diff --git a/README.md b/README.md
index 79cd510..3f3bfaf 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # claude-code-best-practice
 your best ai assistant with the best practice
 
-## Core Concepts
+## CONCEPTS
 
 - **[Agents](https://docs.claude.com/en/docs/claude-code/agents)** - Specialized subprocesses that autonomously handle complex, multi-step tasks
 - **[Commands](https://docs.claude.com/en/docs/claude-code/slash-commands)** - Custom slash commands to extend Claude Code with reusable prompts
@@ -15,30 +15,33 @@ your best ai assistant with the best practice
 - **[Output Styles](https://docs.claude.com/en/docs/claude-code/output-styles)** - Custom system prompt modifications for different use cases
 - **[Permissions](https://docs.claude.com/en/docs/claude-code/permissions)** - Fine-grained access control for tools and operations
 
-## Other Libraries
 
-- [Claude Code Tips](https://github.com/ykdojo/claude-code-tips)
-- [Awesome Claude Code](https://github.com/hesreallyhim/awesome-claude-code)
+## LESSON LEARNED
 
-## Keywords
-
-- [ultrathink] Triggers extended thinking with up to ~32K thinking tokens for a single request.
-- [btw] start prompt with btw to let the current task executing in background
-- [claude --dangerously-skip-permissions] "defaultMode": "bypassPermissions"
-
-## Tips
-
-### Claude.md
+### Context Engineering
 - [Humanlayer - Writing a good Claude.Md](https://www.humanlayer.dev/blog/writing-a-good-claude-md)
 
 ### Debugging
 - always ask claude to run the terminal (you want to see logs of) as a background task for better debugging
 - use claude in chrome to let claude see chrome console logs on its own
 
-### Sandboxing
+### Workflows
 - [Ralph plugin with sandbox](https://www.youtube.com/watch?v=eAtvoGlpeRU)
+- [RPI - Research Plan Implement](https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/ace-fca.md)
+- [AgentOs - 2026 its overkill (Brian Casel)](https://www.youtube.com/watch?v=0hdFJA-ho3c)
 
-## Documentation
+## LIBRARIES
+
+- [Claude Code Tips](https://github.com/ykdojo/claude-code-tips)
+- [Awesome Claude Code](https://github.com/hesreallyhim/awesome-claude-code)
+
+## KEYWORDS
+
+- [btw] start prompt with btw to let the current task executing in background
+- [claude --dangerously-skip-permissions] "defaultMode": "bypassPermissions"
+- *deprecated** [ultrathink] Triggers extended thinking with up to ~32K thinking tokens for a single request.
+
+## DOCS
 
 ### **[docs/AGENTS.md](docs/AGENTS.md)** - Agent Orchestration Best Practices
 Learn how to properly orchestrate multiple agents, avoid common pitfalls when sub-agents aren't invoking, and implement sequential workflows using the Task tool.
@@ -49,18 +52,6 @@ Quick reference tables showing how to invoke agents and commands from different
 ### **[docs/WEATHER.md](docs/WEATHER.md)** - Weather System Flow Documentation
 Complete system architecture and flow diagram for the weather data fetching and transformation workflow, demonstrating real-world agent and command orchestration.
 
-## SKILLS
-#### Skills vs. Agents | Commands | Memory
-[Claude Code Skills: What Problem Do They Solve? - Brian Casel](https://www.youtube.com/watch?v=Z0DB0kCfNOM)
-
-#### Types of Skills
-[The REAL POWER of Claude Agent SKILLS - Grace Leung](https://youtu.be/m-5DjcgFmfQ)
-
-#### Venn Diagram - Skills vs. Agents | Commands
-[Claude Code Brand New Feature: Claude Skills - Ray Amjad](https://www.youtube.com/watch?v=v1y5EUSQ8WA)
-![](!/skill-agent-commands.png)
-
-
 ## IDE
 
 ### Cursor vs. Windsurf vs. VS Code