materialofair

三阶段专利撰写workflow（Research → Plan → Implement），借鉴AutoPatent架构，通过 Codex CLI 原生 spawn_agent 派发 explorer/reviewer child agent 协作，确保专利质量和授权率；也用于整理或优化已有 DOCX 专利交底书、保留图片和版式资源并生成新版 Word 文档

Analyze raw prompts, identify intent and gaps, inventory the current oh-my-codex skill catalog across local/upstream sources, choose the best-fit skill chain, and output a ready-to-paste optimized prompt for Codex. Advisory role only — never executes the task…

Tests Codex skill functionality with TDD approach, verifying skills work correctly through automated test scenarios and validation

Review software architecture using repository evidence, with focused design, change, and system modes. Use when evaluating an architecture proposal before implementation, verifying a completed feature or refactor for boundary and dependency regressions, or…

AI-native code annotation protocol that encodes intent, risk, dependencies, constraints, and test expectations in machine-parseable comments.

Professional Codex-native multi-agent code review with confidence scoring

架构规划专家 - 使用 Codex 本地上下文、仓库证据和只读 child agent 进行大型系统架构设计与规划。

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Explain a topic like I'm a 5 year old. Use when the user types /eli5 [topic] or asks for a dead-simple picture explainer of how something works.

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my…

Optimize a rough prompt with an independent subagent, present several CONCISE ready-to-run variants for the user to pick or edit, then EXECUTE the chosen prompt directly in the current session. Unlike prompt-optimizer (advisory only — it just hands back…

MANUAL ONLY. Run a structured pre-MR review when the user explicitly requests merge-review via /merge-review, $merge-review, merge-review, or natural language such as 执行 merge-review. Produces impact analysis report, merge readiness checklist, regression…

Use when the user wants to "quick init project", "bootstrap a new project", "recommend fullstack vs frontend vs backend", "initialize monorepo", "generate project scaffold", "project setup recommendation", or asks "快速初始化项目", "初始化 monorepo", "生成项目脚手架方案"

Use when user wants durable Context->Spec->Plan->Implement tracks ('conductor', 'structured workflow', 'track this', 'context then plan'). Creates and governs `.omc/conductor/` artifacts for OpenCode multi-session delivery.

Playwright end-to-end orchestration for critical user journeys, artifact capture, flaky-test isolation, and CI-ready reporting.

Post-change intelligent test generation workflow that detects stack, analyzes changed files, and produces acceptance plus regression tests.