#drCatHicks
LightNews LightNews
robw.bsky.social
Uuugh; AI is not better informed than your doctor

It can help you find & organize expertise & research *from other doctors & specialists*; see e.g. github.com/DrCatHicks/i...

But you're right, also, that by default a lot of AI tools can use your data in all kinds of ways, need to manage that
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
September 30, 2026 at 11:32 AM
grimalkina.bsky.social
I wanted to give /informed-patient some better guidance for handling medical classification frameworks and helping you reason about them. This is still in experimentation phase so I welcome hearing about whether it works or not

see it at: github.com/DrCatHicks/i...
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
September 24, 2026 at 9:19 PM
hatchman76.bsky.social
Everyone using AI in their jobs needs to add this skill. Now. github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
September 18, 2026 at 11:15 PM
chaosgreml.in
I’m not using those features. I’m using a skill built by an actual learning scientist.

github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
September 8, 2026 at 5:22 AM
ashleyjuavinett.bsky.social
Has anyone here used @grimalkina.bsky.social’s informed patient skill?

It is, quite possibly, the coolest thing she’s ever built and *legitimately* very useful.

This could really be a game changer for grappling with rare diseases or complex intersections.

github.com/DrCatHicks/i...
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
September 7, 2026 at 3:12 PM
grimalkina.bsky.social
And mine: github.com/DrCatHicks/i...
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
September 4, 2026 at 4:30 PM
markposts.bsky.social
Fiiiiinally got around to using @grimalkina.bsky.social 's learning opportunities plugin for Claude Code on a project and it's really good

github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
August 27, 2026 at 7:46 PM
alilleybrinker.com
If you're concerned about the loss of your own expertise, you can and should engage in known learning practices like self-tests, review, and communication with others to make sure you know what it's important you know.

@grimalkina.bsky.social's Learning Opportunities skill is excellent for this FYI
August 24, 2026 at 7:52 PM
cdemwell.bsky.social
Some people are doing really good stuff with this. eg: have you seen @grimalkina.bsky.social 's informed-patient skill? It's "just a skill" but it does a pretty good job, even on free models and agents (eg: opencode) github.com/DrCatHicks/i...
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
August 23, 2026 at 4:24 AM
brokentoys.social
this has been very helpful. it does solid research and explains how and why it comes to the conclusions it does.

github.com/DrCatHicks/i...
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
August 20, 2026 at 5:25 PM
thisismissem.social
github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
August 20, 2026 at 12:04 AM
mvij.org
Claude Code skill for debugging your health github.com/DrCatHicks/informed…
• A structured symptom inventory (frequency, severity, functional impact, timeline) • A literature search with transparent search terms • A verification note so you can check the sources yourself • An Evidence Snapshot with 1-3 bullets on how well-studied a condition is, the strongest relevant finding(s), and clinical challenges • Competing scenarios or hypotheses for your symptom picture, with evidence for and against each • Epistemic red flags relevant to your situation (e.g., understudied condition, long time-to-diagnosis, self-report as primary evidence) • A prioritized question list for your appointment, ranked by you
August 18, 2026 at 2:35 AM
circlejtp.me
Her informed-patient skill (github.com/DrCatHicks/i...) has been invaluable. Helping me bring together all the information. Highlight missed patterns. Think through "what do I want/need out of this appointment".

2/X
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
August 16, 2026 at 6:03 PM
circlejtp.me
I am forever indebted to @grimalkina.bsky.social. I'm someone pretty knowledgeable about healthcare and its associated systems. Yet, this last month has strained every bit of knowledge I have especially with brain fog and the general stress/pain/discomfort of being the patient.

1/X
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
August 16, 2026 at 6:03 PM
erispoe.bsky.social
Now for general questions I use a skill I derived from @grimalkina.bsky.social informed-patient skill, driving it to find, evaluate and actually cite sources. It’s amazing I basically removed the medical framing.

Takes a lot more time but I can trust the answers.

github.com/DrCatHicks/i...
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
August 10, 2026 at 4:05 PM
jeffgreene.bsky.social
github.com/DrCatHicks/l... Should probably tag @grimalkina.bsky.social given we are talking about her skill. :)
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
August 9, 2026 at 4:03 PM
chaosgreml.in
We know that LLMs can be used to teach concepts (see the great work done by @grimalkina.bsky.social with GitHub.com/drcathicks/learning-opportunities), but let’s discuss “beautiful, readable” code (lots of opinions here!):
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
GitHub.com
August 8, 2026 at 7:04 PM
grimalkina.bsky.social
You might enjoy some of the refs in a few places I talk about metacognition if you haven't read this area

www.fightforthehuman.com/cognitive-he...

www.fightforthehuman.com/cognitive-he...

github.com/DrCatHicks/t...
Cognitive Helmets for the AI Bicycle: Part 1
I hear people name these three fears: will developers lose their problem-solving skills, learning opportunities, and critical thinking? One science-backed area can help: better metacognitive strategie...
www.fightforthehuman.com
July 29, 2026 at 2:55 PM
bmann.ca
I have pi downloaded but I also have never really gotten into customizing my shell configuration.

I might use some of @grimalkina.bsky.social’s learning skills to understand pi github.com/DrCatHicks/l...

There really is a lot going on
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
July 26, 2026 at 3:20 PM
grimalkina.bsky.social
haven't used but I think things like this are directionally neat and in the orient subskill contributed by @mcmullarkey.bsky.social to learning-opportunities we did a quick pass at imagining repo context for comprehension goals!

github.com/DrCatHicks/l...
github.com
July 25, 2026 at 9:07 PM
chaosgreml.in
@grimalkina.bsky.social and the skill is here: github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
July 25, 2026 at 6:44 PM
going to try this now github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
July 25, 2026 at 4:48 PM
natfu.be
Thanks! I think I've arrived to about the same conclusions. It's difficult to stay engaged all the time though so I think we should have our harnesses reinforce that instead of having "discipline", that'd be bad UX/DX anyways. I've tried to use something like "grill-me" github.com/DrCatHicks/l...
GitHub - DrCatHicks/learning-opportunities: A Claude or Codex skill for deliberate skill development during AI-assisted coding
A Claude or Codex skill for deliberate skill development during AI-assisted coding - DrCatHicks/learning-opportunities
github.com
July 23, 2026 at 7:44 PM
fubarchitect.com
yeah, i haven't used it so i can't speak on it but the work is here: github.com/DrCatHicks/i...

i think she likely does well with avoiding dangerous sycophancy for this usecase but it does seem like a tough problem
GitHub - DrCatHicks/informed-patient: A Claude Skill to create an evidence review to inform specific health questions
A Claude Skill to create an evidence review to inform specific health questions - DrCatHicks/informed-patient
github.com
July 20, 2026 at 11:51 AM
grimalkina.bsky.social
I won't show you all the demographic back and forth, but I'll show you just how easy it is to make an AI-administered survey good, even with the stupid AI tone ("honest" lol), you can dramatically improve LLM output with a good harness

Here are inventory instructions:
github.com/DrCatHicks/i...
Two honest boundaries up front, so they don't surprise you later: I won't recommend for or against EV, and I won't weigh in on dose changes — those are the oncology team's call. What I can do well here is help you build a clear picture of what to watch for, how strong the evidence behind the safety profile actually is, and what specific, well-timed questions to bring to their next appointment. We can also do this in pieces — answer what's easy now, and we can pick up the rest later. Here's the inventory. The most important thing to know about EV is that its risk profile is very regimen- and person-specific, so a handful of these answers will genuinely change what I search for and what I tell you to watch. Answer what you can, skip what doesn't apply or you don't know. 1. The regimen and setting — this one matters most. Is this EV on its own, or EV plus pembrolizumab (often written "EV+P")? Pembrolizumab is an immunotherapy that adds a whole separate category of possible reactions, so knowing this reshapes the search. And roughly what setting — advanced/metastatic, or something else you were told? 2. Where they are in the course. When did treatment start, and which cycle are they on now (or how many infusions so far)? Some of the most serious reactions cluster in the early cycles; others (like nerve symptoms) build up cumulatively over time. Timing changes what's most likely right now. 3. Baseline health that maps onto EV's specific known risks. Any of these that apply: Blood sugar — any diabetes, pre-diabetes, or higher body weight? (EV can push blood sugar dangerously high, and this risk is concentrated in certain people.) Nerves — any numbness, tingling, or weakness before starting treatment, from any cause? Skin — any pre-existing skin conditions, or a history of bad drug rashes?
July 19, 2026 at 4:58 PM