J
Jesse Vincent
blog.fsck.com · Personal blog · on HN since 2009
Jesse Vincent, a software and hardware developer, writes about using coding agents and his Superpowers workflow for Claude Code.
What HN saysCommenters recommend his Superpowers skills and workflow as working well for interactive, iterative development, and link his CLAUDE.md and demo transcript.
37HN people shared it
12linked it in comments
37stories submitted
1.2Kstory points
4 months agolast shared
2009people per year2026
Most-shared posts
- 1Superpowers: How I'm using coding agents in October 20254 people · 435 points · first shared 2025 · 231 comments on HN
- 2Jesse Vincent: How I'm using coding agents in September, 20254 people · 11 points · first shared 2025 · 1 comments on HN
- 3Using GraphViz for Claude.md3 people · 6 points · first shared 2025 · 1 comments on HN
- 4Prototype ergonomic mechanical keyboards2 people · 227 points · first shared 2013 · 142 comments on HN
- 5Learn from my misery: Don't buy a nook.2 people · 178 points · first shared 2010 · 59 comments on HN
- 6Dear diary, today the user asked me if I'm alive2 people · 46 points · first shared 2025 · 74 comments on HN
- 7Superpowers 62 people · 5 points · first shared 2026 · discussion on HN
- 8Froyo for nookcolor2 people · 4 points · first shared 2010 · discussion on HN
- 9Wordiest: Android APK ported to iOS by ChatGPT 5.22 people · 3 points · first shared 2025 · discussion on HN
- 10Building a Keyboard: Part 21 people · 113 points · first shared 2012 · 22 comments on HN
- 11Building a Keyboard1 people · 90 points · first shared 2012 · 14 comments on HN
- 12One weird trick makes the AI a better writer1 people · 6 points · first shared 2025 · discussion on HN
- 13Fixing my Facebook feed with ChatGPT Atlas1 people · 5 points · first shared 2025 · 1 comments on HN
- 14When it comes to MCPs, everything we know about API design is wrong1 people · 4 points · first shared 2025 · 1 comments on HN
- 15Some New Agentic Patterns1 people · 3 points · first shared 2026 · discussion on HN
What HN people wrote when they linked it
CharlesW · 2026-07-02
As a long time user, I'd recommend checking out https://github.com/obra/superpowers#the-basic-workflow. If that reasonates with you, try using it to develop a few features or capabilities.
It works very well for the way that I work (interactively and iteratively, not "one-shot"), and it helps me to better work in less time. Superpowers is one of the few skill/agent suites I use for all software development projects.
If you like building skill/agents, the posts at https://blog.fsck.com/ are a great resource for learning how to do well. The effectiveness of my project Axiom (a skill/agent suite for Apple OS developers) has benefited enormously from the knowledge that Superpowers' creator Jesse Vincent has been kind enough to share.
TLDR: You owe it to yourself to try it.
ryancnelson · 2025-10-16
The uptake on Claude-skills seems to have a lot of momentum already! I was fascinated on Tuesday by “Superpowers” , https://blog.fsck.com/2025/10/09/superpowers/ … and then packaged up all the tool-building I’ve been working on for awhile into somewhat tidy skills that i can delegate agents to:
http://github.com/ryancnelson/deli-gator I’d love any feedback
SeanAnderson · 2025-10-09
https://raw.githubusercontent.com/obra/dotfiles/6e088092406cf1e3cc78d1… contains the following entry:
"- If you're uncomfortable pushing back out loud, just say "Strange things are afoot at the Circle K". I'll know what you mean"
Most of the rules seem rationale. This one really stands out as abnormal. Anyone have any idea why the engineer would have felt compelled to add this rule?
This is from https://blog.fsck.com/2025/10/05/how-im-using-coding-agents-in-septemb… mentioned in another comment
jrh3 · 2025-10-16
The tools I build for Claude Code keep reducing back to just using Claude Code and watching Anthropic add what I need. This is my tool for brownfield projects with Claude Code. I added skills based on https://blog.fsck.com/2025/10/09/superpowers/
https://github.com/RossH3/context-tree - Helps Claude and humans understand complex brownfield codebases through maintained context trees.
iamjfu · 2025-10-12
I am interested by this link: https://blog.fsck.com/blog/2025/superpowers/superpowers-demo.txt
``` Claude Code v2.0.13 Sonnet 4.5 (with 1M token context) Claude Max /Users/jesse/tmp/new-tool/.worktrees/todo-cli ```
How does this person have access to Sonnet 4.5 with 1m token context? I don't see this referenced anywhere when I search or when I ask Claude about it.
threecheese · 2025-10-09
If you really want your mind blown, see what Jesse is doing (successfully, which I almost can’t believe) with Graphviz .dot notation and Claude.md:
https://blog.fsck.com/2025/09/29/using-graphviz-for-claudemd/
simonw · 2025-10-09
That doesn't surprise me too much coming from Jesse. See also his attempt to give Claude a "feelings journal" https://blog.fsck.com/2025/05/28/dear-diary-the-user-asked-me-if-im-al…
gkop · 2015-06-14
No I haven't seen videos. Honestly I'm just impressed by the level of iteration from prototype to prototype that Jesse has blogged about extensively for some time, leading up to http://blog.fsck.com/2013/12/model-00.html .
TacticalCoder · 2014-01-29
Most of these keyboards based on the ErgoDox (and the ErgoDox itself) make the mistake of considering that the thumb is a finger positioned like the others. And the keys you're supposed to hit with your thumbs are just placed in a crazy way (totally non-ergonomic IMHO).
To me one of the rare person who really "got it" is "Jesse" (he's both here, on GeekHack and on Deskthority) with its "butterfly" keyboard.
That's one of the only split (and ergonomic) keyboard that takes into account the fact that the thumb's opposition-apposition makes it unlike any other finger.
Look at his "butterfy" keyboard here and how smartly the keys you're to hit with the thumbs are positionned:
http://blog.fsck.com/2013/12/better-and-better-keyboards.html
obrajesse · 2013-12-12
Actually, I _started_ from an ErgoDox. :)
( http://blog.fsck.com/2013/01/pinkies-and-your-brain.html )
The ErgoDox is really the two halves of a Kinesis flattened.
Keyboard.IO is a little bit different. There's a splay of a few degrees between the columns that map to each finger. A bunch of the work you do with your pinkies on the ErgoDox or just about any other keyboard moves to your thumbs. And yes, it ended up as a single keyboard. I really, really wanted to do something that was two separate pieces. Between the risks it would add to the mechanical design and the fact that I found myself intensely frustrating that the two halves of the ErgoDox were never in quite the places I expected them to be, we've decided to run with a single-piece unit, at least for the Model 01.
timknauf · 2010-01-23
Here's that Nook piece for future reference:
http://blog.fsck.com/2010/01/dont-buy-a-nook.html
http://news.ycombinator.com/item?id=1071138
tao_oat · 2025-10-17
Skills were released in Claude Code, what, yesterday? I doubt there's a simple answer to this -- it'll depend on the model, task, etc.
You could try to get your agent to test its own skills. From https://blog.fsck.com/2025/10/09/superpowers:
> As Claude and I build new skills, one of the things I ask it to do is to "test" the skills on a set of subagents to ensure that the skills were comprehensible, complete, and that the subagents would comply with them. (Claude now thinks of this as TDD for skills and uses its RED/GREEN TDD skill as part of the skill creation skill.)
> The first time we played this game, Claude told me that the subagents had gotten a perfect score. After a bit of prodding, I discovered that Claude was quizzing the subagents like they were on a gameshow. This was less than useful. I asked to switch to realistic scenarios that put pressure on the agents, to better simulate what they might actually do.