Typefully MCP Server | Typefully Help Center

Check this out to connect it: support.typefully.com/en/articles...

Claude with Typefully connected is pretty insane.

Finalize — Claude Code skill for ship-readiness passes Finalize Your job is to help ship. Take ownership of the last serious pass before merge: understand what changed, identify what could still go wrong, look for what can be safely simplified, fix...

I have /finalize skill that I'm often using after working on something, to make it shippable.

It auto-fixes obvious issues, creates branch/PR if needed, simplifies where safe, consider blind spots and alternatives etc.

Working quite well for me. gists.sh/linuz90/8e0...

Great prompt I tried today:

› Is there a smart way to make {file path} smaller and tighter, while actually making it achieve the same goals even BETTER?

This made some AGENTS .md files ~50% smaller, with no quality loss.

GitHub - linuz90/lwt Contribute to linuz90/lwt development by creating an account on GitHub.

Here's the repo with install instructions: github.com/linuz90/lwt

I'm shipping faster and faster thanks to my little "lwt" worktree helper.

Makes it so easy to spin up agents on tasks.

Now it even auto-splits the terminal in iTerm and Ghostty.

Some cool examples:

No sign-up, no tracking. Just a better way to read and share notes and code.

Killer use case: have your AI agent like OpenClaw share research, notes, or code with you as a pretty gist.

Drop it in a meeting chat and watch the reactions.

Free and open source ✌️

gists.sh Gists, but beautiful

GitHub Gists are useful but look terrible.

So I’ve built:

→ gists.sh

Simply replace the domain in any gist URL with gists dot sh.

You’ll get:
• Clean typography and layout
• Great syntax highlighting
• Dark mode
• Multi-file gists with tabs
• Markdown that actually looks good

If you're using OpenClaw on Telegram, set up forum topics.

Turns one messy chat into organized topics. Each with its own isolated LLM session. Your finance chat never bleeds into your dev context.

Setup: enable Threaded Mode in BotFather, tell your agent to create topics and route messages.

It can also directly launch your favorite AI CLI on worktree creation.

Feel free to contribute and make it your own.

Worktrees are great but the terminal UX is terrible.

Built a small CLI that makes them usable for me.

It shows the status of each one clearly, and makes adding and removing super easy. Copies .env too (recursively) and optionally installs deps.

→ github.com/linuz90/lwt

Whatever recurring need you have, ask your OpenClaw "should we make a skill and/or cron for this?" and it will guide you through it.

And just make sure to put your notes where it can access them and ask it to index them and point to the most important ones in USER .md.

I never wanted a "second brain", but here we are.

An indirect effect of sharing my notes with my OpenClaw is that my notes are now improving and compounding daily.

What if OpenClaw could make you feel like you’re the star in your own movie?

→ Set up elevenlabs
→ Choose a warm, enthusiastic voice
→ Get an energetic soundtrack
→ Ask it to prepare a great morning digest
→ Tell it to use the voice + soundtrack

Insane to start the day like this 🍿

My bot pulls this every 30 minutes during heartbeats, so it knows what’s up and whether to ping me.

It’s truly context-aware:

- idle for hours + good recovery → suggests a walk
- late night + still on Mac + low HRV → nudges me to rest
- deep in work + music on → stays quiet

Now my agent can check /me for:

• Apple Health: sleep, HRV, recovery, resting HR, steps, active calories
• Mac: presence, idle time, focused app
• Spotify: now playing, recent tracks, top artists
• Steam/PlayStation: games played + time
• Slack: online/away, DND, status
• More (suggestions?)

A Telegram chat displays updates from a user, detailing sleep, gaming, music preferences, and recent development work.

I wanted OpenClaw to know what I’m up to, but it runs isolated on a VPS.

So I had Claude Code build a /me endpoint on my Mac: a small Bun server that aggregates local data into one JSON blob.

It’s locked down with Tailscale, so only devices on my private mesh can access it.

🧑‍🍳

I just find it annoying

Global AI agents guidelines for managing GitHub gists, commit rules, handling file conflicts, and planning strategies.

If you're using multiple AI agents across many projects, you need a global AGENTS file.

I keep mine in a dev folder, and symlink to:

~/CLAUDE . md (Claude Code)
~/AGENTS . md (Codex, Gemini, Cursor...)

This keeps behavior consistent across all agents.

We keep adding integrations, turning @typefully.com into a powerhouse.

Raycast, Zapier, MCP, AI skills, Claude... it's all there.

If you're a techie, this is THE social media tool to use.

typefully by typefully/agent-skills Install the typefully skill for typefully/agent-skills

It's like having a 24/7 social media manager in your terminal.

You keep shipping, and let your agents help you grow.

To get started:

▸ npx skills add typefully/agent-skills

This uses the skills CLI from Vercel to guide you through setup.

Learn more: skills.sh/typefully/a...

Your favorite AI coding agents can now manage your socials.

We're finally shipping a Typefully skill today.

Our skill makes AI agents learn about Typefully, so they can help you draft, refine, schedule, add media, and a lot more 🔥

It's quite magical to see it in action:

My M3 Air with 16GB of RAM isn't cutting it anymore though.

I think I'm getting the new MBP they'll announce soon.

I think I'm Conductor-pilled.

More improvements and features for Typefully incoming ⚡

Damn Claude don't be too hard on yourself

ccmd - fzf picker for Claude Code commands ccmd - fzf picker for Claude Code commands. GitHub Gist: instantly share code, notes, and snippets.

Just add this to your .zshrc:

→ gist.github.com/linuz90/f82...

Requires fzf (ask Claude Code to set it up if you don't have it).

I got tired of forgetting my Claude Code slash commands, so I asked Claude to build a function that shows all my commands, with autocomplete.

Type `ccmd` → fuzzy search → hit Enter to run.

Game changer if you have lots of commands scattered around.

GitHub - linuz90/claude-telegram-bot Contribute to linuz90/claude-telegram-bot development by creating an account on GitHub.

If you want this, I completely open sourced my setup.

It simply runs Claude Code via the official SDK on your Mac, so nothing hackish going on.

→ Make sure to read the "Personal Assistant Guide" inside it.

Check it out: github.com/linuz90/cla...

Claude Code runs my life now.

It checks my tasks, email, notes, health data, calendar, and more through subagents, MCPs, tools, and scripts.

And I chat and speak with it via Telegram all day.

I called it “Max” since it’s maxing out my Claude sub 😂