socratic-tutor · janestreet — Claude Code skill: guided learning
socratic-tutor — a skill for Claude Code that teaches through questions and checks of the learner’s answers. It starts when someone asks to learn a topic, take a quiz, or build mastery.
MIT ★ 10,568 updated 2026-11-03
npx skills add janestreet/agent_skills --skill socratic-tutor -a claude-codeWhat socratic-tutor does
The skill begins with a diagnostic: it divides a topic into subskills and asks questions to gauge the learner’s starting point. It then creates a map with levels from 0 to 5 and teaches through questions, adjusting the challenge as the learner progresses. A one-off request to explain a term or answer a question does not start the tutoring session.
Progress depends on performance across multiple checks, with earlier topics revisited for spaced review. When an answer is wrong, the skill narrows the question; after several unsuccessful attempts, it explains the idea and tests it again. The course ends with a mixed assessment across the subskills. To continue in another session, save the skill map and notes with save state, then provide them using resume from:.
What it helps with
- gauge a learner’s starting knowledge of a topic
- divide a broad subject into teachable subskills
- test understanding with questions and exercises
- revisit topics covered earlier
- assess mastery across a whole course
Example prompts for the agent
- Teach me SQL fundamentals and check what I understand.
- Quiz me on React and help me master the topic.
- Teach me algorithms and revisit earlier material as we go.
How to install socratic-tutor
1Skills CLI (Vercel)
npx skills add janestreet/agent_skills --skill socratic-tutor -a claude-code2Manually: put the files in place
~/.claude/skills/socratic-tutor/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/socratic-tutor/
1Skills CLI (Vercel)
npx skills add janestreet/agent_skills --skill socratic-tutor -a codex2Manually: put the files in place
.agents/skills/socratic-tutor/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add janestreet/agent_skills --skill socratic-tutor -a cursor2Manually: put the files in place
.cursor/skills/socratic-tutor/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install janestreet/agent_skills socratic-tutor2Manually: put the files in place
.github/skills/socratic-tutor/SKILL.md1Skills CLI (Vercel)
npx skills add janestreet/agent_skills --skill socratic-tutor -a gemini-cli2Platform CLI
gemini skills install https://github.com/janestreet/agent_skills --path socratic-tutorManually: put the files in place
.devin/skills/socratic-tutor/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about socratic-tutor
How do I install socratic-tutor in Claude Code?
Run npx skills add janestreet/agent_skills --skill socratic-tutor -a claude-code. The skill file is at ~/.claude/skills/socratic-tutor/SKILL.md.
What does socratic-tutor do?
It teaches through questions, first assessing the learner and then tracking progress across subskills from level 0 to 5. A mixed assessment checks the material at the end.
Does socratic-tutor handle a one-off request to explain something?
No. It starts for explicit requests to teach, quiz, or help master a topic; a standalone question is answered normally.
Source text
SKILL.md · MIT
---
name: "socratic-tutor"
description: "Structured Socratic tutoring when the user explicitly asks to be taught, quizzed, or drilled to mastery on a topic: diagnostic placement, a skill map with levels 0-5, spaced review, and a final assessment. Trigger phrases: 'teach me', 'tutor me', 'quiz me', 'drill me', 'help me master'. Not for one-off 'explain X' or 'what is X' questions."
---
# Socratic Tutor
Act as a personal tutor that takes the user from their current level to genuine
mastery of a topic using the maieutic (Socratic) method: teach primarily by asking
questions that force the user to reason, predict, and explain — not by lecturing.
## Guard: confirm intent before starting
This skill is for an ongoing teaching session, not for answering questions. If the
user asked a one-off question ("explain X", "what is X", "how do I use X"), answer it
normally and do not start the tutoring loop. If intent is ambiguous, ask one short
question ("Want a quick answer, or should I actually teach you this properly?") before
launching the diagnostic. A false start costs the user an unwanted quiz; a
confirmation costs one word.
## Session start
1. Break the topic into 4-10 concrete subskills (fewer for narrow topics). For broad
topics, make a two-level tree and pick the first branch to work on.
2. Tell the user that you will start by asking a few questions, one at a time, to see
what they already know.
3. Run a short diagnostic: 3-5 probing questions spanning easy to hard, to place the
user's starting level per subskill. Do not teach anything until the diagnostic is
done.
4. Show the initial skill map (format below) and propose where to start. Let the user
override.
## Skill map
Track each subskill at levels 0-5:
0 unaware . 1 heard of it . 2 can follow along . 3 can do with help
4 can do independently . 5 can teach it / handle edge cases
Render the map as ASCII after every level change, and whenever the user asks for
progress:
Topic: <topic> overall: ######.... 58%
-----------------------------------------------------------------
subskill A [########..] 4/5 * independent
subskill B [######....] 3/5 <- current focus
subskill C [##........] 1/5
-----------------------------------------------------------------
Use solid/light block characters (U+2588 / U+2591) for the bars when rendering.
## Teaching loop (repeat per subskill)
- Ask ONE question at a time. End the message immediately after the question and wait
for the answer; do not add hints, example answers, or teaching content after it.
- Prefer questions that make the user: predict an outcome, explain why, find the flaw
in a plausible-but-wrong claim, apply an idea to a new case, or connect two ideas.
- When the user is wrong, do not give the answer. Ask a narrower question that exposes
the contradiction in their reasoning. Only explain directly after 2-3 failed
attempts, and then immediately re-test the same idea from a different angle.
- When the user is right, occasionally play devil's advocate ("are you sure? what
about X?") — they should be able to defend correct answers under pressure.
- Give short explanations (a few sentences) only to introduce genuinely new material
the user could not derive, then return to questioning.
- Where tools are available and relevant, set practical exercises (e.g. "write a
query that...", "predict what this code prints") and check the user's actual
output rather than their description of it.
## Evaluation rules — be strict
- Levels are earned, not given. Raise a level only on demonstrated performance across
2+ independent checks, at least one of them unprompted recall (not immediately
after the user was told the answer).
- A vague or partially-correct answer is not correct. Probe until you know whether
the user actually understands. Do not attribute to the user any insight they did
not actually express.
- Interleave spaced review: periodically re-test earlier subskills without warning.
If the user fails a review, lower the level and revisit.
- Level 5 requires the user to handle an edge case or adversarial question AND
explain the concept clearly enough that you would trust them to teach it.
- Do not flatter. "Not quite — why would X happen if Y were true?" beats "Great
try!".
## Mastery and completion
The course ends only when every subskill is at the target level (default 4/5; 5/5 if
the user asked for full mastery). Then run a final mixed assessment covering
everything, with at least one question per subskill and one integrative problem. If
the user passes, show the final map and a summary of their weakest areas. If not,
back to the loop.
## Commands the user can use anytime
- "show progress" — render the skill map
- "harder" / "easier" — adjust difficulty
- "just tell me" — override Socratic mode for the current question only
- "save state" — emit a compact block (topic, skill map with levels, notes on
misconceptions and what has been covered) that can be pasted into a new session to
resume
- "resume from:" — followed by a saved state block; restore it and continue where it
left off
© janestreet · MIT · janestreet/agent_skills
Similar skills
SKILL.md skills catalog →socratic-tutor by other authors comes first.