dev

Orchestrate feature development through a chained sub-skill pipeline to a pull request.

50|37|Updated Oct 8, 2025
One-click install
npx skills add https://github.com/browseros-ai/BrowserOS-agent --skill dev-browseros-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev
Source: https://github.com/browseros-ai/BrowserOS-agent/tree/main/.claude/skills/dev
Command: npx skills add https://github.com/browseros-ai/BrowserOS-agent --skill dev-browseros-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This workflow provides a complete, repeatable path to develop features end-to-end, reducing manual handoffs by orchestrating exploration, design, PRD creation, implementation, review, and PR creation in a deterministic pipeline.

Core Features & Use Cases

  • End-to-end orchestration: Chains sub-skills into a seamless feature development pipeline from ideation to PR.
  • Artifact generation: Writes intermediate and final outputs to .llm/<feature_name>/ for traceability.
  • Interactive design prompts: Pauses for user input when making design decisions or PR approvals, enabling collaborative workflows.
  • Use Case: Teams can start with a feature description, have the system generate design options, PRD, implementation notes, and a ready-to-submit PR.

Quick Start

Invoke /dev1-start <feature description> to begin the automated development pipeline.

Frequently Asked Questions about dev

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate end-to-end feature development from ideation to pull request?

To orchestrate end-to-end feature development, you can use an automated pipeline that chains sub-skills for exploration, design, PRD creation, implementation, review, and PR submission. This reduces manual handoffs by coordinating the entire workflow deterministically.

What is the best way to automate PRD creation and implementation notes for new features?

Automating PRD creation and implementation notes is best handled through a development workflow pipeline that takes a feature description and generates design options, PRDs, and implementation traces. Intermediate outputs are written to .llm/<feature_name>/ for traceability.

Can I pause the feature development pipeline for user input during design decisions?

Yes, you can pause the feature development pipeline for user input. The workflow supports interactive design prompts, pausing when making design decisions or PR approvals to enable collaborative human-in-the-loop workflows before proceeding to the next stage.

How do I generate a ready-to-submit pull request from a feature description?

You generate a ready-to-submit pull request by invoking the pipeline with a feature description. The system orchestrates exploration, implementation, and review, culminating in a finalized PR while writing all intermediate artifacts to a designated directory.

Does this automated development workflow require specific sub-skills for code review and release?

Yes, the automated development workflow relies on chained sub-skills to handle code review and release. It orchestrates these sub-skills sequentially within a defined pipeline to ensure deterministic progression from feature design to final PR creation.

Where are intermediate artifacts stored during an automated feature development pipeline?

Intermediate artifacts during an automated feature development pipeline are stored in the .llm/<feature_name>/ directory. This ensures full traceability of generated design options, PRDs, and implementation notes throughout the end-to-end workflow.