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

Paidagogos

ASecurity

Use when the user wants to learn something, be taught a topic, understand a concept, or explore something visually or interactively. Triggers on: "teach me X", "explain X", "how does X work", "I want to learn X", "I don't understand X", "walk me through X", "show me X visually", "animate X", "plot X with sliders". Also triggers when the user names something they're confused about without using the word "learn" — e.g. "I keep mixing up SQL joins" or "I want to understand git rebase". Routes to...

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentspythongosqlreactgit

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add neotherapper/claude-plugins --skill paidagogos --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Paidagogos?

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

Security grade badge for Paidagogos
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/neotherapper-paidagogos/badge)](https://www.skillsdirectory.com/skills/neotherapper-paidagogos)

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: paidagogos
description: >
  Use when the user wants to learn something, be taught a topic, understand a
  concept, or explore something visually or interactively. Triggers on: "teach
  me X", "explain X", "how does X work", "I want to learn X", "I don't
  understand X", "walk me through X", "show me X visually", "animate X", "plot
  X with sliders". Also triggers when the user names something they're confused
  about without using the word "learn" — e.g. "I keep mixing up SQL joins" or
  "I want to understand git rebase". Routes to paidagogos:micro for focused
  concepts. Handles server start ("/paidagogos serve") and future features
  (quiz, progress, curriculum). Use this skill for any learning intent even
  when the request is indirect.
license: MIT
metadata:
  version: "0.2.0"
  author: Georgios Pilitsoglou
---

# paidagogos — Router

Entry point for the `paidagogos` plugin. Classify the user's learning intent and scope, then route to the right sub-skill. Always state which sub-skill is being routed to — never silently reroute.

## Routing table

| User input | Action |
|---|---|
| "teach me [concept]" | Scope check → route to `paidagogos:micro` |
| "explain [thing]" | Scope check → route to `paidagogos:micro` |
| "how does [thing] work" | Scope check → route to `paidagogos:micro` |
| "what is [thing]" (learning context) | Scope check → route to `paidagogos:micro` |
| "I don't understand [thing]" | Scope check → route to `paidagogos:micro` |
| "walk me through [thing]" | Scope check → route to `paidagogos:micro` |
| "show me [thing] visually / with sliders / animated" | Scope check → route to `paidagogos:micro` (interactive mode) |
| "/paidagogos [topic]" (bare invocation) | Scope check → route to `paidagogos:micro` |
| "/paidagogos serve" or "start the server" | Start visual-kit: run `visual-kit serve --project-dir .` in background (`run_in_background: true`), poll `.visual-kit/server/state/server-info` until `status` is `"running"`, report the URL. Do NOT ask the user to run it. |
| "quiz me on [thing]" | Respond: "`paidagogos:quiz` is coming in a later release. Use `/paidagogos [topic]` to get a lesson with a built-in quiz." |
| "what have I learned" / "show progress" | Respond: "Progress tracking is not modelled yet — curricula are content-only by design. Ask for the path to see the concept tree." |
| "continue my lesson on X" | Respond: "Session recall is coming in a later release." |
| "I want to become [role]" / "roadmap for X" | Route to `paidagogos:path` |
| "show me the curriculum" / "learning path for X" | Route to `paidagogos:path` |
| "what should I learn next" | Route to `paidagogos:path` |
| "/paidagogos:path" | Route to `paidagogos:path` |
| "what curricula do you have" / "show me all roadmaps" | `paidagogos:path` (index) |
| "/paidagogos:path" with no topic | `paidagogos:path` (index) |

## Scope classifier

Before routing to `paidagogos:micro`, decide if the topic is a single concept or a broad area.

**Single concept → route directly:**
Maps to ≤3 distinct sub-concepts. Examples: "CSS flexbox", "async/await", "the event loop", "SQL JOINs", "Python list comprehensions", "derivatives", "(a+b)²".

**Broad topic → ask first:**
Maps to >3 sub-concepts or is a whole technology/field. Examples: "React", "machine learning", "system design", "calculus", "Python".

When the topic is broad, respond:

```
**[Topic]** is a broad area with many concepts. What would you like to do?

1. **One focused lesson** — pick one concept to learn right now (I'll suggest a good starting point)
2. **Full learning path** — the concept tree, rendered in the browser

Which would you prefer?
```

If the user picks option 1: suggest the best entry concept and invoke `paidagogos:micro`.
If the user picks option 2: invoke `paidagogos:path`.

When a curriculum already exists for the broad topic (see the index produced by
`paidagogos:path`), skip the question and route straight to `paidagogos:path` —
asking is only worthwhile when no path exists yet.

When genuinely uncertain, default to the broad topic flow and ask.

## Debug mode

If `PAIDAGOGOS_DEBUG=1` is set, print before routing:

```
[paidagogos:router] intent=micro topic="{topic}" level={level} scope={single|broad}
```

## Out of scope

Lesson generation, visual rendering, progress storage, and curriculum planning are all delegated — this skill only classifies and routes. (End of file - total 74 lines)

Attribution

neotherapperneotherapper
View sourceSee grades on GitHubMore from neotherapper →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

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 Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 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', ...

697551 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 →