills
ComposioHQ

skill-installer

by ComposioHQ

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Comments 15.4K 6mo ago
ComposioHQ

create-plan

by ComposioHQ

Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.

Code Gen 15.4K 6mo ago
ComposioHQ

linear

by ComposioHQ

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

Auth 15.4K 6mo ago
ComposioHQ

brand-guidelines

by ComposioHQ

Applies OpenAI's brand colors and typography to any artifact that should match the Codex/OpenAI look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Cloud 15.4K 6mo ago
ComposioHQ

internal-comms

by ComposioHQ

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

File Ops 15.4K 6mo ago
ComposioHQ

mcp-builder

by ComposioHQ

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Processing 15.4K 6mo ago
ComposioHQ

domain-name-brainstormer

by ComposioHQ

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

Code Review 15.4K 6mo ago
ComposioHQ

support-ticket-triage

by ComposioHQ

Triage customer support tickets/emails/chats into categories, priority, and next action; draft responses and create reproducible steps; use for Zendesk/Intercom/Help Scout exports or pasted threads.

Code Gen 15.4K 6mo ago
Orchestra-Research

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.

ML Ops 11.2K 6mo ago
Orchestra-Research

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 studying monosemantic representations in language models.

Caching 11.2K 7mo ago
Orchestra-Research

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 sharing.

Agents 11.2K 8mo ago
Orchestra-Research

axolotl

by Orchestra-Research

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

Code Gen 11.2K 8mo ago
Orchestra-Research

constitutional-ai

by Orchestra-Research

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

ML Ops 11.2K 8mo ago
Orchestra-Research

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 without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

i18n 11.2K 8mo ago
Orchestra-Research

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, and distributed checkpointing.

Automation 11.2K 6mo ago
Orchestra-Research

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.

CLI Tools 11.2K 8mo ago
Orchestra-Research

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 Shakespeare (CPU) or OpenWebText (multi-GPU).

Processing 11.2K 8mo ago
Orchestra-Research

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 used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

CLI Tools 11.2K 8mo ago
Orchestra-Research

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 launch command. HuggingFace ecosystem standard.

Code Gen 11.2K 8mo ago
Orchestra-Research

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 tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

CLI Tools 11.2K 8mo ago
Orchestra-Research

ML Training Recipes

by Orchestra-Research

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

Automation 11.2K 4mo ago
Orchestra-Research

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 Transformers.

ML Ops 11.2K 8mo ago
Orchestra-Research

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 multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Code Gen 11.2K 8mo ago
Orchestra-Research

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 LoRA/QLoRA. Single-file implementations, no abstraction layers.

Code Gen 11.2K 8mo ago