deep-question

Other Community

Repo stars 24,518
Author repo DeepTutor

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Generate quiz questions with answers on any topic. Use the exec tool to invoke DeepTutor's quiz generation pipeline (ideation →…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “When to Use”, “Command”, “Options”, “Examples”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name deep-question directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “When to Use / Command / Options” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Deep Question (Quiz Generation)

Use the exec tool to invoke DeepTutor's quiz generation pipeline (ideation → evaluation → generation → validation).

When to Use

User wants practice questions or quizzes on a topic
User is preparing for an exam or self-testing
User asks to "generate questions", "quiz me", "create practice problems"

Command

deeptutor run deep_question "<topic>" --format json -l <lang> [options]

Options

Flag	Description
`-l <lang>`	Response language: `en` or `zh`
`--config num_questions=N`	Number of questions (default: 1, max: 50)
`--config difficulty=<level>`	`easy`, `medium`, `hard`
`--config question_type=<type>`	`multiple_choice`, `open_ended`, `true_false`, etc.
`--config mode=<mode>`	`custom` (default) or `mimic`
`-t rag`	Ground questions in a knowledge base
`--kb <name>`	Knowledge base to use

Examples

Basic quiz:

deeptutor run deep_question "Calculus integration techniques" --format json -l en --config num_questions=5 --config difficulty=medium

Multiple-choice from a textbook:

deeptutor run deep_question "Chapter 3: Linear Algebra" --format json -l zh -t rag --kb math-textbook --config question_type=multiple_choice --config num_questions=10

Hard open-ended questions:

deeptutor run deep_question "Quantum mechanics fundamentals" --format json -l en --config difficulty=hard --config question_type=open_ended

Important

This capability can take over a minute for multiple questions — use timeout=300 with the exec tool.
Parse NDJSON events with "type": "content" for the generated questions and answers.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Other
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @HKUDS · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview deep-question.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Deep Question (Quiz Generation)

Use the `exec` tool to invoke DeepTutor's quiz generation pipeline (ideation → evaluation → generation → validation).

## When to Use

- User wants **practice questions** or **quizzes** on a topic
- User is preparing for an exam or self-testing
- User asks to "generate questions", "quiz me", "create practice problems"

## Command

```bash
deeptutor run deep_question "<topic>" --format json -l <lang> [options]
```

### Options

| Flag | Description |
|------|-------------|
| `-l <lang>` | Response language: `en` or `zh` |
| `--config num_questions=N` | Number of questions (default: 1, max: 50) |
| `--config difficulty=<level>` | `easy`, `medium`, `hard` |
| `--config question_type=<type>` | `multiple_choice`, `open_ended`, `true_false`, etc. |
| `--config mode=<mode>` | `custom` (default) or `mimic` |
| `-t rag` | Ground questions in a knowledge base |
| `--kb <name>` | Knowledge base to use |

## Examples

Basic quiz:
```bash
deeptutor run deep_question "Calculus integration techniques" --format json -l en --config num_questions=5 --config difficulty=medium
```

Multiple-choice from a textbook:
```bash
deeptutor run deep_question "Chapter 3: Linear Algebra" --format json -l zh -t rag --kb math-textbook --config question_type=multiple_choice --config num_questions=10
```

Hard open-ended questions:
```bash
deeptutor run deep_question "Quantum mechanics fundamentals" --format json -l en --config difficulty=hard --config question_type=open_ended
```

## Important

- This capability can take **over a minute** for multiple questions — use `timeout=300` with the `exec` tool.
- Parse NDJSON events with `"type": "content"` for the generated questions and answers.

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> When to Use → Command → Options → Examples → Important
terms    -> practice questions · quizzes · over a minute · Use the exec tool to invoke DeepTutor's quiz generation pipeline (ideation → evaluation → generation → validation). · - This capability can take over a minute for multiple questions — use timeout=300 with the exec tool.
files/cmd -> exec · -l <lang> · --config numquestions=N · --config difficulty=<level> · easy · medium · hard · --config questiontype=<type>
body sha256 -> 0697b7697b30