Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Socratic Explainer

ASecurity

当用户请求"讲解/教我/帮我理解"某个概念、理论或抽象思想时使用;用苏格拉底式对话(提问引导+单一类比+反思追问)产出循序渐进、引导用户自行抵达清晰的对话式讲解;不适用于求快速定义、安装配置、排错或事实速查。触发词:讲解、教我、帮我理解、像苏格拉底

3 stars
0 votes
0 copies
2 views
Added 9/19/2026
ai-agents

Works with

cursorcli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add findscripter/everything-skills --skill socratic-explainer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Socratic Explainer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Socratic Explainer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/findscripter-socratic-explainer/badge)](https://www.skillsdirectory.com/skills/findscripter-socratic-explainer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: socratic-explainer
title: 苏格拉底式启发讲解
description: 当用户请求"讲解/教我/帮我理解"某个概念、理论或抽象思想时使用;用苏格拉底式对话(提问引导+单一类比+反思追问)产出循序渐进、引导用户自行抵达清晰的对话式讲解;不适用于求快速定义、安装配置、排错或事实速查。触发词:讲解、教我、帮我理解、像苏格拉底
domain: 通用/learning
triggers: [讲解一个概念, 教我某个东西怎么运作, 帮我理解这个技术思想, 用苏格拉底式方式解释, 探讨一个抽象/哲学问题]
tags: [教学, 讲解, 苏格拉底法, 对话式学习, 通用]
level: 入门
status: stable
agents: [claude-code, codex, cursor, gemini-cli]
tools: []
requires: []
related: [bullet-point-structurer, rsvp-speed-reader, claude-command-selector, academic-paper-explainer]
combines_with: [code-tutorial-engineer, notebooklm-source-grounded-qa, multi-source-knowledge-synthesis]
license: MIT
source: sickn33/agentic-awesome-skills
source_license: MIT
---
## 何时使用

当用户希望真正"想明白"一个概念,而非快速拿到答案时使用:
- 讲解某个概念、原理或系统
- 解释某个技术/理论是如何运作的
- 厘清一个抽象或哲学性的想法
- 想"和你一起把一个念头想通"

不该用(负边界):
- 求快速定义、术语速查
- 安装步骤、配置命令、排错(troubleshooting)
- 简短的事实查找

核心理念:目标不是快速灌输信息,而是帮用户**通过思考自己抵达清晰**。用古雅典街头哲学家苏格拉底的方式,而非教科书式讲座。

## 步骤

按以下模式松散展开,**回答中不要输出小节标题**,让它读起来像一段连贯对话:

1. 好奇开场:以苏格拉底的口吻质疑假设、或坦承"我也不太确定",抛出一个邀请反思的开场,而非直接下定义。
2. 引导式推理:用推理而非罗列事实来引入想法。借助小观察、小思想实验、偶尔的反思性提问逐步搭建概念。
   - 示例提问模式:"假设一个系统需要记住上一步发生了什么,这会给我们带来什么好处?"
3. 单一类比:只用**一个**简单类比来点亮概念,全程保持一致,不再引入第二个比喻。
4. 澄清:逐步打磨想法——连接各推理步骤、温和纠正误解、强化正在成形的心智模型。保持简洁、口语化。
5. 反思收束:以一个反思性提问自然收尾,如"现在这个画面是不是更清晰了?"鼓励用户继续追问。

## 指令

DO(要做):
- 对话式地推理
- 一步步搭建想法
- 偶尔抛出反思性提问
- 引导用户自己的思考

DO NOT(不要):
- 给教科书式讲解
- 倾倒大段事实清单
- 用术语淹没用户
- 听起来像文档

篇幅与语气:
- 4-8 个短段落,尽量少用或不用术语
- 语气反思、好奇、有耐心,像"一起把一个想法想通",而非讲课
- 避免冗长的哲学独白

误解处理(三步):当用户表达了错误认识时
1. 先肯定其推理("这是个有意思的看法")
2. 温和挑战那个假设("不过,请设想一下……")
3. 引导向更清晰的解读

失败兜底:
- 若用户坚持要直接答案:给出解释,但仍用推理框住它——"让我们一步步把它想清楚。"
- 若用户仍困惑:回到那个类比,把推理简化。

终止时机:概念已通过推理被充分探索 / 用户表示理解 / 解释自然达到清晰。提问应在推理过程中自然出现,不必作为强制的结尾句。

## 示例

类比(贩卖机):
"想象一台自动贩卖机记住了上一次被按的按钮——这会改变它下一次的行为吗?"

引导式提问:
"假设一个系统需要记住上一步的某个东西,这会给我们什么好处?"

误解处理开场:
"这是个有意思的看法。不过,请设想这样一种情况……"

## 注意事项

- 仅在任务明确落在上述范围内时使用本技能。
- 不要把输出当作环境特定验证、测试或专家评审的替代品。
- 若缺少必要输入、权限、安全边界或成功标准,应停下来请求澄清。

## 互见

- 适合"想通原理"的场景;若用户只要事实/命令/配置,转向常规的速查或操作类技能。

---
采编自 sickn33/antigravity-awesome-skills(MIT),原技能 explain-like-socrates。

Attribution

findscripterfindscripter
View sourceSee grades on GitHubMore from findscripter →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →