Matt Galligan

@whatdotcd Yep! We got the Graco Turn2Me and it's been awesome, very happy with it. Only downside is it's heavier so it's best if it's installed and not swapped between vehicles.

Have any of you done those swivel car seats? Do you have strong opinions?

@EricJorgenson @moccamasterusa Yep. These ones are beautiful *and* make great coffee. ratiocoffee.com/products/ratio…

Has anyone found a Drip coffee maker with no plastic parts? Surprisingly difficult. Bonus points for thermal, insulated. carafe Hope @moccamasterusa gets on it.

@mronge The connections have all been super solid with it so far. But the biggest thing holding me back from using it a ton has got to be modifier support. The iPad can't handle cmd modifier combos, the Mac version seems to swallow some whole. Hoping it can be addressed!

Workbench 1.2 just shipped - Remote desktop for your headless Mac from iPhone or iPad. New stuff: - Full Screen Unified Display on Mac - Speech-to-text for non-English languages - App stays connected in the background - Improved zooming on iPad/iPhone - Improved Intel Mac support - Login stability fixes everywhere - Option to hide the dock icon Stick around to the end of the video for a little surprise 😗

@cognition Big fan of DeepWiki here, but having some trouble with trying to get a couple of repos indexed today. I've submitted (w/ email) on some repos, and even got the "ready" confirmation but they're still showing as empty. Any way to get them moving along? I can provide the specific ones. cc @dabit3

Just going to have to live vicariously through everyone posting about how awesome the new @OpenAI Codex computer use is while I wait for my usage to reset 😭

@jaredpalmer @github Sick. Just signed up for my outfitter-dev org. I exclusively use stacked PRs today so I'm excited to see how they'd work for my workflows.

1. Big planning process. Once it's well defined, turn them into Linear issues. 2. Use @gitbutler or @graphite to stack branches based on the issues, often 5-10 in the stack, but have done as much as 35. 3. Work up the stack, ensuring each can pass build/test locally and CI independently. 4. Run Codex review on a loop to get all P1's and P2 issues fixed, until it starts spitting out P3's then done. 5. Submit the full stack to GitHub, each as individual branches. Let feedback roll in from Greptile, Devin, Codex, etc. 6. Run my /pr-loop skill which gathers all feedback, dedupes it, associates with specific branches, then feeds it into agents sequentially, from the bottom of the stack up. Fix things up, submit, repeat. 7. Once the feedback gets to a minimum, CI is green, and Greptile says 5/5 on each PR, merge the stack. Seems complex but it's dialed in w/ just three skills. Can build massive features but not sacrifice review quality with too many LOC changes or files in a giant PR.

i'm sure we all have our little coding 'hacks,' here are my top 5, please share yours (or help me improve mine! 🙏): 1. Plan -> Deepen Plan -> Then let Codex review the plan, then hand it back to Claude Code 2. Let Co-Work read the plan and build you a PDF of the plan in plain english along with flowcharts (vs just "go to work!"), this is a great for overall logic agreement 3. If I'm unsure of a stack or an algorithm choice (e.g. best algo for clustering objects with vector embeddings), give it to the beast models and let them deep research it for 20 mins 4. If have something big to tackle, always quit and restart Claude Code 5. On big PRs, I always let CC, Codex, and @greptile view it (at the same time), never fails to find some P1s

I've tried just about every voice dictation app on the market multiple times. @aquavoice is the one that gets my DAU. So stoked it's finally landed on iOS.

@tobi Just submitted four PRs to qmd that together improves chunk identification. Think it would be a step change for handling nested code blocks, lists, and xml tags like those used in agent instructions. More here: gist.github.com/galligan/a8d3c… Lmk if I can help more! Love qmd.

@Shpigford iA Writer

What app has the best markdown reading/writing experience you’ve ever experienced in your entire life?

@maxkruger @AnthropicAI @claudeai Obsidian's chrome plugin as a "copy as markdown" in the drop down next to the main action button. Use it when on the specific Claude chat you want. Paste into Claude code. Does the trick!

Is there any easy way to transfer Claude chats to Claude code? Did some deep research on a new idea and want it to start coding. Doesn’t seem to be an easy way @AnthropicAI @claudeai

PDFs can be a tricky beast, and not all are created equal. Some have OCR built in, which can sometimes be a good thing, and sometimes bad. So far I haven't found a silver bullet solution but here are a few things I've had success with: 1. Claude is pretty good just uploading one, and asking it to turn it to markdown. Gemini I'd say is equally good (and faster). Try that first. 2. If OCR is built in, sometimes it's too quick to trust that output which may not always be accurate. You can ask an agent to write a script to split pages individually, and then read those singles. That can sometimes help match OCR content to image recognition. 3. Explicitly saying you want it to use an image model *and* read any embedded text if available is a reasonable backstop if the above doesn't work. 4. Build a sophisticated pipeline that does all of the above, and then sends the outputs to a "judge" agent to tell you which result is better and then accept that. This can be very reliable, and doesn't take a lot of coding. But it's the big guns, and most of the time you won't need it.

When working with multiple long, complex PDFs for a single project -- do people just upload directly to a frontier model or convert to Markdown first?

Well apparently I'm one of the 7%. Hit my limit earlier today in *one* hour unexpectedly. It was before this was announced so I was *very* confused. I toggle between Codex and Claude, but when I get into a groove with one I just stick with them. Guess I need to adjust.

If this could be made to work with @gitbutler or @graphite PR stacks holy moly that would be a crazy unlock.

@addison @kieranklaassen @GeoffreyHuntley @ryancarson @gregisenberg @syncthing Not super fun. Though fwiw at some point I just threw Claude at the problem (in the CLI and browser) and it hammered through. Now have it working on my three machines, plus my phone. Works like a dream.

@mg @kieranklaassen @GeoffreyHuntley @ryancarson @gregisenberg @syncthing I tried this a month ago, and wasn't in love with the setup process.

AI builders, what's the best way to sync skills over three different machines? (eg. MacStudio, Mac Mini, and MacbookPro) I've got ~100 skills I'm using globally. cc @kieranklaassen @GeoffreyHuntley @ryancarson @gregisenberg

@addison @kieranklaassen @GeoffreyHuntley @ryancarson @gregisenberg Get @syncthing running on all of your machines (can even work in remote machines/containers). Create a share that includes your `~/<user>/<harness>/skills/` directory (and others if you wish). Then let them sync and you're good to go!

@kieranklaassen @GeoffreyHuntley @ryancarson @gregisenberg If you haven't solved this, that makes me feel less dumb. Thanks for responding!!

It can definitely do a lot. For me, the app-specific window sizing was what I was after. Coupled with being able to set a single hotkey for all app-specific window sizing was killer. Then add the mouse button gesture and it was the trifecta. So with a press and hold on my scroll wheel, then cursor down (pull back), the windows always snap precisely to where I want them every time…specific to each app. That was my primary reason for using Rectangle Pro for a long time...and then Aerospace kind of took its place for most of the time. It's a different mode for sure, but I still use that old mouse gesture to this day when I go back to "floating" mode for certain apps with Aerospace.

@mg @dwr I think Rectangle is enough.

Best window management software for macOS? yabai? Amethyst? Magnet? Moom?

@zoink Yo heads up…was digging through the docs for this and right now the breadcrumbs in each doc aren't clickable. Makes navigation a little less easy. Awesome MCP stuff though!

Agents, meet the Figma canvas

@AndrewWarner @alexframegreen Appreciate that. It's so easy sometimes to miss stuff like this. When you're heads-down building stuff, eventually your eyes gloss over and you can just stop noticing things. Happens all the time. Sending in stuff like this doesn't take much time, but hopefully it helps!

@mg @alexframegreen Matt, I love your attention to details like that.