agentation
agentation — Visual UI Feedback Bridge for AI Agents
The missing link between human eyes and agent code. Instead of describing "the blue button in the sidebar," you hand the agent
.sidebar > button.primary. It cangrepfor that directly.
When to use this skill
- When a human wants to mark exact UI elements and send structured feedback to an agent
- When MCP watch mode is available and the agent should stay in a live annotation loop
- When a copied annotation payload includes
elementPath,reactComponents, or bounding box data - When
omgentersverifyorverify_uiand UI feedback should drive the next fix
Instructions
Step 1: Respect phase and lifecycle guardrails
More from akillness/oh-my-gods
deepagents
>
19agent-workflow
>
19data-analysis
>
16omg
OMG — Integrated AI agent orchestration skill. Plan with ralph+plannotator, execute with team/bmad, verify browser behavior with agent-browser, apply UI feedback with agentation(annotate), auto-cleanup worktrees after completion. Supports Claude, Codex, Gemini CLI, and OpenCode. Install: ralph, omc, omx, ohmg, bmad, plannotator, agent-browser, agentation.
16frontend-design-system
Produce production-grade UI designs using clear design tokens, layout rules, motion guidance, and accessibility checks for consistent, scalable frontend development.
15omc
oh-my-claudecode — Teams-first multi-agent orchestration layer for Claude Code. 32 specialized agents, smart model routing, persistent execution loops, and real-time HUD visibility. Zero learning curve.
15