cluster · claude-skill-development2026·iv·23006← All Skills
Ch. ·

Claude Skill Workshop

6 open-source Claude Skills, with the design patterns behind them

A working corpus of Claude / Agent Skills for real workflows: deliberation (agora), card generation (any2card), learning paths (interactive-learning), README + infographics (readme-generator), travel guidebook PDF (travel-guidebook), immersive narrative (theatre).

Tools in this cluster

agora

Multi-perspective deliberation system — 6 rooms, 31 thinkers, structured debate for any life domain

$ npx skills add https://github.com/geekjourneyx/agora

any2card

Convert any text, article, or thread into shareable HTML info cards with 4 theme families

$ npx skills add https://github.com/geekjourneyx/any2card

interactive-learning

Turn any content into a verifiable learning path — concept extraction, diagnostic, Socratic verification loop

$ npx skills add https://github.com/geekjourneyx/interactive-learning

readme-generator

Generate professional README.md with 16:9 infographics, SEO-optimized metadata, and structured author sections — powered by Playwright and AI agent skills

$ npx skills add https://github.com/geekjourneyx/readme-generator

theatre

Immersive historical narrative experience Skill — driven by a Witness Engine, supports multi-script extension. You are not an observer, you are a witness — present at different depths, hearing different histories

$ npx skills add https://github.com/geekjourneyx/theatre

travel-guidebook

AI agent skill that generates beautifully typeset travel guidebook PDFs — from research to print, powered by parallel agents and Amap MCP

$ npx skills add https://github.com/geekjourneyx/travel-guidebook

Frequently Asked Questions

What are the 6 deliberation rooms in Agora?
Each room focuses on a life domain: career, relationships, finance, health, creativity, and life philosophy — each populated with curated historical and contemporary thinkers.
How is Agora different from just asking Claude a question?
Agora structures the response as a formal deliberation — multiple named thinkers argue from their distinct worldviews, creating genuine tension and revealing blind spots a single perspective misses.
How do I install it?
Run: npx skills add https://github.com/geekjourneyx/agora
What output format does any2card produce?
It outputs self-contained HTML files — single cards or multi-card decks — ready to screenshot, embed, or share directly.
What are the 4 theme families?
The themes cover editorial, minimal, dark, and illustrated styles — each with multiple variants for different tone and platform needs.
How do I install it?
Run: npx skills add https://github.com/geekjourneyx/any2card
What is the Socratic verification loop?
After teaching a concept, the skill asks probing questions rather than presenting answers — it waits for your response, identifies gaps, and re-teaches only what you missed.
How is this different from asking Claude to explain a topic?
A plain explanation is passive. interactive-learning forces active recall with diagnostics and won't let you advance until key concepts are verified — it behaves more like a tutor than a reference.
How do I install it?
Run: npx skills add https://github.com/geekjourneyx/interactive-learning
What does readme-generator do?
It generates a complete README.md with 16:9 infographics and SEO-optimized metadata, using Playwright to render visuals and Claude Skills to write content.
How do I install it?
Run: npx skills add https://github.com/geekjourneyx/readme-generator
Does it work without Playwright installed?
No. Infographic rendering depends on Playwright. The skill checks at runtime and prompts installation.
What is the Witness Engine?
A narrative state machine that places the user as a witness inside a historical scene — your depth of presence (observer / participant / decision-maker) changes what you hear and see.
Can I add my own scripts?
Yes. The skill is designed for multi-script extension — drop a script file into the scripts/ directory and it shows up.
Is this a game?
No. It is an immersive narrative experience — closer to interactive non-fiction than to gameplay.
What is the parallel agents pattern in travel-guidebook?
Multiple sub-agents research different aspects of a destination simultaneously — attractions, food, transit, lodging — then a layout agent merges results into a single PDF.
Why does it need Amap MCP?
For accurate Chinese location data, transit routes, and POI details that English-only APIs lack.
What format is the output?
A typeset PDF with cover, table of contents, day-by-day itinerary, and printable page breaks.