Agentation
When you're staring at a broken UI element and need to tell your AI coding agent exactly which button or form field is wrong without typing out vague descriptions or guessing at selectors, this captures the precise element, bounding box, and context as a structured packet you can hand straight to Claude Code, Codex, or similar agents. It's not a browser automation tool, it's the annotation bridge between what a human reviewer clicks in the real rendered page and what the agent needs to apply a fix. Works best in copy-paste review loops or synced watch mode where annotations flow automatically into the agent context. The routing guide is solid: use browser-harness for clean verification sessions, playwriter for logged-in browser reuse, and this when exact human UI feedback is the missing piece.
- skills.sh installs
- 171
- GitHub stars
- 22
- last updated
- Jun 3, 2026
Install
$ npx -y skills add akillness/oh-my-skills --skill agentation --agent claude-codeInstalls into .claude/skills of the current project.
Files
agentation
agentation is the rendered-UI feedback bridge in this repo.
Use it when a human needs to click the actual UI, attach feedback to the exact element or region they mean, and pass a structured packet to the coding agent. The main job is annotation routing: choose the right annotation mode, capture precise evidence, then hand the fix loop to the right adjacent skill or agent runtime.
When to use this skill
Use agentation when the task needs one or more of these:
- a human reviewer pointing at a real UI element instead of describing it vaguely
- structured feedback packets with selectors, element paths, bounding boxes, or copied markdown
- a local copy-paste review loop between a browser and a coding agent
- an MCP-backed sync/watch loop where new annotations flow into the agent context automatically
- a self-driving critique/fix loop that still starts from rendered UI evidence
- platform setup for passing pending UI annotations into Claude Code, Codex, Gemini CLI, or OpenCode
Do not use agentation by default for:
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/akillness/oh-my-skills
- First seen
- Jun 3, 2026
More from akillness/oh-my-skills
All 81- Bmad Idea171
- Code Review171
- Marketing Automation171
- Obsidian Plugin171
- Opencontext171
- Standup Meeting171
- Task Estimation171
- Ui Component Patterns171
- Changelog Maintenance170
- Monitoring Observability170
- Sprint Retrospective170
- Deployment Automation169
- Ohmg169
- Security Best Practices169
- Authentication Setup168
- Fabric168
- Firebase Ai Logic168
- Debugging167
- Environment Setup167
- Git Submodule167
- Git Workflow167
- Marketing Skills Collection167
- Pattern Detection167
- Bmad166
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs