NemoClaw Knowledge Wiki

Home

❯

concepts

❯

tokens

tokens

Apr 24, 20261 min read

  • concept
  • claude-skills
  • agent-skills
  • ai-playbook

Tokens

Source Notes

  • 2026-04-23: https://www.youtube.com/watch?v=HCwfRe5EHGQ Here is a comprehensive Markdown summary of the video regarding Claude Skills (also known as Agent Skills). # Claude Skills: The Ultimate Guide & Use Cases Presenter: Rick Mulready (The AI Playbook) 1. What Are Claude Skil (Claude Skills: The Ultimate Guide & Use Cases)

Graph View

  • Tokens
  • Source Notes

Backlinks

  • INDEX
  • Rick mulready - Claude skills
  • Ron Claude code locally - Mervin Praison channel
  • Running long running lim tasks successfully
  • Sam Witteveen - new Open Ai models
  • The AI model doesn't work - the harness does. Channel Prompt Engineering
  • This video announces and explains the new updates to OpenAI's Codex using 5.1 and cloud agents on gi
  • Use JSON prompting for accurate image generation
  • Use clawdcode Matthew Be
  • Using Claude Code sub agents
  • Using Claude code via phone
  • Using MCP safely via Docker
  • Using Ralph loops inside Claude Code
  • Watch Claude Agent Skills Explained on YouTube
  • Use JSON prompting for accurate image generation
  • context-rot
  • context-tokens
  • context-window
  • model-efficiency
  • multimodal-language-models
  • one-shot-build
  • self-attention
  • subagents
  • user-authentication
  • vocabulary-size
  • AI & Agents
  • AI Hallicinations
  • AI can work worse with Claude.md and agents.md files. Channel Theo
  • About the new Ollama gui interface
  • Adam Lucek - Flux model for Open AI generated image gen
  • Adam Lucek - RAG basics
  • Adam Lucek - optimal RAG chunking with ChromaDB
  • Ai zero trust setup. IBM channel
  • Claude Code - workflow. Yifan - Beyond the Hype channel
  • Claude Code workflow using sub-agents
  • Clawbot Matthew Berman channel
  • Compare of Claude Opus 4.5 vs ChatGPT 5.2 Matt Maher
  • Context engineering by prompt engineering channel
  • Dave's Garage - review of AI models
  • DeepSAeek Engram paper - Prompt Engineering channel
  • Enhanced rag. Channel Prompt Engineering
  • Fine Tuning RAG - Adam Lucek
  • Fixing long running Claude code sessions
  • Gemini Pro for professional work flow - Jeff Su
  • Gemini flash 3
  • Google Ai studio tips - Elle wang
  • Grace Leung Claude skills
  • How does 4bit quantisation work
  • IBM agentic security
  • Jeredblu running LLM locally
  • Kiki K2 - Prompt Engineering
  • Langchain context engineering
  • Langchain researcher with Gemini 2.5
  • Langextract Sam Witteveen
  • New Claude Code features
  • RAG re-ranking with pruning - channel Prompt Engineering
  • Rick mulready - Claude skills
  • Ron Claude code locally - Mervin Praison channel
  • Running long running lim tasks successfully
  • This video announces and explains the new updates to OpenAI's Codex using 5.1 and cloud agents on gi
  • Use JSON prompting for accurate image generation
  • Using MCP safely via Docker
  • Using Ralph loops inside Claude Code
  • Your Lab job is complete — YouTube Summariser (#1454)
  • Agent Skills: Why Code Enhances LLM Efficiency Over Markdown for Scraping
  • Bonzai 8B: PrismML's Revolutionary 1-Bit LLM First Look & Test
  • Demystifying Claude Code: Key Concepts for Non-Technical Users
  • LlamaIndex's LiteParse: Agentic Document Processing and the End of Frameworks
  • OpenClaw: Autonomous AI Agent Setup, Configuration, and Advanced Integration
  • TurboQuant: Extreme Compression for Local LLM Efficiency and Context Windows
  • Agent Skills: Why Code Enhances LLM Efficiency Over Markdown for Scraping
  • Bonzai 8B: PrismML's Revolutionary 1-Bit LLM First Look & Test
  • Claude Cowork: Desktop AI Co-worker Core Capabilities and Advantages
  • Demystifying Claude Code: Key Concepts for Non-Technical Users
  • LlamaIndex's LiteParse: Agentic Document Processing and the End of Frameworks
  • OpenClaw: Autonomous AI Agent Setup, Configuration, and Advanced Integration
  • TurboQuant: Extreme Compression for Local LLM Efficiency and Context Windows
  • Agent Skills Why Code Enhances LLM Efficiency Over Markdown for Scraping
  • Bonzai 8B PrismMLs Revolutionary 1-Bit LLM First Look Test
  • Claude Cowork Desktop AI Co-worker Core Capabilities and Advantages
  • Demystifying Claude Code Key Concepts for Non-Technical Users
  • LlamaIndexs LiteParse Agentic Document Processing and the End of
  • Meta Muse Spark Features Performance and Strategic Shift to Proprietary AI
  • OpenClaw Autonomous AI Agent Setup Configuration and Advanced
  • TurboQuant Extreme Compression for Local LLM Efficiency and Context
  • Claudes Advisor Strategy Monitor Tool and Managed Agents for AI Development
  • Google TurboQuant LLM Memory Efficiency Breakthrough Industry Impact
  • Demystifying AI Transformer Training on a 1979 PDP-11
  • Graphify: Knowledge Graph for AI Coding Assistant Context and Memory
  • Anthropic's Compute Miscalculation: Claude Demand and Strategic Impact
  • OpenAI GPT-5.5: Smartest Frontier Model Driving Agentic AI and Efficiency
  • DeepSeek V4: China's Cost-Efficient Open-Source AI Challenges US Dominance
  • DeepSeek V4: Hybrid Attention, Efficiency, and Architectural Innovations Analysis
  • URL Ingest Summary
  • NVIDIA Sonic: Groundbreaking AI for Nuanced Humanoid Robot Teleoperation
  • AI Context Layer Architectures: Karpathy's Wiki vs. OpenBrain Comparison
  • Google Gemma 4: Open-Weight AI for Local, Private Execution
  • Google Deep Research Max: Enhancing AI Research with Proprietary Data & Visuals
  • Google DeepMind's Gemma 4: Open-Source AI Models and Architectural Innovations
  • Optimizing LLM Agent Token Usage with MCP and Code Execution

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community