iiinova — where your digital self keeps evolving

"Fully Replicable" means all of the expected data is available or that the analysis code replicates? If the former, label as "Complete Data" or "Data Available"?

000

Niall Keleher @nkeleher.com · 08/04/2026

Every game like that moves Kirby one step closer to being a Yankee and it breaks my heart.

000

Niall Keleher @nkeleher.com · 23/03/2026

That's really good! Might be some folks you find here, too. bsky.app/profile/did:...

111

Niall Keleher @nkeleher.com · 23/03/2026

And 🔱⚾Mariners Trending if you're not sure who to follow! bsky.app/profile/did:...

010

Niall Keleher @nkeleher.com · 22/03/2026

Nice! Base on those benchmark graphs maybe the true name is bluecrab?

100

Niall Keleher @nkeleher.com · 20/03/2026

Renee's lists are amazing public service. They helped me create this MLB Trending feed. bsky.app/profile/did:...

010

Niall Keleher @nkeleher.com · 16/03/2026

Swap out Perdomo (or Soto) for Harper 1) ump gets an earful 2) bros call it a ball and statcast is infallible.

011

Niall Keleher @nkeleher.com · 19/02/2026

Indeed. More innovation would be a gift.

010

Niall Keleher @nkeleher.com · 30/01/2026

Same scene at Jackson and 23rd.

000

Niall Keleher @nkeleher.com · 29/01/2026

Though I'm now realizing I added one particular economist that is too popular. Revert commit.

010

Niall Keleher @nkeleher.com · 29/01/2026

I liked the intention of your original Econsky feed. Seems like the emoji and hash tags lead to a lot of content that isn't conducive to conversation. I'm experimenting with an EconSky Trending that draws from list of soc scientists (available for remix on Skyfeed) bsky.app/profile/did:...

130

Niall Keleher @nkeleher.com · 14/01/2026

And Grant gave another good suggestion for starting out bsky.app/profile/gmcd...

120

Niall Keleher @nkeleher.com · 14/01/2026

5. Ask Claude to use that skill using a "slash command" `/{name-of-skill} perform task x on file @{file-name} at line 123.`

100

Niall Keleher @nkeleher.com · 14/01/2026

3. Try instructing Claude to create or edit a file to achieve some task. 4. Add a `.claude/skills/{name-of-skill}/SKILL.md` with instructions that you would want yourself or someone else using the code to be aware of when performing a task (potentially the same as above).

100

Niall Keleher @nkeleher.com · 14/01/2026

So to get back to your question. 1. Start claude from the terminal (or VS Code or Positron or other coding interface) where you already have code written. 2. Run `/init` and claude will create a CLAUDE[dot]md file for you. Read it closely and make sure the file's contents ar accurate.

100

Niall Keleher @nkeleher.com · 14/01/2026

Then if you have Claude Code open in a terminal, you can write something like `/stata write a do file that creates a summary statistics table of variables x,y,z from auto.dta and export the table to a .tex file` or `use the Stata skill to create a graph of all of the vehicle types in auto.dta`

100

Niall Keleher @nkeleher.com · 13/01/2026

Then a skill can also include additional instructions , say in a references/ subfolder of the skill...just more guidance that a human or computer might want to have at their fingertips. I'd say that's the place to start.

100

Niall Keleher @nkeleher.com · 13/01/2026

In this particular case, ti's instructions that I'd want any RA to be familiar with if I asked them to start work on a particular IPA project. They're guidelines that are based on what we train people to know, and they help give Claude a compass and set the guardrails.

100

Niall Keleher @nkeleher.com · 13/01/2026

The way I think about Claude Skills is that they are small sets of instructions that you would like a human (or computer) to understand when approaching a task. Have a look a our Stata skill: github.com/PovertyActio....

github.com

110

Niall Keleher @nkeleher.com · 13/01/2026

Yes! Effectively what I did for IPA's Stata Skill, which draws from IPA, World Bank DIME, @seankhiggins.bsky.social, and Gentzkow & Shapiro guides. github.com/PovertyActio... Has been really beneficial for drafting full Stata end-to-end.

github.com

130

Niall Keleher @nkeleher.com · 13/01/2026

And highly recommend getting comfortable with a little bit of git. It's really helpful to be able to monitor code changes as they accumulate and only committing to a git branch after you've reviewed and tested the code. For a currated set of resources on Git data.poverty-action.org/software/git/

data.poverty-action.org

Git – Research and Data Science Hub

110

Niall Keleher @nkeleher.com · 13/01/2026

Lasse Brune and I are iterating on the content and structure. Key is getting CLAUDE[dot]md set up for use case and common patterns, use Skills, and provide templates/good examples. We're testing with IPA RAs at the moment and looking for more feedback (general principles would be the same for R.

110

Niall Keleher @nkeleher.com · 13/01/2026

My team has been using Claude Code extensively with our python code. We're now rolling out a Stata template that integrates Claude Code for data cleaning and analysis code. github.com/povertyactio...

github.com

GitHub - PovertyAction/ipa-stata-template: Template repository for a Stata analysis project.

Template repository for a Stata analysis project. Contribute to PovertyAction/ipa-stata-template development by creating an account on GitHub.

151

Niall Keleher @nkeleher.com · 10/12/2025

Extremely productive and enlightening collaboration with colleagues from across tech, programs, research, policy, and academia. Thank you @cgdev.org and @agencyfund.bsky.social for convening!

020

Niall Keleher @nkeleher.com · 10/10/2025

The sincerest apologies this was stuck in my drafts and I lost my password written on a postit on my desk rejection.

020

Niall Keleher @nkeleher.com · 25/09/2025

The Mariners are trending! 🔱⚾ bsky.app/profile/did:...

020

Reposted by Niall Keleher

Dean Eckles @eckles.bsky.social · 28/08/2025

I am teaching a PhD seminar this fall which attempts to put a decision-theoretic lens (or lenses) on research design. So e.g., statistical decision theory, eliciting beliefs & preferences, and rational benchmarks. Here's a draft syllabus docs.google.com/document/d/1... What's missing?