メニュー
Interactive Socratic teaching assistant that guides learners through discovery-based questioning
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use this when you need a complete interactive report as a single HTML file with zero install dependencies — covers charts, tables, diagrams, math, KPIs, and prose out of the box.
Use this as the default toolset for coding sessions when you want faster navigation, search, file inspection, and git workflow execution with lower command overhead: tools: - fzf - ripgrep - bat - delta - lazygit - starship - zoxide - eza - atuin - yazi
Out-of-band codebase exploration using a cheap/fast model. Keeps your context clean while a cheap model runs 30-80 commands in parallel. Tunable precision and output size - works for broad orientation or precise targeted questions.
Deterministically fixes broken OpenAI Deep Research markdown citations without using an LLM: creates a .bkp backup, rewrites citation markers, rebuilds references, and runs strict regex validation.
Explore a codebase to gather context for coding tasks. Preserves context window and offloads work to cheaper models.
Dynamically generate and execute a specialized agent for any task. Use when the user has an arbitrary task that would benefit from a custom-generated agent.
| name | socratic-teacher |
| description | Interactive Socratic teaching assistant that guides learners through discovery-based questioning |
An interactive teaching skill that uses the Socratic method to guide learners toward deep understanding through carefully crafted probing questions. The machine adapts question difficulty based on learner responses and provides supportive feedback without giving away answers.
./run.sh --topic "Python generators" --level 2 --max-rounds 10
--topic (required): Learning topic to teach--level (optional, default 1): Learner proficiency level (1-5 scale)--max-rounds (optional, default 10): Maximum number of teaching rounds--working-dir (optional, default "."): Directory to save session transcripts--cwd (optional): Alias for --working-dirThe skill outputs a JSON object with:
{
"topic": "Python generators",
"final_mastery_score": 0.82,
"learning_transcript": [...],
"identified_gaps": ["state_preservation", "lazy_evaluation"],
"strengths": ["function_calls", "return_values"],
"termination_reason": "mastery",
"rounds_completed": 6
}
Topic: Python generators, Level: 2
Question: What do you think happens when you call a function with 'yield'?
Hint: Think about what the function returns...
Your response: It returns a value?
Feedback: Good instinct on 'returns'! Can you think about *when* it returns
compared to a regular function?
---
Question: When the yield happens, does the function stop running?
Your response: Yes, it pauses and comes back later?
Feedback: Exactly! It pauses. Now, what happens to the local variables
when it pauses?
---
[... more rounds ...]
Final Mastery: 82%
Identified gaps: state_preservation
Ready to learn: generator.send() method