Starter kit for building an agent harness, the map, guardrails, and feedback loops that let AI agents ship software reliably.

A collection of Claude skills organized by how I think, decide, research and build.

weekly hermes skill that reads my X bookmarks + grok x_search and filters them against my github, surfaces 3-4 repos worth my time

The 15-minute Sunday Claude review. 5 things to check every week so next Monday's Claude starts smarter than this one did.

Setup notes and the self-written skill file from my Hermes Friday GitHub agent. Everything you'd need to build the same thing.

Portfolio and blog for qendresa.dev – exploring code and creativity

Three Claude Code features almost nobody uses, configured. Statusline, /resume, and a custom /script command in under 20 minutes.

AI projects to build in a weekend. For developers: requires Python or Node.js, an Anthropic API key, and comfort with the terminal. Starter code and READMEs for each project.

Pre‑deployment evaluation for commerce agents: price accuracy, budget safety, and x402 correctness

One-command template that turns any repo (or the Anthropic Mythos leak) into a verifiable multi-agent setup

escrow releases only when proofs pass (ERC-8004 Validation + ACP on Base)

Tiny streaming logger + reproducible coding eval with manifest & attestation for decentralized-AI workflows.

set up React (Vite) or Next.js projects with automatic GitHub repo creation and Vercel deployment