Jane Street's socratic-tutor agent skill teaches by asking questions, not lecturing
intellectronica · x · 2026-11-09
A skill called socratic-tutor from the janestreet/agentskills repo is getting attention as a fun and useful way to learn with an AI agent.
Key design points:
- Uses the Socratic method: teaches primarily by asking questions that force the user to reason, predict, and explain rather than lecture
- Includes a guard against false starts: one-off questions get normal answers, and ambiguous intent triggers a quick confirmation ("quick answer, or actually learn it?") before launching the tutoring loop
- Install via npx skills add https://github.com/janestreet/agentskills --skill socratic-tutor
Distributed through skills.sh, it has 19 installs in its first day, 80 GitHub stars, and passed Socket and Snyk security audits.
More from coding & agent
- Day 309/365 of GPU Programming: Optimizing LLaMA2-7B on Edge with SIMD and Multithreading — NandoDF · 2026-11-09
- Berkeley-led paper: evolved agents gain 5.2 reliability points while losing 10 tasks they once solved — rohanpaul_ai · 2026-11-09
- Running a Home Mac mini as an Always-On Node for Remote AI Tasks — xiaohu · 2026-11-09
- Capwise repo goes public: native macOS screen recording and AI editing workbench — vista8 · 2026-11-09
- Capwise open-sources beta of AI screen recorder with bilingual captions and Agent CLI — vista8 · 2026-11-09
- Agent PRs merge at just 32.7% vs 84.4% for humans, with 91% more review time — gerardsans · 2026-11-09