deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-26 00:15
Agents & models
24,822 results
denario
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when…
n8n-mcp-tools-expert
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or…
openrlhf-training
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×…
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…
simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
cli-for-agents
Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors,…
continual-learning
Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
orchestrate
Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via…
ralph-loop
Start a Ralph Loop for iterative self-referential development. Use when the user asks to run a ralph loop, start an iterative loop, or wants repeated…
review-and-ship
Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
workflow-from-chats
Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine…
openclaw
Designs, builds, debugs, and documents OpenClaw workflows, skills, and AI assistant configurations. Use when the user mentions "OpenClaw," "personal AI…
openclaw-dingtalk-channel
DingTalk channel plugin for OpenClaw that enables enterprise bot integration using Stream mode without public IP requirements
solana-mcp-vybe
Use Vybe's public Solana MCP server to query Solana blockchain data, tokens, NFTs, and accounts from Claude, Cursor, or any MCP client
agent-architecture-lens
Review agent control flow, durable state, retries, and recovery. Use when choosing a loop or state graph, or when a tool-calling workflow must survive failures…
minimax-runner
Execute prompts using Minimax models through Cline CLI in headless mode. Use when users explicitly request Minimax execution, when a workflow needs a Minimax…
integrate-audio
Help users integrate Runway audio APIs (TTS, sound effects, voice isolation, dubbing)
integrate-characters
Help users create Runway Characters (GWM-1 avatars) and integrate real-time conversational sessions into their apps
integrate-documents
Help users add knowledge base documents to Runway Characters for domain-specific conversations
browser
Web browser automation with AI-optimized snapshots for claude-flow agents
warren-buffett
Buffett's investment decision-making framework and business analysis thinking. A cognitive operating system distilled from 60 years of Berkshire shareholder letters, classic investment cases (Coca-Cola, Apple) and Q&A at the Omaha shareholder meetings. Core value: (A) Investment decision assistant > (C) Business model analyst >…
relay-dispatch
Dispatch implementation tasks via worktree isolation. Use when delegating work to an executor, running background dispatches, or parallelizing independent…