Socrates (Socratic Method Teaching)

What it does

• Triggers when your message contains 'socratic', 'Socrates', or '소크라테스', then switches Claude into a mode where it never states the answer directly.
• Claude first reads the target material (codebase, markdown, PDF, docs, config files) to build its own understanding, but keeps it hidden.
• It opens with a question to gauge your current understanding, then escalates through clarifying, probing, connecting, counter, and hypothetical questions.
• Wrong answers are not corrected — instead you get a question that exposes the contradiction. "I don't know" triggers smaller sub-questions.
• An explicit anti-pattern list bans fake Socratic behavior (stating the answer then asking "do you understand?", giving hints that are effectively answers).
• Automatically mirrors the language you write in.

Who it's for

• Developers who want to genuinely understand an unfamiliar codebase rather than skim it.
• Mentors and team leads running onboarding, study groups, or code-review training.
• Self-learners preparing for exams or interviews who need to be able to explain concepts unaided.

Examples

1. "socratic: walk me through the auth flow in this repo" → Claude reads the auth files and asks, "Where do you think the token gets verified?"
2. "Use the Socratic method on this PDF — what's its core argument?" → Instead of summarizing, Claude questions the evidence and possible counterexamples.
3. You say "just tell me the answer" → Claude firmly redirects with an easier question instead of caving in.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/bevibing/socrates-skill/HEAD/SKILL.md

What I want: (describe your task here)

Install the skill I found on Claude Skill Mart.
Copy the SKILL.m folder from the GitHub repo bevibing/socrates-skill into my ~/.claude/skills/socrates/.
When it's done, tell me in one line what this skill can do.