Who it is forA student or parent helping a child choose a science fair or class project topic with time to explore.
The problemA list of standard project ideas makes the choice a grading exercise instead of a curiosity exercise.
The outcomeA mind map with seeds, tendrils, and gut-check lines that suggest which angles hold real curiosity.
What you need first
- Access to Claude with skills support
- Either the wonder-pill.skill file from the Releases page or a local copy of the Wonder-Pill repository
- A topic you want to explore, plus any constraints such as budget, deadline, or materials
Steps
- Download wonder-pill.skill from the Releases page and click Save skill in Claude.
- Type /wonderpill followed by the topic, for example /wonderpill fungi.
- Tell the intake questions you want pure wondering with no deadline and no build requirement.
- Click nodes on the mind map to read each gut-check line aloud.
- Pick one branch and ask the skill to run again on that branch alone.
Prompt for your agent
Using the Wonder Pill skill from ara-mkr/Wonder-Pill, run /wonderpill on <topic> with a loose leash and no deadline. Return the written wonderings for the most grounded branch. Verify that the output includes at least one gut-check line and does not pick a winner.
Caveat. The README warns that a deadline or a request to pick one will push the skill toward concrete output it is not designed to give, so keep the request open.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page