#software-architecture

A Codex and ChatGPT Skill that helps agents avoid scope creep and overengineering—finish the ask, prove it works, and keep software architecture clear.

Ten composable AI skills covering the full arc from idea to launch. Discovery hub for prd-ready, architecture-ready, roadmap-ready, stack-ready, repo-ready, production-ready, deploy-ready, observe-ready, launch-ready, harden-ready. Plug into Claude Code, Codex, Cursor, Windsurf.

Council skill for Codex, Claude Code, and AI coding agents: expert review before coding, architecture decisions, refactors, and debugging.

Architectural taste for TypeScript coding agents. Minimize conceptual surface area, create boundaries deliberately, and generate code humans can navigate, review, and evolve.

Guardrails for AI coding agents. EADOS generates a governed repo - agent contract, ADRs, CI gates, SemVer - for any of 19 languages, then enforces the rules with lint. Works with Claude Code, Codex, and Gemini.

ActionParity (影核/ShadowCore) — open standard: one canonical app action across GUI, CLI, MCP and AI. AI agents can verify every action without pixels.

Evidence-first code review and refactoring skills for Claude Code and Codex. Find root causes, reject unnecessary refactors, and make the smallest safe change.

A staged-gates, multi-agent software delivery methodology for Claude Code — sub-agent definitions, orchestration protocol, quality-gate hooks, and ports for other AI coding tools. From the article 'The Agentic Delivery Office'.

Evidence-based multi-pass repository audits for Codex, Claude Code, and Agent Skills-compatible coding agents.

Diago turns engineering work into AI-powered, evidence-grounded software diagrams for Codex and Claude.