dev1-start

Scaffold a feature workspace and survey the codebase for new development tasks.

Updated Mar 31, 2026

Search Tags:#workflow #design #workspace #handoff #start #feature-development #codebase-exploration

Ready to run

npx skills add https://github.com/Sridhar-Ranganaboina/WebGenie --skill dev1-start

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: dev1-start
Source: https://github.com/Sridhar-Ranganaboina/WebGenie/tree/main/packages/browseros-agent/.claude/skills/dev1-start
Command: npx skills add https://github.com/Sridhar-Ranganaboina/WebGenie --skill dev1-start

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Start a new feature development workflow by performing a quick, high-level exploration of the codebase to understand the stack, project layout, and existing artifacts, then kick off the design phase.

Core Features & Use Cases

Workspace scaffolding: derive a short snake_case feature name from the user's description, create the directory .llm/<feature_name>/, and write .llm/<feature_name>/tmp_context.md with the original request, timestamp, and current working directory.
High-level discovery: read CLAUDE.md (or .claude/CLAUDE.md) if present, identify the stack, dependencies, and project structure.
Handoff to design: summarize findings and trigger the next design step via /dev2-design <feature_name>.

Quick Start

Describe the feature you want to explore to initiate the dev1-start workflow and generate the initial workspace and exploration notes.

Frequently Asked Questions about dev1-start

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

FAQPage Schema

How do I start a new feature development workflow with codebase exploration?▼

Starting a new feature development workflow involves performing a high-level codebase survey to identify the stack and dependencies, then scaffolding a dedicated workspace directory with initial context files for handoff.

What is the best way to scaffold a workspace for early-stage feature requests?▼

Scaffolding a workspace for feature requests is best done by deriving a snake_case feature slug, generating an .llm/<slug>/ directory, and writing a tmp_context.md file to capture the original request, timestamp, and working directory.

How do I automate initial feature discovery and project layout identification?▼

Automating initial feature discovery requires reading project configuration files like CLAUDE.md to identify the project structure, stack, and dependencies, ensuring deterministic outputs for the next development phase.

Can I use this workflow to hand off codebase exploration findings to the design phase?▼

Yes, this workflow summarizes high-level discovery findings and generates an exploration log, explicitly triggering the next design step via a command like /dev2-design to ensure a smooth handoff.

Do I need existing project artifacts like CLAUDE.md to run this feature discovery process?▼

You do not strictly need existing artifacts to run feature discovery, but having configuration files like CLAUDE.md or .claude/CLAUDE.md present allows the workflow to accurately identify your stack and project layout.

What are the limitations of automating early-stage feature discovery?▼

Limitations of automating feature discovery include relying solely on high-level codebase surveys, which may miss deep architectural nuances, and generating only brief exploration logs suitable for initial design handoff rather than detailed implementation.