# Jane Street Open-Sources agent_skills With a Socratic Tutor SKILL.md

> Source: <https://explainx.ai/blog/janestreet-agent-skills-socratic-tutor-github-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog>
> Published: 2026-11-10 00:00:00+00:00

**Jane Street** — the quantitative trading firm known for OCaml-heavy engineering — published **[agent_skills on GitHub](https://github.com/janestreet/agent_skills?ref=explainx)** in early November 2026. The repo crossed **roughly 2,100 stars** within days, per the [repository README](https://github.com/janestreet/agent_skills?ref=explainx) 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](https://explainx.ai/blog/aws-quick-skills-agents-catalog-build-guide-2026) 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 since**November 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](https://explainx.ai/blog/what-are-agent-skills-complete-guide), Quick, or custom harnesses like [Executor 2's MCP gateway](https://explainx.ai/blog/executor-2-beta-open-source-mcp-gateway-one-catalog-claude-code-cursor-codex-policies-mit-4k-stars-guide-2026).

## Repository layout

The [GitHub tree](https://github.com/janestreet/agent_skills?ref=explainx) on November 10 listed:

- `socratic-tutor/SKILL.md` — primary instructions
- `CONTRIBUTING.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](https://github.com/janestreet/agent_skills/blob/master/socratic-tutor/SKILL.md?ref=explainx) 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

1. **Decompose** the topic into**4–10 subskills** (fewer for narrow subjects).
2. Run a **3–5 question diagnostic** spanning easy to hard**before teaching** .
3. Render an **ASCII skill map** with levels**0–5** per subskill and an overall percentage bar.
4. 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** without**two independent checks** , one**unprompted recall** .
- **Vague answers count as wrong** — probe until understanding is demonstrated.
- **Spaced review** can**lower** levels if the user forgets earlier material.
- **Level 5** requires an edge-case or adversarial question**and** 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 map
- `harder` /`easier`
- `just tell me` — one-question lecture override
- `save 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):

1. Clone `https://github.com/janestreet/agent_skills` .
2. Copy `socratic-tutor/` into your host's skills directory per that product's docs.
3. Prompt: **"Use socratic-tutor — teach me how KV cache eviction works."**

**With a plain chatbot:**

1. Paste the **body** of`SKILL.md` after the frontmatter into a custom instruction field.
2. Start with an explicit trigger: **"Tutor me on backpropagation."**

Compare results with AWS Quick's approach to **progressive disclosure** in [skills publishing](https://explainx.ai/blog/aws-quick-skills-agents-catalog-build-guide-2026): 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](https://explainx.ai/blog/tencent-teamai-cli-git-based-team-skills-2026) | 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](https://explainx.ai/blog/stack-diagram-agent-skill-architecture-diagrams-github-trending-2026) | 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, then**stop the message** — no trailing hints, no example answers in the same turn.
- Prefer questions that force **prediction** ,**error finding** , or**transfer** 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](https://explainx.ai/blog/aws-quick-skills-agents-catalog-build-guide-2026).

## Jane Street and the wider skills arms race

November 2026 is crowded with **skills-shaped** releases:

- **AWS Quick** productized**publish/share** for business users.
- **Jane Street** open-sourced**pedagogy** .
- Trending repos such as [Stack Diagram](https://explainx.ai/blog/stack-diagram-agent-skill-architecture-diagrams-github-trending-2026) target**diagram 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 with[output-token awareness](https://explainx.ai/blog/ai-labs-output-token-inflation-pricing-playcode-2026) 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** or**on-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.*