Top AI Projects: Mobile‑Controlled Claude Code, Hackathon‑Winner Claude Config, and AI‑Powered Document Illustration

The article introduces four standout AI tooling projects—Happy Coder for mobile Claude Code access, the Everything Claude Code configuration suite from a hackathon champion, the Document Illustrator skill that auto‑generates illustrations, and the free Gemini CLI course—plus the skills.sh marketplace, detailing their features, installation steps, and practical evaluations.

Old Zhang's AI Learning
Old Zhang's AI Learning
Old Zhang's AI Learning
Top AI Projects: Mobile‑Controlled Claude Code, Hackathon‑Winner Claude Config, and AI‑Powered Document Illustration

Happy Coder: Mobile control for Claude Code

Happy Coder is a mobile + web client for Claude Code / Codex that lets developers monitor and control AI‑generated code while away from their computers.

📱 Mobile access : native iOS, Android, and Web apps.

🔔 Push notifications : alerts when the AI needs permission or encounters errors.

⚡ One‑click device switch : seamless hand‑off between phone and computer.

🔐 End‑to‑end encryption : code never leaves the device in plaintext.

🛠️ Fully open source : MIT‑licensed, no telemetry.

Happy Coder project screenshot
Happy Coder project screenshot

Project URL: https://github.com/slopus/happy

npm install -g happy-coder
# Replace claude command
happy

# Replace codex command
happy codex

Everything Claude Code: Full‑feature configuration

A collection of agents, skills, hooks, commands, rules, and MCP configurations curated over ten months by an Anthropic hackathon winner. It provides a "full‑blood" setup for Claude Code.

Agents : planner, architect, tdd‑guide, code‑reviewer, … – specialized sub‑agents with clear responsibilities.

Skills : coding standards, front‑back patterns, TDD workflow, security review – domain knowledge and workflow definitions.

Commands : /tdd, /plan, /e2e, /code‑review, /build‑fix – one‑click actions.

Rules : security checks, code style, test requirements, Git workflow – enforced conventions.

Hooks : pre‑ and post‑tool triggers – automation.

MCP Configs : GitHub, Supabase, Vercel, Railway, … – cloud service integration.

Installation (recommended plugin mode):

# Add marketplace
/plugin marketplace add affaan-m/everything-claude-code

# Install plugin
/plugin install everything-claude-code@everything-claude-code

Manual installation:

git clone https://github.com/affaan-m/everything-claude-code.git
cp everything-claude-code/agents/*.md ~/.claude/agents/
cp everything-claude-code/rules/*.md ~/.claude/rules/
cp everything-claude-code/commands/*.md ~/.claude/commands/

Important reminder : Enabling too many MCPs shrinks a 200k‑token context window to about 70k. The author recommends 20‑30 MCPs total, with no more than 10 active per project, and keeping the overall tool count under 80.

Document Illustrator: AI‑generated illustrations for documents

A Claude Code skill that parses a document, extracts core topics, and automatically creates professional‑looking images.

🤖 AI summarization : understands content and extracts themes.

📝 Format‑agnostic : works with Markdown, plain text, PDF, etc.

🎨 Three styles : gradient glass cards, ticket‑style, vector illustration.

📐 Flexible aspect ratios : 16:9 (landscape) or 3:4 (portrait).

🖼️ Optional cover image : generates a summary cover.

Style details:

Gradient glass card : Apple Keynote‑like glass‑morphism, aurora gradient – suitable for tech product showcases, data reports, future trends.

Ticket style : high‑contrast B/W, structured layout, boarding‑pass look – suitable for infographics, statistics, timelines.

Vector illustration : flat design, retro palette, panoramic composition – suitable for storytelling, concept explanation, educational content.

Installation:

npx skills add https://github.com/op7418/Document-illustrator-skill

Usage inside Claude Code:

帮我为这个文档生成配图:~/blog/my-article.md

Claude prompts for aspect ratio, cover generation, and number of images, then saves the results alongside the source file.

Gemini CLI: Free short course

The short course “Gemini CLI: Code & Create with an Open‑Source Agent” (DeepLearning.AI & Google, instructor Jack Wotherspoon) teaches developers how to use Gemini CLI together with MCPs and extensions.

Learning outcomes:

MCP + extensions: coordinate local files with Google Workspace, Canva, etc.

Software development automation: build web features, create dashboards, set up GitHub Actions for code review.

Beyond code: generate social media content and organize learning materials from multimedia files.

Course outline (≈1 hour):

What is Gemini CLI? – 5 min

A Tour of Gemini CLI – 7 min

Context is Key: GEMINI.md – 4 min

Workflows with MCP – 5 min

Customization with Extensions – 4 min

Gemini CLI for Software Development – 6 min

Gemini CLI for Data Analysis – 6 min

Gemini CLI for Content Creation – 4 min

Gemini CLI for Learning – 5 min

Target audience: developers with basic command‑line and Python knowledge.

Skills.sh: Central hub for Agent Skills

Directory and distribution platform for Agent Skills. Users can discover and install community‑contributed skills with a single command. npx skills add <owner/repo> Popular skills include:

vercel-react-best-practices (frontend)

web-design-guidelines (design)

frontend-design (frontend)

building-native-ui (mobile)

better-auth-best-practices (authentication)

seo-audit (SEO)

copywriting (content)

marketing-psychology (marketing)

pdf、xlsx、pptx、docx (document processing)

brainstorming (creativity)

test-driven-development (testing)

systematic-debugging (debugging)

humanizer-zh (Chinese output)

baoyu-article-illustrator (article illustration)

baoyu-post-to-wechat (WeChat publishing)

Original Source

Signed-in readers can open the original source through BestHub's protected redirect.

Sign in to view source
Republication Notice

This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactadmin@besthub.devand we will review it promptly.

Gemini CLIClaude CodeAgent SkillsDocument IllustratorEverything Claude CodeHappy Coderskills.sh
Old Zhang's AI Learning
Written by

Old Zhang's AI Learning

AI practitioner specializing in large-model evaluation and on-premise deployment, agents, AI programming, Vibe Coding, general AI, and broader tech trends, with daily original technical articles.

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.