Zara Zhang
- Imagine if Claude Code/Codex can access AND operate all your chats, calendars, meetings, docs, sheets... That's possible now with Lark CLI. The world's most all-in-one collaboration tool just became the world's most agent-friendly collaboration tool. I just built a skill on top of this: Not only does it extract to-dos from the meetings, it actually EXECUTES those to-dos... insane https://t.co/Dzviq7vdQQ
- I created a Claude Skill that make beautiful slides on the web. The world hasn't woken up to the fact that code can create much better slides than most PPT tools. - Claude interviews you first about aesthetics, then generate a few directions to "show not tell", and you can pick your favorite - Cool transitions and animations - Interactive hover states and cursor effects - Auto-fits on any screen - Supports converting existing PPTX files to web-based slides; preserves original images and brand assets I asked Claude to make a slide show about this skill to showcase what it can do. Link to skill below
- Created a custom slash command "/handover" in Claude Code: When I'm ending a Claude session (e.g. context window filling up), I get Claude to generate a "https://t.co/GZrCLFU2Zu" document which summarizes everything we did in this session, including decisions, pitfalls, lessons learned, etc. So the next session's Claude has full context. This prevents amnesia and preserves institutional knowledge
- 10 beginner-friendly ideas to build with Claude Code (Prompts included)
- My Frontend Slides skill now has 7.8k stars on Github which is crazy!! I just restructured it following the "progressive disclosure" pattern: went from 1,625 lines loaded every time to 183. Same functionality, 89% less context bloat. Treat your instruction file like a table of contents, not a textbook. Put the rules up front. Put the reference material in separate files the agent reads only when it needs them. It's like the difference between handing a new hire a 30-page briefing doc vs. a 2-page summary with "see appendix B for details."
Imagine if Claude Code/Codex can access AND operate all your chats, calendars, meetings, docs, sheets... That's possible now with Lark CLI. The world's most all-in-one collaboration tool just became the world's most agent-friendly collaboration tool. I just built a skill on top of this: Not only does it extract to-dos from the meetings, it actually EXECUTES those to-dos... insane https://t.co/Dzviq7vdQQ
I created a Claude Skill that make beautiful slides on the web. The world hasn't woken up to the fact that code can create much better slides than most PPT tools. - Claude interviews you first about aesthetics, then generate a few directions to "show not tell", and you can pick your favorite - Cool transitions and animations - Interactive hover states and cursor effects - Auto-fits on any screen - Supports converting existing PPTX files to web-based slides; preserves original images and brand assets I asked Claude to make a slide show about this skill to showcase what it can do. Link to skill below
Created a custom slash command "/handover" in Claude Code: When I'm ending a Claude session (e.g. context window filling up), I get Claude to generate a "https://t.co/GZrCLFU2Zu" document which summarizes everything we did in this session, including decisions, pitfalls, lessons learned, etc. So the next session's Claude has full context. This prevents amnesia and preserves institutional knowledge
10 beginner-friendly ideas to build with Claude Code (Prompts included)
My Frontend Slides skill now has 7.8k stars on Github which is crazy!! I just restructured it following the "progressive disclosure" pattern: went from 1,625 lines loaded every time to 183. Same functionality, 89% less context bloat. Treat your instruction file like a table of contents, not a textbook. Put the rules up front. Put the reference material in separate files the agent reads only when it needs them. It's like the difference between handing a new hire a 30-page briefing doc vs. a 2-page summary with "see appendix B for details."