materialofair/oh-my-codex

patent-workflow

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

Source text: Chinese

prompt-optimizer

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…

skill-tester

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

architecture-review

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-commenting

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

aireview

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

architect-planner

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。

Source text: Chinese

backend-patterns

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

checkpoint

Imported from everything-codex command checkpoint

coding-standards

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

conductor

Use when the user explicitly asks for Conductor, wants track/spec/plan/review artifacts on disk, or needs long-lived project context management. Prefer start-dev for small or one-off tasks. If Conductor is not configured in the project, start with setup.

consensus

多视角共识决策 - 使用 Codex 主线与只读 child agent 获取架构、实现和风险视角并综合决策。

Source text: Chinese

de-ai-writing

Use when the user asks to remove AI tone, humanize a draft, or polish text written (or smelling) like an LLM. Trigger phrases include "去 AI 味"、"去ai味"、"降低机器感"、"改得像真人写的"、"不要 AI 腔"、"humanize"、"de-ai"、"remove AI tone". Default optimized for Chinese; supports…

Source text: Mixed languages

debug-analysis

深度调试分析 - 使用 Codex 本地证据检索、命令验证和只读 child agent 进行系统性根因诊断。

Source text: Chinese

deepinit

Deep codebase initialization with hierarchical AGENTS.md documentation

e2e

Imported from everything-codex command e2e

eval-harness

Formal evaluation framework for Codex sessions implementing eval-driven development (EDD) principles

eval

Imported from everything-codex command eval

evolve

Imported from everything-codex command evolve

frontend-patterns

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

iterative-retrieval

Pattern for progressively refining context retrieval to solve the subagent context problem

local-skills-setup

Set up and manage local skills for automatic matching and invocation

mcp-setup

Configure popular MCP servers for enhanced agent capabilities

multi-model-research

多代理技术调研 - 使用 Codex 主线与只读 child agent 并行收集架构、实现、文档和风险视角。

Source text: Chinese

project-session-manager

Manage isolated dev environments with git worktrees and tmux sessions

quick-init-project

This skill should be used when the user asks to "快速初始化项目", "根据需求推荐全栈还是前端/后端", "初始化 monorepo", "生成项目脚手架方案", "project bootstrap recommendation", or "fullstack vs frontend vs backend decision".

Source text: Mixed languages

refactor-clean

Imported from everything-codex command refactor-clean

release

Automated release workflow for oh-my-codex

research

Use this skill for multi-stage, evidence-based research with parallel investigation, source ranking, verification, and synthesis.

setup-pm

Imported from everything-codex command setup-pm

skill-create

Imported from everything-codex command skill-create

start-dev

Intelligent adaptive workflow with automatic pattern library loading, codebase exploration, and multi-approach architecture. Auto-detects frontend/backend tasks and loads relevant patterns.

tdd-workflow

Use this skill for test-first implementation of new features, bug fixes, and refactors with RED-GREEN-REFACTOR discipline and explicit verification gates.

test-coverage

Imported from everything-codex command test-coverage

thinkdeep

深度推理分析 - 使用 Codex 结构化推理、证据检索和可选只读 child agent 处理复杂问题。

Source text: Chinese

ultrapilot

Parallel autopilot with file ownership partitioning

update-codemaps

Imported from everything-codex command update-codemaps

update-docs

Imported from everything-codex command update-docs

verification-loop

Use this skill for iterative verify-fix cycles across build, type, lint, test, and security gates until completion or explicit stop conditions.

writer-memory

Agentic memory system for writers - track characters, relationships, scenes, and themes