Jane Street — the quantitative trading firm known for OCaml-heavy engineering — published agent_skills on GitHub in early November 2026. The repo crossed roughly 2,100 stars within days, per the repository README and GitHub counter on November 10.
It is not a model release. It is a reference implementation of the same Agent Skills folder pattern AWS Quick adopted in its November skills guide and Anthropic popularized for Claude agents. The first skill, socratic-tutor, turns a host model into a strict personal tutor that teaches through questions, diagnostics, and leveled mastery checks.
TL;DR #
| Question | Answer |
|---|---|
| License? | MIT per LICENSE.md in the repo |
| Skills shipped? | socratic-tutor today; README invites more |
| Format? | Directory with root SKILL.md plus optional assets |
| Install? | Copy folder into agent skills path or paste SKILL body |
| Trigger phrases? | teach me ,tutor me ,quiz me ,help me master |
| Star velocity? | 2.1k+ stars sinceNovember 3, 2026 creation |
Why a trading firm shipped a tutor skill #
Jane Street's public engineering brand centers on disciplined learning — interns famously work through Socratic problem sets. Publishing a SKILL.md that encodes that pedagogy for external agents extends the same idea to any model host that reads the Agent Skills spec.
For explainx.ai readers, the interesting part is structure, not mystique about Jane Street's internal stack. The skill is portable text you can audit, diff in git, and reuse in Claude Code skills folders, Quick, or custom harnesses like Executor 2's MCP gateway.
Repository layout #
The GitHub tree on November 10 listed:
socratic-tutor/SKILL.md— primary instructionsCONTRIBUTING.md,LICENSE.md,.ocamlformat,.gitignore
README copy: "Agent skills from Jane Street" — "A collection of skills for AI agents and chatbots. Each skill is a directory containing a SKILL.md file with instructions for the agent."
No Python package, no npm install — intentionally host-agnostic.
Inside socratic-tutor/SKILL.md #
The published SKILL.md opens with YAML metadata:
name: "socratic-tutor"
description: "Structured Socratic tutoring when the user explicitly asks to be taught, quizzed, or drilled to mastery on a topic..."
Guard: do not hijack casual questions
The skill mandates a guard before the teaching loop. If the user only asks "what is X" or "explain X", answer normally. If intent is ambiguous, ask one confirmation: quick answer versus full tutoring. That prevents accidental quiz mode — a common failure when skills descriptions are too broad.
Session flow
- Decompose the topic into4–10 subskills (fewer for narrow subjects).
- Run a 3–5 question diagnostic spanning easy to hardbefore teaching .
- Render an ASCII skill map with levels0–5 per subskill and an overall percentage bar.
- Enter the teaching loop :one question per message , wait, no trailing hints.
Levels are defined plainly: 0 unaware through 5 can teach it / handle edge cases.
Strict evaluation rules
Jane Street's copy is unusually explicit about anti-sycophancy:
- No level bumps withouttwo independent checks , oneunprompted recall .
- Vague answers count as wrong — probe until understanding is demonstrated.
- Spaced review canlower levels if the user forgets earlier material.
- Level 5 requires an edge-case or adversarial questionand teach-back quality.
- Do not flatter — prefer**"Not quite — why would X happen if Y were true?"**
User commands
The skill documents escape hatches:
show progress— redraw the mapharder/easierjust tell me— one-question lecture overridesave state/resume from:— portable session blobs
That last pair is valuable for long-running mastery paths across sessions — a pattern more skills should copy for education use cases.
How to try it today #
With a SKILL.md-capable agent (Claude Code, Cursor agents, other spec hosts):
- Clone
https://github.com/janestreet/agent_skills. - Copy
socratic-tutor/into your host's skills directory per that product's docs. - Prompt: "Use socratic-tutor — teach me how KV cache eviction works."
With a plain chatbot:
- Paste the body of
SKILL.mdafter the frontmatter into a custom instruction field. - Start with an explicit trigger: "Tutor me on backpropagation."
Compare results with AWS Quick's approach to progressive disclosure in skills publishing: Jane Street loads everything when triggered; Quick loads metadata first. Host behavior still matters.
How this compares to other team skills repos #
| Repo / product | What it ships | Jane Street difference |
|---|---|---|
| Tencent TeamAI-CLI | Git-synced team skills for CLI agents | Jane Street ships pedagogy , not CI sync |
| AWS Quick catalog | Hundreds of business templates | Jane Street is minimal ,MIT ,auditable |
| Stack Diagram agent skill | Visual architecture diagrams | Different task domain |
Star velocity and maintenance signals #
The candidate feed logged 2,124 stars with repo created November 3, 2026 — fast uptake for a single-skill repo. Commit history showed two commits on November 10 fetch — early but not abandoned.
Watch for:
- Additional skills directories beyond
socratic-tutor - CONTRIBUTING.md norms for external PRs
- Whether Jane Street pins model-specific addenda
Treat star count as interest in agent skills as a format, not proof the pedagogy beats human tutors.
Skill map example (what the agent should render) #
Jane Street specifies an ASCII template the host should print after diagnostics. The pattern looks like this in SKILL.md:
Topic: overall: ######.... 58%
-----------------------------------------------------------------
subskill A [########..] 4/5 * independent
subskill B [######....] 3/5 <- current focus
subskill C [##........] 1/5
-----------------------------------------------------------------
The file asks for solid block U+2588 and light block U+2591 characters when the environment supports them. That visual discipline matters for long-running tutoring sessions where users lose track of progress. It also makes save state blocks easier to parse when pasted into a new chat.
Teaching loop rules in plain language
After the map appears, the agent should:
- Ask one question, thenstop the message — no trailing hints, no example answers in the same turn.
- Prefer questions that force prediction ,error finding , ortransfer to a new case.
- On wrong answers, narrow the question twice before explaining.
- On right answers, occasionally devil's advocate to test robustness.
- Run spaced review on earlier subskills without announcing it.
The skill explicitly forbids attributing insights the user did not state. That line fights hallucinated progress reports, a common failure mode when models want to be encouraging.
Final assessment gate
Completion requires every subskill at the target level (default 4/5, or 5/5 if the user asked for full mastery). Then the agent runs a mixed assessment with at least one question per subskill plus one integrative problem. Failures send the user back into the loop rather than issuing a participation trophy.
Porting socratic-tutor to your agent harness #
| Step | Action | Pitfall |
|---|---|---|
| 1 | Copy socratic-tutor/ verbatim into your skills root |
Renaming name: in frontmatter breaks triggers |
| 2 | Ensure host loads description for routing | Broad descriptions cause false positives — this skill already narrows triggers |
| 3 | Disable parallel tool calls during tutoring | Extra tools interrupt the one-question-per-turn contract |
| 4 | Cap max output tokens per turn | Long lectures violate the format even if the model "helps" |
| 5 | Log level changes externally if you grade employees | SKILL.md does not persist state unless user runs save state |
If you maintain skills in git, add a CI check that SKILL.md frontmatter name matches the directory name — the same lint AWS Quick recommends for production skills in its November guide.
Jane Street and the wider skills arms race #
November 2026 is crowded with skills-shaped releases:
- AWS Quick productizedpublish/share for business users.
- Jane Street open-sourcedpedagogy .
- Trending repos such as Stack Diagram targetdiagram generation .
Jane Street's contribution is normative text: it tells the model how not to teach. That is harder to copy than a script because it depends on turn-by-turn discipline from the host runtime.
For education startups, the skill is a free baseline to compare against proprietary tutors. Run A/B tests: default system prompt versus socratic-tutor on the same calculus or ML syllabus and measure human-rated mastery, not token count alone.
OCaml culture and .ocamlformat in the repo #
The repository root includes .ocamlformat, a wink at Jane Street's OCaml ecosystem, even though the skill itself is Markdown. Contributors editing future skills should keep CONTRIBUTE.md norms in mind if the firm accepts external skills — today the repo is tiny, but the file signals reviewed contributions rather than drive-by prompts.
Limitations and risks #
- Token burn : Socratic loops are long; pair withoutput-token awareness when using reasoning models.
- No sandbox : The skill assumes the host enforces tool policies; it does not ship execution sandboxing — irrelevant for pure Q&A tutoring but critical if you add code-exec exercises.
- Not financial advice : Jane Street's brand does not make this a trading signal.
When not to use this skill #
Skip socratic-tutor for:
- Incident response oron-call pages where the user needs an answer in one shot.
- Compliance answers that must quote regulation verbatim — use retrieval with citations instead.
- Creative brainstorming where leading questions constrain ideation.
- Children's homework without oversight — the skill is strict, not a substitute for teacher supervision.
For security training, pair tutoring with factual runbooks and restrict tool access in the host so a student agent cannot exfiltrate data while "learning."
Related reading #
Jane Street agent skills library card pulled from shelf illustrating SKILL.md collections
Star counts and commit totals are accurate as of November 10, 2026 per GitHub.