Log inSign up
Joan León 🏞️⚡️
21.5K posts
Joan León 🏞️⚡️ profile banner
@nucliweb

Joan León 🏞️⚡️

@nucliweb
⚡️ Web Performance Artisan at @perfreviews_ | @GoogleDevExpert in #WebTech | @cloudinary Ambassador
Girona, Catalunya
nucliweb.net
Joined August 2008
4,306
Following
12.1K
Followers
RepliesRepliesRepostsRepostsMediaMediaArticlesArticles

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @nucliweb
    Joan León 🏞️⚡️
    @nucliweb
    Jun 4, 2023
    I have published a website with Web Performance Snippets to make it more user-friendly, more orderly, and with a search feature ⚡️💾 webperf-snippets.nucliweb.net #WebPerf #Performance #PerfTools
    WebPerf Snippets
    From webperf-snippets.nucliweb.net
    3
  • @nucliweb
    Joan León 🏞️⚡️
    @nucliweb
    Aug 16
    I love the optimization: web, rendering, images, video, and now tokens. @lydiahallie published a great guide to Maximizing the value of your Claude Code sessions claude.com/blog/maximizin… #AIOptimization #AI #Claude
    A dark-themed presentation slide titled "TL;DR" displaying tips for optimizing Claude API usage and token efficiency. The slide is divided into two columns:

Left column discusses:
- Using `/clear` command between tasks to prevent context carryover and reduce token usage
- Setting model and effort level before starting a session to avoid breaking the prompt cache mid-conversation
- Mentioning files with @ notation instead of naming them, to attach files directly and save API calls

Right column covers:
- Adding quiet flags to commands or running them in a subagenr to manage noisy output while keeping results in the conversation
- Running `/context` once per session to review loaded content (CLAUDE.md and MCP tool definitions) and remove unnecessary items
- Running `/compact` before breaks, since prompt cache expires after an hour and summarizing conversations is cheaper while the cache is active
  • @nucliweb
    Joan León 🏞️⚡️
    @nucliweb
    Aug 13
    139 guides, a quarter of a million tokens. The skill that serves them costs 250. It holds no knowledge: it teaches the agent to go find it, with an embeddings model that runs locally, no network and no API keys. joanleon.dev/en/modern-web-… #AI #WebDev #CodingAgents
    A skill that knows nothing: the architecture of Modern Web Guidance | Joan León
    From joanleon.dev
  • @nucliweb
    Joan León 🏞️⚡️
    @nucliweb
    Aug 11
    CrUX data isn't 28 days old. It's two days old What takes 28 days is for the window to fully turn over, and that's why p75 sits still for two weeks and then drops all at once I wrote about it, with two interactive demos joanleon.dev/en/crux-28-day… #WebPerf #CoreWebVitals #CrUX
    The CrUX 28-day rolling window | Joan León
    From joanleon.dev
  • @nucliweb
    Joan León 🏞️⚡️
    @nucliweb
    Aug 5
    A letter from @addyosmani landed in my mailbox today, thanking me for my work on Agent Skills. I got in through web performance and stayed for the rest. Thinking about contributing to open source? Start small. Docs and honest reviews count. github.com/addyosmani/age…
    A printed thank-you letter from Addy Osmani on a dark background, hand-signed and dated 2026, next to its opened envelope postmarked San Francisco. Four stickers lie beside it: "Coder", "Computer Club", a Cmd+Z one reading "Just Undo It", and a perfume bottle reading "#perfmatters".
    1