Liban (lee~ben) Kano

Liban, To you. Love, Liban.

@bnj God bless you.

@libankano I got you

@bnj love love Variant, just paid. Feature request: could you enable exporting when in the bookmarked folders. I bookmark a variant and when I go to that folder and try to export those items on top are missing.

Lex Luthor.

@dan__rosenthal Microsite

I stopped sending text-only outreach to my best prospects. Instead, I built personalized ‘microsites’ using Gamma's API and Clay: Each microsite pulls in the prospect's company colors, logos, ICP research, TAM breakdowns, and a customized proposal with a scheduling link. (and it’s all 100% automated) This way, every prospect sees a custom proposal before we ever get on a call. I documented the full workflow so anyone can set this up: • Clay template for account enrichment (importable) • Gamma API call format for microsite generation • Auto-branding logic for colors and logos • GTM analysis prompt structure • Scheduling link integration Comment "MICROSITE" and I'll send it over. PS - The template is reusable. Once it's set up, you can generate a new microsite for any prospect in minutes.

@paulg Paul — would you be able to say more about “the shape of ideas”.

This was after I mentioned the idea of buying rare old things as a hedge, since one thing AI won't be able to do is go back in time. I don't put too much weight on the specific year, but the shape of the idea is interesting.

"Anything made before 2028 is going to be valuable." — an OpenAI employee implicitly discloses their timetable

Introducing Naive - hire autonomous employees with their own identity. Own compute. Own bank account. Own legal entity. Own email. Own credentials. Own mobile. No humans-in-the-loop. They sign up for tools, pay for services, deploy apps, file documents, and run your entire company. Describe a business. Naive runs it. Reply "Naive" + RT. Get $100 credit for free.

@usenaive @ycombinator Naive

@felixrieseberg @noahzweben Cowork & Claude Code now connect via dispatch ?

By popular demand, Dispatch can now launch Claude Code sessions. Ask it to build, make, or improve something! To use it, update your Claude desktop app and make sure you have Code enabled.

Cool Lydia — I can definitely see this aiding those skills that become stale. Made a prompt to help Claude Code implement this into existing skills: Hey Claude, since we already have several local skills built in the .claude/skills folder right here in this project, I want to upgrade those existing skills right now to use the new dynamic exclamation mark backtick shell command feature. That way every time I invoke one of the skills, it will automatically run commands on my computer and inject the fresh live project data into the prompt without me having to copy anything manually. Please begin by listing all the current local skill folder names so I can see what's there. Then go through each one in turn and update its SKILL.md file safely: add or update the YAML frontmatter at the top to include the allowed-tools permission for Bash so the commands can run, keep every bit of the original name description and instructions completely untouched, insert a new Live Project Context section right after the frontmatter that pulls in real-time details using the !`command` syntax like git status with !`git status --short`, recent commits with !`git log --oneline -5`, and changed files or PR info with !`gh pr diff --name-only` or whatever fits that particular skill best, and finally tweak the task instructions at the end to remind yourself to always base responses on only that freshly injected live data. After you've finished updating each one, confirm exactly what you changed for that skill and remind me how to call it going forward so we can test the live updates together immediately. — — — Just copy and paste that whole block directly into your ongoing Claude chat. It'll handle scanning your existing skills, adding the dynamic injections, and keeping everything you already built 100% intact. Once it confirms the upgrades, simply type /your-skill-name (whatever your original skill names are) and you'll instantly see the live data appear.

if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result!

@homsiT Hey, for someone that hasn't used Readwise but has a plethora of Twitter bookmarks, is there a way to backlog or backconnect to Readwise?

1. Install Readwise CLI 2. OpenClaw, Claude Code, Codex, or any coding agent can now: * Search your entire readwise library * Read full content of anything you've saved * Tag, create highlights, organize on your behalf * Pipe reading data into any workflow Your agent now knows everything you've read :)

@yazins Hey, would you consider just adding Wispr Flow as well and knock out two birds with one stone?

Just shipped the biggest update to OpenOats (prev OpenGranola: the open-source meeting copilot for macOS): Meeting Templates + AI Notes ✨ Pick a template before your meeting (1:1, Customer Discovery, Hiring, Stand-Up, Weekly) and after it ends, generate structured notes from the full transcript with one click. Notes stream in real-time as the LLM writes them. Browse past sessions, regenerate with different templates, copy to clipboard. Also fixed a subtle bug where the last ~3 seconds of audio could be lost when stopping a session. Now the app gracefully drains all buffered speech before closing. 4 new files, 1,277 lines added. All open source. github.com/yazinsai/OpenO…

@ctatedev Hey Chris - I just want to say thank you! Agent browser has been a game changer, seriously.

agent-browser v0.21 It just keeps getting better (bc of you) 😮 `batch` command 😮 `network har` commands 😮 `upgrade` command 😮 iframe support 😮 --user-data-dir support After this, you can just upgrade it: npm i -g agent-browser brew install agent-browser

@MichLieben Claude Code

We spent hundreds of hours building Claude Code skills for our $7M ARR GTM agency (and we're giving them away for free) - ICP research - signal scoring - cold email writing - sales intelligence - campaign intelligence. These run inside every system we build for 70+ B2B clients. Reply "Claude Code" and I'll send you the Github repo with everything.

@blinkdotnew Claw

Introducing Blink Claw - the first platform to hire unlimited AI employees that run your business 24/7. 180+ AI models included. Gmail, Slack, LinkedIn, HubSpot - one-click connect. No API keys, no $600 Mac Mini. Reply "Claw" + RT. Your first agent is on us. ($50 - 200 creds)

@coinbase The Sims: GTA

Game not over. It’s time to take back control. Presenting “Your Way Out,” the extended cut.

@Riyvir Yooooo you are a g g g g g Genius.

here's another little tool i've been working on called "typoverse." i have thousands of fonts but i find myself always using the same ones. and i am simply not going to manually tag or categorize fonts either. so i built a tool that compares all my fonts to each other and maps them based on similarity. would this be useful to anyone?

Does X work? I'm looking to speak with Product Designers.

Does this X button work? I'm looking to connect with Product Designers.

@brynary In english what does this translate to?

Today I'm thrilled to open source what I've been working on... Meet Fabro (github.com/fabro-sh/fabro), the dark software factory for small teams of expert engineers. Fabro gets you out of the REPL (read-eval-prompt-loop) by layering deterministic workflow graphs over agent sessions. It's batteries included with cloud sandboxes, quality sign offs, multi-model ensembles, and Git checkpoints. It's MIT licensed so you can fork and own your AI coding toolchain. Single Rust binary with zero deps. I'd love to hear what you think!

Just launched localhost:3000 Let me know if anyone want's to try it!