Parallel exploration of implementation approaches - implements multiple variants simultaneously and lets tests determine the winner
#ai-agents
3674 posts
Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.
Evidence-based senior product designer skill for Claude Code — turns any UI/app build into research-driven, accessible, non-generic design....
Build a complete, secure SaaS end to end in Claude Code: prevention-first security (not audit), real Stripe payments (not just a catalog), a...
Xcode-free iOS development with xtool - build SwiftPM apps on Linux, Windows, and macOS without Xcode
PR health assistant - monitors CI, triages review comments, fixes issues with systematic prevention. Uses gh CLI and gh-pr-review extension.
research & dispatch skills for Claude Code — 研究调度(Quick Recon + fact-check)+ 多模型调用器(纯调用器版)
A Claude Code plugin for Obsidian — Karpathy's LLM Wiki shipped as a four-layer, hook-enforced agent stack with multi-agent orchestration.
12 AI-powered skills for product discovery — from raw customer signal to validated opportunity. Built for Claude Code & GitHub Copilot.
Personal operating system for executives - reflection frameworks, goal systems, coaching-style reviews (Gustin, Ferriss, Robbins, Lieberman,...
State-of-the-Art (2026) Claude Code skills for building and auditing software — 40+ domain & language skills, BUILD/AUDIT modes, audit check...
An agent skill for Peter Lynch-style stock analysis, inspired by Learn to Earn, One Up on Wall Street, and Beating the Street.