Wildroot

Search

199 posts · best match first · searched 136,196 posts from the last 48 hours · 0.69 s

Best match combines word and meaning matches. Phrases, hashtags, accounts and websites guide which posts fit; timely queries also favor recent posts. Match labels describe why a post appears, not its quality or accuracy.

Show newest first

  1. @mengli512.bsky.socialBluesky

    ECC packs 68 agents, 292 skills and 94 commands into Claude Code, but the real cost is your context window, so install selectively. How much of your 200k context are you willing to trade? #ECC #agents #Claude #ClaudeCode pythonlibraries.substack.com/p/292-skills...

    pythonlibraries.substack.com 292 skills at once in Claude Code, how much 200k context left?

    Has the hashtagAI
  2. My personal website is live: gcheseaux.ch A CV in a word processor file became a bilingual site with a blog, generated PDF CVs, accessibility checks and a small build script. Built over a few evenings with Claude Code and Mistral Vibe, and every line reviewed by me. The first blog post tells the whole story, including what I did not let AI do: gcheseaux.ch/blog/how-i-built-… #AI #ClaudeCode #WebDev #BuildInPublic

    gcheseaux.ch Guillaume Cheseaux

    Has the hashtagAI
  3. @juneberri3.bsky.socialBluesky

    with all of these claudecoded "pc ports" coming out, u might as well just play on emulator instead. what is even the benefit at this point

    Matches your words
  4. @robotpony@mas.toMastodon

    I'm not sure how Claude does it, but in my workflow I screenshot visual bugs with an overlay, explain it, and it scans and finds it in seconds. This is on extremely slow internet. It feels fast enough to be local. #claude_code

    Same subjectAI
  5. @robotpony@mas.toMastodon

    Claude is getting good at measuring things in browsers. This replaces a lot of manual labour with tools like XScope and the browser inspector. The whole process is similar to working with a human developer: log a bug with a screenshot, ask it to review and mock up a fix, then approve or adjust. It uses minimal tokens, too. #claude-code

    Same subject
  6. @dev.toBluesky

    A 62-year-old dev with almost 30 years in the field says Claude handles about half the workload. This dev has Kiro rebuild Winamp, then weighs where taste and deep stack knowledge still matter in frontend work. { author: @erikch.bsky.social } dev.to/erikch/are-f...

    dev.to Are Frontend Developers Cooked? Is Frontend design safe?

    Same subjectAI
  7. @maddog-here.bsky.socialBluesky

    Most of my Claude Code steps didn't need Opus, so I built maddog. It routes each step by decision type: Haiku for decided work, Sonnet for one choice, Opus for discovery. My own sessions: 57% of output tokens on Haiku/Sonnet vs 31% without it. github.com/Harish-here/maddog

    Same subjectAI
  8. @zvezda.bsky.socialBluesky

    Like you can just get SADX on steam for cheap, and download the dreamcast mods. No need to destroy the environment for a shitty recomp

    Same subject
  9. @custat.netBluesky

    Great, seeing people lumping .hack fans as "all in on AI" now probably because of the fucking Claude decomp

    Same subject

Search looks through the last 48 hours of public posts for your words, "exact phrases", #hashtags, @handles and websites, and also finds posts about the same thing by meaning. New posts join about every 10 minutes. We only include posts whose authors allow logged-out viewing (Bluesky) or search (Mastodon, indexable accounts), and we re-check Bluesky authors each time we show a page. Likes and follower counts never decide the order. Meaning search uses a model on Wildroot’s server. Query text may be sent through OpenRouter to an embedding provider if that model is unavailable or for a quality-check sample. Wildroot does not save query text to disk. Looking for posts like one you have? Similar posts. How to opt out.