Because working with AI for a long time creates three different problems: 1. **Losing the thread of the session** The AI and the user start to forget where they were, what has already been decided, and what the next step is. → That is why `session-statusline` exists. 2. **Accumulating bad memory or bloated context** `CLAUDE.md` / memory can become a dumping ground for old, repeated, or irrelevant information. → That is why `memory-audit` exists. 3. **Clearing the session and losing continuity** When you run `/clear` or switch agents, a lot of useful information can disappear. → That is why `session-handoff` exists. Summary in one sentence: > We created these Skills to keep AI lean, avoid rework, and ensure continuity without carrying unnecessary context.

https://openai.com/index/introducing-gpt-5-5/ https://www.youtube.com/watch?v=A9G3s8Qeu_8

🧠 THE MODEL (clear view) You have 3 layers: 1. ⚓ Anti-anchoring → removes bias 2. 🎩 6 hats → separates how you think 3. 🔵 Final blue → turns it into a decision ⚓ 1. ANTI-ANCHORING (before everything) This is the most underrated part — and the most powerful. The problem: You already start thinking like this: - “I think this is good” - “I’m afraid of this” - “I’ve already decided without noticing” 👉 That’s mental anchoring What you do: - Reframe the problem - Question your assumptions - Consider the opposite - Imagine failure 👉 Result: you enter the process less biased 🎩 2. THE 6 THINKING HATS Now the core idea:👉 you think one mode at a time ⚪ White Hat — Facts Mode: reality Questions: - What do we know? - What don’t we know? - What is assumption? 👉 No opinions. Only data. 🟡 Yellow Hat — Benefits Mode: logical optimism Questions: - What could go right? - What are the advantages? - Why could this work? 👉 Must include reasoning (not just “sounds good”) ⚫ Black Hat — Risks Mode: protection Questions: - What could go wrong? - Where could this fail? - What are the real risks? 👉 This prevents bad decisions 🟢 Green Hat — Creativity Mode: expansion Questions: - What other options exist? - What’s another way? - What bold idea could work? 👉 No judging — just generating ideas 🔴 Red Hat — Intuition Mode: emotion Questions: - What do I feel? - Does this feel right or wrong? 👉 No explanation. Just feeling. 🔵 Blue Hat — Control / Decision Mode: management + conclusion At the end: - What’s the best option? - What’s the plan? - What do we do now? 👉 This turns thinking into action 🔢 3. THE REAL FLOW (the key) You don’t use them randomly — you follow order: 1. ⚓ Anti-anchoring 2. 🔵 Blue (organize) 3. ⚪ White (facts) 4. 🟡 Yellow (benefits) 5. ⚫ Black (risks) 6. 🟢 Green (alternatives) 7. 🔴 Red (intuition) 8. 🔵 Blue (final decision) 💡 MOST IMPORTANT INSIGHT 👉 The power is not the hats👉 It’s not mixing them

How Claude Design Works 1. Access You go to claude.ai/design. The interface combines chat + visual canvas side by side, allowing you to talk while the design is created in real time. 2. Content Input You can provide input in several ways: - Text: example — “create a pitch deck about X” - File uploads: DOCX, PPTX, XLSX, images - Website capture: simply enter a URL to extract style and elements - Brand: connect your team’s code or design files, automatically applying colors, fonts, and components 3. Design Generation The model (Opus 4.7) creates a complete first version, such as: - Slides - Wireframes - Prototypes - Marketing assets 4. Refinement You can make adjustments without starting over: - Direct comments on elements (e.g., “make this button bigger”) - Edit text directly on the canvas - Adjust using sliders (spacing, color, layout) - Request changes via chat (e.g., “make it more serious”) 5. Sharing and Export - Internal link for your team (view or edit) - Export to: Canva, PDF, PPTX, HTML - Dev integration: send directly for implementation Typical Workflow Idea → Prompt → First version → Adjustments → Sharing → Export/Implementation Key Differentiator Unlike tools like Figma or Canva:you don’t design — you talk, and your brand identity is applied automatically. https://www.anthropic.com/news/claude-design-anthropic-labs

❯ /release-notes ⎿ Version 2.1.110: · Added /tui command and tui setting — run /tui fullscreen to switch to flicker-free rendering in the same conversation · Added push notification tool — Claude can send mobile push notifications when Remote Control and "Push when Claude decides" config are enabled · Changed Ctrl+O to toggle between normal and verbose transcript only; focus view is now toggled separately with the new /focus command · Added autoScrollEnabled config to disable conversation auto-scroll in fullscreen mode · Added option to show Claude's last response as commented context in the Ctrl+G external editor (enable via /config) · Improved /plugin Installed tab — items needing attention and favorites appear at the top, disabled items are hidden behind a fold, and f favorites the selected item · Improved /doctor to warn when an MCP server is defined in multiple config scopes with different endpoints · --resume/--continue now resurrects unexpired scheduled tasks · /context, /exit, and /reload-plugins now work from Remote Control (mobile/web) clients · Write tool now informs the model when you edit the proposed content in the IDE diff before accepting · Bash tool now enforces the documented maximum timeout instead of accepting arbitrarily large values · SDK/headless sessions now read TRACEPARENT/TRACESTATE from the environment for distributed trace linking