AI Resources
Cha Khan · From the talk “It Just Keeps Getting Faster”, 19 Oct 2026
What I use every day to build with AI agents, in the order a piece of work goes.
Start hereELI5Any topic as a picture explainer. Install it first, then let it explain the rest of this list to you.Open →Talk to your agent
Wispr FlowEnkeon
Agree on what to build
Grill Me
How to be more ambitious
HTML, not MarkdownBuild it right
pstack
HTML, not MarkdownMake it look good
taste-skillImpeccable
diagram-design
AnatomySee the work
HTML, not Markdown
ELI5Start here
Lavish
i-have-adhd
AXI
agent-browserShip it safely
no-mistakesRun many agents
firstmate
T3 Codeherdr
What I find most useful
Or hand it to your agent
It installs ELI5, looks at the work you do, and makes you an ELI5 page on the tools that fit it.
Read resources.md. Install ELI5 from it right away. Then look at how I have been working and the work I have been doing, and pick the resources that would be most useful and relevant to me. Use /eli5 to make one ELI5 page that walks me through them: what each one does for me, why it fits my work, and the first thing to try. Ask before you install anything else.
Wispr Flow
Talk to your agent instead of typing. Messy is fine.
Talk to your agent
Wispr


Enkeon
One memory for you and all your AI tools. Context carries across sessions.
Talk to your agent
Enkeon

Grill Me
The agent interviews you until it understands what you want.
Agree on what to build
Matt Pocock’s skills

How to be more ambitious
Models can do more than most people ask. Aim higher, with specific goals.
Agree on what to build
Felix Rieseberg
- speeddo the same work faster (the article skips this one)
- altitudeaim at the outcome: what should happen next?
- depthuse the real tools and raw data of top professionals
- rangeborrow how other fields would solve it

pstack
Makes the agent work like a careful senior engineer, and prove it.
Build it right
Lauren Tan (poteto), Cursor





taste-skill
Art direction and reference images instead of generic AI pages.
Make it look good
Leon Lin




Impeccable
Critiques and polishes any interface: layout, type, colour, motion.
Make it look good
Paul Bakaus




diagram-design
Plain words in, a clean diagram out. 44 diagram types.
Make it look good
Cathryn Lavery





Anatomy
Explains an idea by drawing it as a real, working machine. Detailed isometric figures that move.
Make it look good
wheresryan22

The Unreasonable Effectiveness of HTML
Ask for an HTML page, not a wall of Markdown.
Agree on what to build · Build it right · See the work
Thariq Shihipar, Claude Code team

ELI5
Any topic as a picture explainer: big visuals, few words.
See the workStart here
Thariq Shihipar, Claude Code community plugin

Lavish
An editor for your agent’s HTML pages. Click, change, send it back.
See the work
Kun Chen

i-have-adhd
Your agent leads with the answer and the next step.
See the work
ayghri
Great question! Let me think about this. Your auth flow has a few moving pieces: the middleware, the token verification, and the cookie handling. Looking at src/auth.ts, the verifyToken function (around lines 42-58) seems to be using an older jsonwebtoken API. One approach would be to update the package and rewrite that function. After making the change, you'd want to run the auth tests to confirm nothing breaks. By the way, you might also want to look at your dependency versions overall. Hope this helps! Let me know if you want to dig deeper.
Edit src/auth.ts:42 to update the token validation. 1. Open src/auth.ts 2. Replace verifyToken (lines 42–58) with the snippet below 3. Run npm test -- auth.spec.ts Next: paste the first failing line if any test fails.

AXI
Command-line tools built for agents: GitHub and Chrome, fewer tokens, fewer mistakes.
See the work
Kun Chen

agent-browser
Your agent opens, clicks and screenshots a real browser to check its work.
See the work
Vercel Labs
- openagent-browser open localhost:3000
- snapshotreads the page: buttons, links, fields
- clickagent-browser click @e3
- screenshotagent-browser screenshot page.png
- checkthe agent looks, then fixes what is wrong


no-mistakes
Make no mistakes.
Ship it safely
Kun Chen

firstmate
Talk to one agent. It runs a crew and checks their work.
Run many agents
Kun Chen

- yousay what you want, once
- firstmateplans and splits the work
- crewagents build the parts in parallel
- checkevery part is reviewed
- shipmerged, you get one report

T3 Code
One app for Claude, Codex, Cursor and more, side by side.
Run many agents
Theo, ping.gg

herdr
A terminal where many agents run in panes you can watch and talk to.
Run many agents
herdr
