Built from hands-on work optimizing production Astro sites across static, hybrid, and SSR output modes. Covers the full performance stack: native image optimization with the Astro Image component, View Transitions API integration, prefetch strategies, Dev Toolbar audit workflows, accessibility fixes aligned to WCAG, and Core Web Vitals improvements. Grounded in Astro 3/4/5/6+ internals and real optimization cycles — not generic web performance advice.
Autonomous multi-agent system for e-commerce advertising. Features AI-driven creative generation, real-time multivariate testing, and cross-platform budget optimization (Meta, TikTok, Amazon). Uses historical performance data to autonomously refine targeting, bids, and creative assets, maximizing ROAS while reducing manual overhead. A scalable, data-driven solution for end-to-end campaign management.
Connect Cursor, Claude Code, Hermes & Codex with a shared local SQLite brain. Slash token costs by 92.2% with instant, zero-amnesia cross-agent recall. 100% private, BYOK, lifetime buyout.
Audit AI agent workspaces for authority, secrets, data flow, memory, supply-chain, and evidence risks—locally and without executing target code.
This Skill is built on practical expertise in AI agent safety, prompt-injection defense, source-to-sink privacy review, tool and MCP metadata integrity, memory provenance checks, autonomous action scoping, and evidence-based verification. It helps agents separate instructions from evidence before tool calls, uploads, publishing, deletion, code execution, or network output.
Prevents AI agents from declaring tasks complete until every requirement is verified with a one-line evidence anchor — when a gate fails, the agent stops and reports rather than proceeding, and only a human can unlock the gate to continue.
A lightweight Copilot subscription agent runtime built on FastAPI and Copilot SDK. Manage multi-account OAuth, scheduled tasks, GitHub Enterprise support, and a bilingual Web UI.
Connect any MCP-compatible AI agent (Claude, Cursor, Copilot, Codex, Windsurf, Amp, Cline) to Penpot to create, audit, and maintain design systems — tokens, flows, interactions, animations, and design-to-code export to HTML/CSS/React.
A kickoff protocol (agent skill) for multi-step tasks. Before writing any code, the agent must: run a spec interview, batch every human-authorization step into one checklist, build a self-verification loop (log sink + verify script + dry-run) *before* the feature itself, and build comparable variants instead of blocking on third-party decisions.