Orchestrates the entire development lifecycle from feature exploration to pull request.
Install
mkdir -p .claude/skills/dev-browseros-ai && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11908" && unzip -o skill.zip -d .claude/skills/dev-browseros-ai && rm skill.zipInstalls to .claude/skills/dev-browseros-ai
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Full feature development workflow. Explores codebase, designs, writes PRD, implements, reviews, fixes, and creates PR. Use with "/dev <feature description>".Key capabilities
- →Explore codebase for feature development
- →Design feature options and allow user selection
- →Generate Product Requirements Documents (PRD)
- →Implement features based on designs and PRDs
- →Perform code reviews and apply fixes
- →Create and manage pull requests
How it works
The skill orchestrates a seven-stage feature development pipeline, invoking sub-skills sequentially and handling handoffs between stages, pausing for user input when necessary.
Inputs & outputs
When to use dev
- →Develop a new feature from scratch
- →Manage complex feature implementation
- →Ensure consistent PR workflow
About this skill
Dev Workflow — Orchestrator
Run the full feature development pipeline by invoking sub-skills sequentially. Start by invoking /dev1-start $ARGUMENTS. Each sub-skill will automatically chain to the next one.
Pipeline
/dev1-start— High-level code exploration/dev2-design— Design options (user picks one)/dev3-prd— Questions + PRD/dev4-implement— Implementation/dev5-review— Code review + commit/dev6-review-fix— Apply review fixes + commit (skipped if review is clean)/dev7-pr— Create PR, wait for Greptile, address comments, push
Instructions
Invoke /dev1-start $ARGUMENTS now. It will chain through the rest of the pipeline automatically. Each skill writes artifacts to .llm/<feature_name>/ and hands off to the next skill.
Skills that need user input (design choice, question answers, PR approval) will pause and wait before continuing.
When not to use it
- →When only a single stage of the development pipeline is needed
- →When the user does not want an automated, sequential workflow
Limitations
- →The workflow is sequential, chaining through stages automatically.
- →Skills requiring user input will pause and wait for a response.
- →Artifacts are written to `.llm/<feature_name>/`.
How it compares
This skill provides a complete, automated feature development workflow, managing the entire process from initial exploration to PR submission, unlike executing individual development tasks.
Compared to similar skills
dev side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| dev (this skill) | 0 | 5mo | No flags | Advanced |
| codex | 32 | 2mo | Review | Advanced |
| senior-fullstack | 35 | 7mo | Review | Intermediate |
| codex-claude-cursor-loop | 3 | 9mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by browseros-ai
View all by browseros-ai →You might also like
codex
Lucklyric
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
senior-fullstack
davila7
Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.
codex-claude-cursor-loop
bear2u
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality
consult-codex
centminmod
Compare OpenAI Codex GPT-5.2 and code-searcher responses for comprehensive dual-AI code analysis. Use when you need multiple AI perspectives on code questions.
software-architecture
davila7
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
architect-review
sickn33
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.