# Record an agent-completed browser task as a parameterized Oya playbook

> Complete a test browser task once, save its learned steps as an Oya playbook, and verify a replay with new inputs while retaining repair evidence.

- Skill: `agentskillexchange/record-an-agent-completed-browser-task-as-a-parameterized-oy` (Agent Skill)
- Install (CLI): `npx get-skill add agentskillexchange/record-an-agent-completed-browser-task-as-a-parameterized-oy`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/record-an-agent-completed-browser-task-as-a-parameterized-oy/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-11-15
- Page: https://skillmd.com/skills/agentskillexchange/record-an-agent-completed-browser-task-as-a-parameterized-oy

---


# Record an agent-completed browser task as a parameterized Oya playbook

Complete a test browser task once, save its learned steps as an Oya playbook, and verify a replay with new inputs while retaining repair evidence.

## Prerequisites

Node.js 20+, @oya-ai/browser, configured Oya control plane or cloud API key, model API route; Docker/Compose for self-hosting

## Installation

Install or set up from the source-backed instructions:

Run npm install @oya-ai/browser@1.0.233 in a Node.js 20+ project. For an existing self-hosted deployment set OYA_BASE_URL and OYA_API_KEY; for Oya Cloud follow upstream account setup and set OYA_API_KEY. Configure the model route for learning, then adapt the pinned examples/sdk/05-playbooks.ts sample using a test form and clean up the browser after each run.

- Source: https://github.com/OyadotAI/oya-browser

## Documentation

- https://github.com/OyadotAI/oya-browser/blob/7125d696291bdf8b2a4879e68b6a33186dbe8791/examples/sdk/05-playbooks.ts

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/record-agent-browser-task-as-parameterized-oya-playbook/)

