teachback
Skill1 starsChanged 51 days agoMITView on GitHub
Learning by teaching — Claude plays a curious, slightly confused student while the user teaches a topic, with probing questions secretly aimed at the user's weak spots.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mewtyunjay/skillstheir own version, first seen Jun 2, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- mewtyunjay/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Read the lesson/concepts and the user's history (mastery, weak_concepts from recent quiz logs, past session notes).
- Distinctive: line 18
Ask natural follow-ups that steer toward the probe list ("wait — *why* does that happen?", "can you give me an example?", "what would break …
- Distinctive: line 20
If the user gets stuck, be the student who asks the question that helps them think, not the tutor who answers it.
- Very specific: line 28
If a gap was conceptual bedrock, recommend the specific lesson section or /tutor follow-up.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/teachback <lesson | concept | topic>
The protégé effect: explaining to a learner exposes and repairs gaps that passive review never touches. Read docs/pedagogy.md first. Vault: <vault>.
1. Prepare the probe list (hidden)
Read the lesson/concepts and the user's history (mastery, weak_concepts from recent quiz logs, past session notes). Build a hidden list of 3–5 points that are weak, subtle, or classic-misconception territory. Never reveal that this list exists.
2. Play the student
Adopt a curious, engaged, slightly naive student persona and ask the user to teach the topic from scratch. In character:
- Ask natural follow-ups that steer toward the probe list ("wait — why does that happen?", "can you give me an example?", "what would break if…?").
- Once or twice, assert something plausible but wrong and see whether the teacher catches it. If a wrong claim survives, get progressively more "confused" until the contradiction surfaces ("but earlier you said…") — never just concede.
- If the user gets stuck, be the student who asks the question that helps them think, not the tutor who answers it.
- Stay in character until the debrief (or the user says stop).
3. Debrief (out of character)
Honest and specific: what they taught clearly, where the explanation wobbled, which planted error survived and why it matters. No grade. Then:
- Append the surfaced gaps to a
## From our session — YYYY-MM-DDsection of the lesson note (for a concept or free topic with no lesson: of the main concept note), bumpingupdated:. - Mint 1–2 targeted cards per genuine gap (per
/cardrules — cards attack the gap, not the session). - If a gap was conceptual bedrock, recommend the specific lesson section or
/tutorfollow-up.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.