Engineering discipline for AI agent systems — four always-on principles, test-driven development, verification-before-completion, system-architecture playbooks, a scope-disciplined product manager, docs/-native project management, and Claude Code → GitHub Copilot agent conversion.
7 skills
Context engineering for AI agents — AI-optimized second-brain skills, durable pipeline state for multi-agent handoffs, and expert prompt building.
3 skills
Live status line and agent telemetry — the active /command or skill run with a timer, per-subagent context bar, model, estimated cost, tokens, duration and tool count, plus a per-run report. Run /statusline-kit:setup once to switch the status line on.
1 skill · hooks
Multi-agent web dev pipeline — UX research and design critique around the build, plus the designer ↔ frontend contract: freeze approved mockups into a canonical oracle, port them 1:1 on any stack, and verify with screenshot-based design-diff gates.
2 skills
Content engine for technical creators — social posts and video scripts engineered around named copywriting frameworks, scroll-stopping hooks, and retention mechanics.
1 skill
Interactive AI teaching pipeline — /repo-to-course turns any codebase into a structured tutorial course (markdown, GitHub Pages site, or interactive HTML).
1 command