Global AI rules and tech stack definitions
This repository also configures its own agents. See what ai-globals tells them →
Skill Claude CodeCodex
Lord skill for evidence-based production-readiness audits — full-spectrum project review (architecture, security, data, testing, performance, observability, config, deployment, supply chain, docs, UX/a11y, legal), severity-ranked findings, mid-session decision escalation, and a human-only launch checklist.
Skill Claude CodeCodex
Build the project's voice foundation — about-me.md + voice.md in .ai/ — that every content skill reads before personalized work. Foundation pattern adapted from charlie947/social-media-skills voice-builder.
Skill Claude CodeCodex
Lord skill for Python UI design mastery — PySide6/Qt6 desktop apps, Textual 8 TUI, Flet 1.0 cross-platform, Reflex 0.9 / NiceGUI 3 / FastAPI+htmx web apps, design tokens, states, a11y, and packaging.
Skill Claude CodeCodex
Lord skill for server administration mastery — SSH hardening, firewalls, reverse proxies + TLS, monitoring, logs, backups/DR, container hosts, self-hosted panels (Coolify/Dokploy/Portainer), Proxmox, Tailscale/WireGuard, troubleshooting, Linux + Windows Server.
Skill Claude CodeCodex
Lord skill for reverse engineering shipped artifacts — native binaries, Electron/JavaScript apps, .NET assemblies, APKs, firmware, packages — via REA (rea-agents) CLI/MCP. Evidence-tiered analysis (observation/derivation/inference/unknown), provider-bring-your-own (Ghidra/IDA/Hopper/JADX), read-only by default.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: