AI Link Lab

Skills

Superpowers: Engineering Discipline for AI Coding Agents

Superpowers is an open-source agentic skills workflow by obra that turns brainstorming, planning, TDD, debugging, and code review into habits your AI coding agent follows automatically.

2026-05-18

Karpathy's LLM Wiki: Turn AI Research Into a Living Markdown Knowledge Base

LLM Wiki is not another chatbot over documents. It is a workflow where an LLM maintains a structured Markdown wiki that compounds across sources, questions, and sessions.

2026-05-17

Quartz: Turn Markdown Notes Into a Searchable, Linked Digital Garden

Quartz is a static-site generator built for digital gardens. It turns Markdown notes into websites with full-text search, backlinks, graph view, popover previews, Obsidian compatibility, and technical writing features.

2026-05-17

DESIGN.md: Pure-Text Design Systems That Let AI Agents Generate Pixel-Matched UI

DESIGN.md is a plain-text design system format from Google Stitch. Drop it in your project root and AI coding agents generate UI that matches your brand. No Figma exports, no JSON schemas, no special tooling.

2026-05-16

Image Blaster: Blast Any Image Into a Meshed 3D World in Under 5 Minutes

Image Blaster is a Claude Code skill that turns any image into a full 3D environment: .glb object models, Gaussian splat scenes, ambient audio, and physics SFX. One terminal command, under 5 minutes.

2026-05-16

Karpathy's Fix for Claude Code: Four Principles That Kill Bloated AI Code

Andrej Karpathy called out how LLMs overcomplicate code. This CLAUDE.md plugin fixes it: think before coding, simplicity first, surgical changes, goal-driven execution.

2026-05-11

Agents

Multica: When Coding Agents Multiply, Terminals Stop Scaling

Multica is an open-source Human + Agent project management platform that puts Claude Code, Codex, Cursor Agent, and other coding agents into one board, task lifecycle, skill library, and runtime panel.

2026-05-20

Vibe-Trading: Turn Trading Ideas Into Backtestable Agent Research

Vibe-Trading is an open-source finance research agent workspace. It connects natural-language questions to market data, strategy generation, backtesting, reports, persistent memory, multi-agent teams, and MCP integrations. It is built for research, simulation, and backtesting, not live trade execution.

2026-05-18

Five Things Claude Code 102 Teaches Academic Researchers

Mushtaq Bilal's second Claude Code tutorial went viral with 440K views. Behind the numbers is a clear signal: AI agents for research are moving from experiment to standard practice.

2026-05-13

The Agent Harness: Why Your Model Isn't the Problem

LangChain jumped 25 spots on TerminalBench without touching the model. The harness — not the LLM — is what separates demos from production. Here are the 12 components that matter.

2026-05-11

Your Agent Isn't Blind — You Just Forgot to Give It Eyes

An agent's ceiling is the quality of its data input. Wire up real-time data with XCrawl MCP Server and compress a 40-minute manual workflow into 3 minutes.

2026-05-11

File-Based Agents Don't Need a Build Step

Anthropic's financial-services stack ships 11+ agents, 30+ skills, and 11 data connectors from a single source — no build step, no CI/CD. Here's how, and why it matters.

2026-05-11

Development

Spend One Hour Setting Up Claude Code Harness — See the Difference Immediately

Same model, same Claude Code — with or without a Harness setup, the output gap is staggering. Build a compounding agent configuration system in five steps: CLAUDE.md, Hooks, Skills, LSP, and Sub-agents.

1 days ago

Stop Writing Markdown — Use HTML with Claude Code

Thariq, a Claude Code engineer at Anthropic, explains why he's replacing Markdown with HTML as the primary output format for AI agents — and how you can too.

2026-05-10

OpenSpec: agree with your AI before you write a single line

AI coding without specs means vague prompts and unpredictable results. OpenSpec brings predictability without the ceremony.

2026-05-07

Open Source

skills.sh: Vercel Is Building the npm for Agent Skills

skills.sh is Vercel's open-source CLI and directory for the Agent Skills ecosystem. One command to install reusable skills across 50+ agents, with 410K+ total installs. A deep look at its architecture, cross-agent compatibility, and ecosystem momentum.

2 days ago

AntV Infographic Turns AI Output Into Editable Visuals

AntV Infographic is an open-source declarative infographic engine from AntV. This review covers its AI-friendly syntax, streaming SVG rendering, templates, skills, and trade-offs.

5 days ago

Pi: A Coding Agent That Refuses to Own Your Workflow

Pi is an open-source TypeScript coding agent harness from earendil-works. This review covers its architecture, extensibility, provider support, supply-chain stance, and trade-offs.

5 days ago

Cool Sites

mesh3d: A Better Place to Find 3D Website Inspiration

mesh3d is a curated gallery of Three.js, WebGL, and interactive 3D websites. Here is why designers, developers, and creative teams should bookmark it.

5 days ago

Google Labs: Google's Secret Stash of Playable AI Experiments

I stumbled into labs.google and discovered a dozen experimental AI tools Google is quietly incubating — from the paper-to-podcast NotebookLM to the prompt-free Whisk. Each one is worth an afternoon.

5 days ago