Skip to content

aeonfun/soul.md

Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.

FileKindSize
SKILL.mdskill md4.5 KB
examples/_GUIDE.mdmarkdown1.5 KB
examples/ansem/MEMORY.mdmarkdown645 B
examples/ansem/README.mdmarkdown4.2 KB
examples/ansem/SOUL.mdmarkdown12.5 KB
examples/ansem/STYLE.mdmarkdown10.7 KB
examples/ansem/data/blknoiz06_all.jsonlother38.3 MB
examples/ansem/examples/bad-outputs.mdmarkdown6.1 KB
examples/ansem/examples/good-outputs.mdmarkdown8.7 KB
examples/bad-outputs.template.mdmarkdown2.2 KB
examples/elon-musk/MEMORY.mdmarkdown153 B
examples/elon-musk/QUICKSTART.mdmarkdown4.0 KB
examples/elon-musk/README.mdmarkdown3.5 KB
examples/elon-musk/SOUL.mdmarkdown10.5 KB
examples/elon-musk/STYLE.mdmarkdown5.8 KB
examples/elon-musk/data/sources.mdmarkdown1.2 KB
examples/elon-musk/examples/bad-outputs.mdmarkdown2.6 KB
examples/elon-musk/examples/good-outputs.mdmarkdown3.2 KB
examples/elon-musk/tests/prediction-test.mdmarkdown5.5 KB
examples/garry-tan/MEMORY.mdmarkdown428 B
examples/garry-tan/README.mdmarkdown2.1 KB
examples/garry-tan/SOUL.mdmarkdown13.3 KB
examples/garry-tan/STYLE.mdmarkdown9.2 KB
examples/garry-tan/data/influences.mdmarkdown2.6 KB
examples/garry-tan/examples/bad-outputs.mdmarkdown4.8 KB
examples/garry-tan/examples/good-outputs.mdmarkdown4.5 KB
examples/garry-tan/scripts/fetch_writing.pyscript4.0 KB
examples/garry-tan/scripts/fetch_x.pyscript3.7 KB
examples/garry-tan/scripts/fetch_yt.pyscript2.7 KB
examples/garry-tan/tests/platform_tests.mdmarkdown1006 B
examples/garry-tan/tests/prediction_test.mdmarkdown4.7 KB
examples/garry-tan/tests/results_gpt-4o-mini.mdmarkdown5.9 KB
examples/garry-tan/tests/run_weak_model.pyscript5.5 KB
examples/garry-tan/tests/scores_gpt-4o-mini.mdmarkdown3.6 KB
examples/garry-tan/tests/weak_model_test.mdmarkdown5.3 KB
examples/good-outputs.template.mdmarkdown2.4 KB
examples/hunter-biden/MEMORY.mdmarkdown1.0 KB
examples/hunter-biden/QUICKSTART.mdmarkdown3.3 KB
examples/hunter-biden/README.mdmarkdown6.1 KB
examples/hunter-biden/SOUL.mdmarkdown12.7 KB
examples/hunter-biden/STYLE.mdmarkdown9.1 KB
examples/hunter-biden/data/influences.mdmarkdown4.1 KB
examples/hunter-biden/data/x/tweets.jsonconfig96.0 KB
examples/hunter-biden/data/x/tweets.mdmarkdown65.7 KB
examples/hunter-biden/examples/bad-outputs.mdmarkdown7.4 KB
examples/hunter-biden/examples/good-outputs.mdmarkdown20.7 KB
examples/hunter-biden/tests/prediction-test.mdmarkdown4.2 KB
examples/karpathy/MEMORY.mdmarkdown515 B
examples/karpathy/QUICKSTART.mdmarkdown2.2 KB
examples/karpathy/README.mdmarkdown7.4 KB
examples/karpathy/SOUL.mdmarkdown15.3 KB
examples/karpathy/STYLE.mdmarkdown11.6 KB
examples/karpathy/data/github/karpathy_LLM101n_README.mdmarkdown2.3 KB
examples/karpathy/data/github/karpathy_arxiv-sanity-preserver_README.mdmarkdown6.8 KB
examples/karpathy/data/github/karpathy_char-rnn_README.mdmarkdown12.5 KB
examples/karpathy/data/github/karpathy_llm.c_README.mdmarkdown16.1 KB
examples/karpathy/data/github/karpathy_micrograd_README.mdmarkdown2.4 KB
examples/karpathy/data/github/karpathy_minbpe_README.mdmarkdown9.1 KB
examples/karpathy/data/github/karpathy_nanoGPT_README.mdmarkdown13.5 KB
examples/karpathy/data/github/karpathy_nn-zero-to-hero_README.mdmarkdown6.7 KB
examples/karpathy/data/influences.mdmarkdown4.9 KB
examples/karpathy/data/transcripts/7xTGNNLPyMI.en.txtmarkdown208.7 KB
examples/karpathy/data/transcripts/P6sfmUTpUmc.en.txtmarkdown108.9 KB
examples/karpathy/data/transcripts/PaCmpygFfXo.en.txtmarkdown96.3 KB
examples/karpathy/data/transcripts/SOURCES.mdmarkdown2.7 KB
examples/karpathy/data/transcripts/TCH_1BHY58I.en.txtmarkdown63.3 KB
examples/karpathy/data/transcripts/VMj-3S1tku0.en.txtmarkdown118.3 KB
examples/karpathy/data/transcripts/c3b-JASoPi0.en.txtmarkdown39.5 KB
examples/karpathy/data/transcripts/hM_h0UA7upI.en.txtmarkdown55.4 KB
examples/karpathy/data/transcripts/kCc8FmEb1nY.en.txtmarkdown105.3 KB
examples/karpathy/data/transcripts/l8pRSuU81PU.en.txtmarkdown213.9 KB
examples/karpathy/data/transcripts/q8SA3rM6ckI.en.txtmarkdown102.5 KB
examples/karpathy/data/transcripts/t3YJ5hKiMQ0.en.txtmarkdown52.9 KB
examples/karpathy/data/transcripts/zduSFxRajkE.en.txtmarkdown122.6 KB
examples/karpathy/data/writing/ai-short-peek.htmlother55.7 KB
examples/karpathy/data/writing/biohacking-lite.htmlother41.2 KB
examples/karpathy/data/writing/blockchain.htmlother297.3 KB
examples/karpathy/data/writing/forward-pass.htmlother14.6 KB
examples/karpathy/data/writing/lecun1989.htmlother25.0 KB
examples/karpathy/data/writing/medium.htmlother6.6 KB
examples/karpathy/data/writing/microgpt.htmlother93.8 KB
examples/karpathy/data/writing/phd.htmlother56.7 KB
examples/karpathy/data/writing/recipe.htmlother32.9 KB
examples/karpathy/data/writing/rl.htmlother54.4 KB
examples/karpathy/data/writing/rnn-effectiveness.htmlother79.9 KB
examples/karpathy/data/writing/software-2.0.htmlother235.3 KB
examples/karpathy/data/writing/state-of-cv.htmlother13.3 KB
examples/karpathy/data/x/README.mdmarkdown564 B
examples/karpathy/data/x/curated-tweets.mdmarkdown35.7 KB
examples/karpathy/data/x/posts-original.jsonconfig171.1 KB
examples/karpathy/data/x/profile.jsonconfig470 B
examples/karpathy/data/x/replies.jsonconfig105.5 KB
examples/karpathy/examples/bad-outputs.mdmarkdown6.2 KB
examples/karpathy/examples/good-outputs.mdmarkdown14.8 KB
examples/karpathy/scripts/fetch-data.shscript6.6 KB
examples/karpathy/scripts/weak-model-test.mjsscript15.2 KB
examples/karpathy/tests/prediction-test.mdmarkdown6.1 KB
examples/karpathy/tests/weak-model-results.mdmarkdown12.6 KB
examples/michael-saylor/MEMORY.mdmarkdown351 B
examples/michael-saylor/QUICKSTART.mdmarkdown3.5 KB
examples/michael-saylor/README.mdmarkdown6.5 KB
examples/michael-saylor/SOUL.mdmarkdown13.4 KB
examples/michael-saylor/STYLE.mdmarkdown7.0 KB
examples/michael-saylor/data/influences.mdmarkdown2.5 KB
examples/michael-saylor/examples/bad-outputs.mdmarkdown3.7 KB
examples/michael-saylor/examples/good-outputs.mdmarkdown7.0 KB
examples/michael-saylor/tests/prediction-test.mdmarkdown4.3 KB
examples/steipete/QUICKSTART.mdmarkdown5.1 KB
examples/steipete/README.mdmarkdown6.9 KB
examples/steipete/SOUL.mdmarkdown16.8 KB
examples/steipete/STYLE.mdmarkdown12.1 KB
examples/steipete/data/github/openclaw--openclaw.README.mdmarkdown84.0 KB
examples/steipete/data/github/openclaw--openclaw.VISION.mdmarkdown5.3 KB
examples/steipete/data/github/steipete--Aspects.README.mdmarkdown10.8 KB
examples/steipete/data/github/steipete--CodexBar.README.mdmarkdown8.5 KB
examples/steipete/data/github/steipete--InterposeKit.README.mdmarkdown11.0 KB
examples/steipete/data/github/steipete--Peekaboo.README.mdmarkdown7.4 KB
examples/steipete/data/github/steipete--Tachikoma.README.mdmarkdown3.9 KB
examples/steipete/data/github/steipete--VibeMeter.README.mdmarkdown13.3 KB
examples/steipete/data/github/steipete--agent-rules.README.mdmarkdown146 B
examples/steipete/data/github/steipete--agent-scripts.README.mdmarkdown5.8 KB
examples/steipete/data/github/steipete--birdclaw.README.mdmarkdown15.8 KB
examples/steipete/data/github/steipete--claude-code-mcp.README.mdmarkdown12.7 KB
examples/steipete/data/github/steipete--mcporter.README.mdmarkdown28.4 KB
examples/steipete/data/github/steipete--oracle.README.mdmarkdown28.3 KB
examples/steipete/data/github/steipete--poltergeist.AGENTS.mdmarkdown9.4 KB
examples/steipete/data/github/steipete--poltergeist.README.mdmarkdown13.5 KB
examples/steipete/data/influences.mdmarkdown10.7 KB
examples/steipete/data/transcripts/3-lessons-you-can-use-today.txtmarkdown10.9 KB
examples/steipete/data/transcripts/agentic-workflow-behind-openclaw.txtmarkdown12.6 KB
examples/steipete/data/transcripts/builders-unscripted-ep1.txtmarkdown31.4 KB
examples/steipete/data/transcripts/first-public-appearance-since-launch.txtmarkdown34.4 KB
examples/steipete/data/transcripts/i-ship-code-i-dont-read.txtmarkdown114.7 KB
examples/steipete/data/transcripts/lex-fridman-491.txtmarkdown158.5 KB
examples/steipete/data/transcripts/lex-fridman-clip-ai-agents.txtmarkdown25.9 KB
examples/steipete/data/transcripts/maximize-claude-code-subscription.txtmarkdown25.7 KB
examples/steipete/data/writing/2012-dont-call-willchangevalueforkey.htmlother59.8 KB
examples/steipete/data/writing/2012-hacking-block-support-into-uimenuitem.htmlother183.8 KB
examples/steipete/data/writing/2012-moving-on.htmlother62.2 KB
examples/steipete/data/writing/2012-nsurlcache-uses-a-disk-cache-as-of-ios5.htmlother54.5 KB
examples/steipete/data/writing/2012-pimping-recursivedescription.htmlother55.6 KB
examples/steipete/data/writing/2012-reboot.htmlother50.0 KB
examples/steipete/data/writing/2012-using-subscripting-with-xcode-4_4-and-ios-4_3.htmlother59.5 KB
examples/steipete/data/writing/2014-a-story-about-swizzling-the-right-way-and-touch-forwarding.htmlother112.5 KB
examples/steipete/data/writing/2025-applescript-cli-macos-complete-guide.htmlother110.7 KB
examples/steipete/data/writing/2025-automatic-observation-tracking-uikit-appkit.htmlother104.4 KB
examples/steipete/data/writing/2025-claude-code-anonymous.htmlother54.8 KB
examples/steipete/data/writing/2025-claude-code-is-my-computer.htmlother72.0 KB
examples/steipete/data/writing/2025-code-signing-and-notarization-sparkle-and-tears.htmlother101.6 KB
examples/steipete/data/writing/2025-commanding-your-claude-code-army.htmlother75.2 KB
examples/steipete/data/writing/2025-essential-reading-august-2025.htmlother78.7 KB
examples/steipete/data/writing/2025-essential-reading-july-2025.htmlother73.2 KB
examples/steipete/data/writing/2025-essential-reading.htmlother79.4 KB
examples/steipete/data/writing/2025-finding-my-spark-again.htmlother55.8 KB
examples/steipete/data/writing/2025-introducing-demark-html-to-markdown-in-swift.htmlother63.9 KB
examples/steipete/data/writing/2025-live-coding-session-building-arena.htmlother59.8 KB
examples/steipete/data/writing/2025-llm-codes-transform-developer-docs.htmlother59.9 KB
examples/steipete/data/writing/2025-logging-privacy-shenanigans.htmlother108.4 KB
examples/steipete/data/writing/2025-mcp-best-practices.htmlother69.0 KB
examples/steipete/data/writing/2025-migrating-700-tests-to-swift-testing.htmlother178.7 KB
examples/steipete/data/writing/2025-optimal-ai-development-workflow.htmlother67.8 KB
examples/steipete/data/writing/2025-peekaboo-2-freeing-the-cli-from-its-mcp-shackles.htmlother76.2 KB
examples/steipete/data/writing/2025-peekaboo-mcp-lightning-fast-macos-screenshots-for-ai-agents.htmlother67.1 KB
examples/steipete/data/writing/2025-poltergeist-ghost-keeps-builds-fresh.htmlother81.8 KB
examples/steipete/data/writing/2025-self-hosting-ai-models.htmlother114.9 KB
examples/steipete/data/writing/2025-shipping-at-inference-speed.htmlother70.1 KB
examples/steipete/data/writing/2025-showing-settings-from-macos-menu-bar-items.htmlother110.3 KB
examples/steipete/data/writing/2025-signature-flicker.htmlother69.5 KB
examples/steipete/data/writing/2025-startup-slop.htmlother69.7 KB
examples/steipete/data/writing/2025-stats-store-privacy-first-sparkle-analytics.htmlother58.6 KB
examples/steipete/data/writing/2025-stop-overthinking-ai-subscriptions.htmlother67.4 KB
examples/steipete/data/writing/2025-the-future-of-vibe-coding.htmlother88.9 KB
examples/steipete/data/writing/2025-understanding-codebases-with-ai-gemini-workflow.htmlother62.5 KB
examples/steipete/data/writing/2025-vibe-meter-2-claude-code-usage-calculation.htmlother71.3 KB
examples/steipete/data/writing/2025-vibe-meter-monitor-your-ai-costs.htmlother69.9 KB
examples/steipete/data/writing/2025-vibetunnel-first-anniversary.htmlother59.0 KB
examples/steipete/data/writing/2025-vibetunnel-turn-any-browser-into-your-mac-terminal.htmlother77.7 KB
examples/steipete/data/writing/2025-when-ai-meets-madness-peters-16-hour-days.htmlother70.4 KB
examples/steipete/data/writing/2026-openclaw.htmlother52.1 KB
examples/steipete/data/writing/command-your-claude-code-army-reloaded.htmlother59.4 KB
examples/steipete/data/writing/index.htmlother34.0 KB
examples/steipete/data/writing/just-one-more-prompt.htmlother59.7 KB
examples/steipete/data/writing/just-talk-to-it.htmlother80.8 KB
examples/steipete/data/x/curated-tweets.mdmarkdown42.1 KB
examples/steipete/data/x/openclaw.posts-original.jsonconfig68.4 KB
examples/steipete/data/x/openclaw.profile.jsonconfig478 B
examples/steipete/data/x/openclaw.replies.jsonconfig74.6 KB
examples/steipete/data/x/steipete.posts-original.jsonconfig95.5 KB
examples/steipete/data/x/steipete.profile.jsonconfig485 B
examples/steipete/data/x/steipete.replies.jsonconfig2 B
examples/steipete/examples/bad-outputs.mdmarkdown10.2 KB
examples/steipete/examples/good-outputs.mdmarkdown15.9 KB
examples/steipete/scripts/fetch-data.shexecutablescript11.4 KB
examples/steipete/scripts/pull-x.mjsscript3.9 KB
examples/steipete/scripts/weak-model-test.mjsscript17.7 KB
examples/steipete/tests/prediction-test.mdmarkdown13.2 KB
examples/steipete/tests/weak-model-results.mdmarkdown11.6 KB
examples/vitalik-buterin/MEMORY.mdmarkdown972 B
examples/vitalik-buterin/QUICKSTART.mdmarkdown3.3 KB
examples/vitalik-buterin/README.mdmarkdown6.9 KB

examples/steipete/data/transcripts/3-lessons-you-can-use-today.txt

View on GitHub
Peter Steinberger, the creator of
Clawbot, which just changed its name to
Maltbot and then as of this morning is
now called OpenClaw, I believe, just
went on the Pragmatic Engineer podcast
and gave a banger podcast about how he
built Claudebot, and then his thoughts
on kind of the future of AI development
and development in general. I highly
recommend that you go over to the
Pragmatic Engineer channel, which is a
great channel, and watch that full
podcast if you're into knowing how great
engineers build stuff. There are three
takeaways from that podcast that
directly influence how I'm building out
the rest of the build anything app and I
thought I'd share those with you so you
can weave those into your development
process. The first one is parallel agent
coding loops. So he talked about this
and he actually used five to 10 agents
while he's building out Clawbot which is
not a surprise from somebody who's
building out something like Claudebot or
OpenClaw. But here's one way that you
can think of doing this and there's
three distinct different types of agents
that you can use. The first agent is a
builder agent. The second agent is like
a pair programming agent that checks the
code for the first agent. And the third
agent is like an alignment agent or a
synthesis agent. The first thing you
want to do is break your app into
different sections that don't really
overlap with each other. So like maybe
one section is your onboarding flow for
users and another section is your
settings management and another section
is maybe you're have an inbox app that
you're building. It's important that you
separate these out because it just makes
it cleaner and you don't have one agent
that's trying to write code that's
overlapping with the code from another
agent. So the more you can separate
these out, the easier it'll be for you.
And what you want to do is take a prompt
and assign agent one to a specific area.
So if you're setting up a settings area,
you have one builderbot, so A1 here, and
their job is to build whatever your
prompt says. And then it's going to
build that. And then your second little
buddy helper agent is going to come back
and check the code of that agent. So
[snorts] what you're going to do is
you're going to fire off the prompt, get
that that agent to start coding, and
then you're going to move on to your
second agent. This is in a separate part
of the app. If this was working on
settings, say this one's working on the
onboarding flow, and you're going to
have your second app start working on
the onboarding flow, and then have your
second buddy helper start uh reviewing
the code for this. So it looks like
this. You trigger this one, it starts
working. You come and you give this one
a prompt and it starts working. You come
and give this one a prompt and it starts
working. You go all the way around the
loop. And by the time you're done with
the last loop, this first agent is
completed. Since you've been monitoring
it the whole time, you've had the code
checked. And you go through an entire
loop like this where they all get to
finish their respective builds. And in
between each one of those, you have an
alignment agent. Look at the code and
see if the code from any of those
individual agents are going to screw
anything up when all of that code comes
together. You can do this in more than
one app, too. So, if you're building
several apps at a time, like many of us
are, you can set up your different apps
to where you're building one app with
two or three agents, the second app with
two or three agents, the third app with
two or three agents, and you build out
three loops like this. So, you're
building three apps at a time. you'll
need your caffeine and there's a lot of
context switching. But with the agents
doing most of the work, it kind of frees
you up to think about the larger system
type things and how you're prompting and
how your app actually serves the people
and what problems it solves because
you're just having these agents go
around and build things in loops. The
second thing you talked about is how he
does pull request. So he's working on
this application and there's a lot of
people putting in different pull
requests which if you don't know what
that is, it's just there's different
people or it could be different agents
working on an application and they all
have different pieces of code and at
some point in time all that code needs
to come back into the main codebase. And
to do that they open up these things
called pull requests which is pretty
much just saying hey I've got this piece
of code can we add it to the app? Now,
the way this has always been done in the
past is you open up a pull request and
you go through and you review things
line by line and then if it passes, you
stack that on top of your app and then
you add it to your app. Peter says he's
getting away from this model and he
really talks a lot about something
called weaving your app or sculpting
your app. And let me talk tell you a
little about this because I think it's a
great idea. He doesn't care about pull
requests that much anymore. What he's
really saying is he cares about how a
agent or a person arrived at the
conclusion. So the way I took what he
said was he sees a pull request almost
as like a suggestion. Here's a way you
could build the app. And he will take
those pull requests and what he actually
wants to see is not just the code that
somebody is submitting, but he wants to
see the prompt that generated that code
and how they arrived at their
conclusion. Then what he will do is
actually look at the code with an agent
and then kind of like cherrypick bits
and pieces of that code and have a
discussion about how that code might
influence the main branch and then bring
in different parts of the code or maybe
even rewrite it completely and take that
as a suggestion and say okay now I'm
going to build this out in main. I think
this is a great idea because I can
envision a time in the future, and I'm
actually going to try to play around
with this a little bit more this weekend
if I have time, is to where instead of
having one pull request, maybe you open
up three or four branches off your main
line, and you have agents build things
with slightly different prompts that are
just kind of loose prompts where you're
not being real explicit about how to
build it. Just get three or four
different agents familiar with your
codebase. You can run the init statement
and make sure you're pointing them to
your cloud.md file. And what you would
do is have them all build something for
the app and then you would look at that
code that they have and instead of
saying, "Okay, I'm going to go through
and check it line by line," you have
another agent that reviews all that
code, considers the consequences of what
it would take to bring it in and then
take only the best parts of that code
and merge it into the main part of your
app as you know the official version of
your application. You can do this
already with tools like Claude. And I
know that cursor has a feature where you
can have multiple versions of an agent's
response, but I plan on using this a lot
more and changing the way I think about
pull requests because if I'm being
honest, I hate doing pull requests. I'm
a vibe coder at heart and if it was up
to me, I would just push everything on
main and vibe code away, even if that's
reckless and irresponsible at times. And
the third thing you talked about was
like sculpting versus waterfall. And I
was really glad that he brought this up
because as somebody who's been building
software for a long time and has been
deep in, you know, waterfall and agile
conversations and building software, the
way we used to build software was we
would write up a huge specification.
Then you would give that to a team of
engineers and they would go implement
it. And if you weren't right, you had
this big long gap between when you
actually built something and when it got
released. And this causes all sorts of
problems because if you're wrong, well,
you've already spent tens of thousands,
if not hundreds of thousands of dollars
building some feature that's terrible.
The reason I'm glad he mentioned this is
because today I see a lot of people
talking about specs and building up big
elaborate specs. And it to me almost
feels like the waterfall method is being
brought back into AI development, which
is the last thing we actually want. I
know what I'm trying to do with my app
right now is get completely away from
building specs. And in the build
anything app, I'm making it weird.
You're just pretty much describing the
spirit of a problem. And I know that
sounds weird, but you're describing an
app and you're just describing a
problemcape. And that's the information
that you're actually giving to the AI
agents and then you're working with them
to come up with solutions. This is way
more agile than even agile was. And you
get a lot more opinions. So instead of
saying this is the answer to a problem,
you're giving a bunch of context to all
these agents in the build anything app
and what's actually happening is is
they're responding back to you in
different ways, multiple ways you could
solve a single problem instead of saying
here's the problem. Here's how you're
going to solve it. Go build it. So this
gives you way more degrees of freedom as
a builder. Instead of thinking you're so
smart that you can come up with like the
best answer, you you do the opposite of
that and you say, "I'm not really sure.
Let me try out four or five different
answers." With as powerful as these
coding agents are becoming, that's the
way you can go. It doesn't matter if the
code is perfect at first. You get to
look at fully built out solutions from
four to five like senior developer,
junior developer type of agents. It
sounds like Peter has been through some
of the same type of uh waterfall
methodology in the past and definitely
feels that pain and I was really glad to
see that a engineering leader like him
is bringing stuff like this to the
forefront because a lot of people are
getting into coding now that have not
been building applications for the past
10 year and have not done that with a
corporation. So you'll get these people
that are doing great with vibe coding.
you know, even if it's not the best code
ever, they're getting into coding, which
is what we all want. But then you'll see
all these people that are saying, "We'll
build these huge specs and specify
everything, then just give this to the
agent." And I think that's the wrong way
to build software, and that will not be
the way that we're doing it most
effectively in the future. But that's
all for today. Make sure you go over and
watch the full podcast at the Pragmatic
Engineer channel. It was great. It
influenced the way I'm building out the
Build Anything app. And if you want to
test out the build anything app or get
on the beta test list, go to
ericbefor.com and you also get the
conductor framework there for free when
you sign up. You can use that in any
codebase you want. But that's all for
today. Thank you for watching.
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall