<h1 align="center"> ⚡ hyperskills </h1>

<p align="center"> <strong>Focused AI agent skills for things models don't already know</strong> </p>

<p align="center"> <em>Knowledge, guidance, wisdom, SOTA. Reach for what fits.</em> </p>

<p align="center"> <img src="https://img.shields.io/badge/Skills-17-e135ff?style=for-the-badge&logo=anthropic&logoColor=white" alt="17 Skills"> <img src="https://img.shields.io/badge/skills.sh-Compatible-ff6ac1?style=for-the-badge&logo=vercel&logoColor=white" alt="skills.sh"> </p>

<p align="center"> <a href="https://github.com/hyperb1iss/hyperskills/blob/main/LICENSE"> <img src="https://img.shields.io/github/license/hyperb1iss/hyperskills?style=flat-square&logo=opensourceinitiative&logoColor=white" alt="License"> </a> <a href="https://github.com/hyperb1iss/hyperskills/releases"> <img src="https://img.shields.io/github/v/release/hyperb1iss/hyperskills?style=flat-square&logo=github&logoColor=white" alt="Release"> </a> </p>

---

## 💎 What This Is

Models already know how to write React components, Kubernetes manifests, and PyTorch code. They don't need 300 lines of examples for that.

hyperskills is built around an agent workflow. Brainstorming structured by the Double Diamond. Wave-based research with deferred synthesis. Verification-driven planning and implementation. Cross-model peer review that catches what self-review misses. Seven orchestration strategies for multi-agent work. Conversation consolidation that pulls signal out of past sessions into persistent memory. The process skills are the heart of it, mined from thousands of real dispatches and tens of thousands of tracked operations — most recently re-hardened against a 100-day corpus of 600 real Claude and Codex sessions (Jul 2026).

Domain skills round out the toolbox where models have stale or missing knowledge: current Astral Python tooling, Tilt operational decision trees, and terminal UI design that survives across emulators.

Each skill encodes