From oh-my-agent
Classifies user intent into OMA stages (plan, prd, exec, verify, fix, research, lifecycle) before execution and routes to correct commands. Detects missing inputs for vague requests or unclear phases.
npx claudepluginhub sswym/oh-my-agent --plugin oh-my-agentThis skill uses the workspace's default tool permissions.
使用此技能作为入口门控以减少命令-阶段不匹配。
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
使用此技能作为入口门控以减少命令-阶段不匹配。
plan、prd、exec、verify、fix、research、lifecycle）。/oma:* 命令或 $skill。## 意图
- 主要：
- 置信度：
## 缺少输入
- ...
## 推荐路由
- 下一个命令：
- 委派：
## 交接提示
- ...