skills.rest
rnqhstmd
rnqhstmdCOMMUNITY
Explore all skills by this author →
GitHub

dev

Coordinate multi-agent Claude Code development cycles through PRD, design, implement, review, and commit phases.

Updated Mar 3, 2026
Search Tags:#design#qa#implementation#orchestration#prd#claude-code#trust-ledger
One-click install
npx skills add https://github.com/rnqhstmd/oh-my-bakedpotato --skill dev-rnqhstmd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dev
Source: https://github.com/rnqhstmd/oh-my-bakedpotato/tree/main/.claude/skills/dev
Command: npx skills add https://github.com/rnqhstmd/oh-my-bakedpotato --skill dev-rnqhstmd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Skill automates the end-to-end coordination of PRD → 설계 → 구현 → 리뷰 → 커밋/PR cycles for Claude Code projects through a multi-agent Q&A loop, ensuring phase gates and artifacts are produced consistently.

Core Features & Use Cases

  • Phase orchestration across setup, requirements, design, implement, review, and complete with explicit gates and artifact generation.
  • Domain-context aware prompts and code map accumulation to keep agents aligned with project conventions.
  • State tracking and artifact management (.dev/state.md, .dev/prd.md, .dev/design.md, .dev/codemap.md, .dev/trust-ledger.md, and diff logs) for reproducibility.
  • Parallel QA and security audits with integrated trust ledger synthesis and PR generation.
  • Hotfix support and phase routing to enable rapid, controlled updates.

Quick Start

Describe how to initiate and run the full end-to-end dev cycle for a Claude Code project using the dev skill.

Frequently Asked Questions about dev

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

FAQPage Schema
How do I orchestrate multi-agent Claude Code development cycles from PRD to commit?▼

Multi-agent Claude Code cycles are orchestrated by guiding agents sequentially through PRD, design, implementation, review, and commit phases with explicit gates and artifact generation. The dev skill coordinates this end-to-end loop using Q&A-based decisions and domain context integration.

What is a trust ledger in AI-driven software development?▼

A trust ledger in AI-driven development is a tracked artifact that records parallel QA and security audit results for reproducibility. The trust-ledger.md file synthesizes findings to maintain rigorous state management across development phases.

How do I manage phase gates and state artifacts for Claude Code projects?▼

Phase gates and state artifacts are managed by generating files like state.md, prd.md, design.md, codemap.md, and trust-ledger.md within a .dev directory. This enforces phase progression and enables reproducible asynchronous agent collaboration.

Can I run hotfixes without completing the full PRD to PR cycle?▼

Hotfixes bypass the full cycle by using dedicated phase routing paths for rapid controlled updates. This allows quick patches while still maintaining diff collection and base-branch handling for integration.

Does multi-agent code implementation work with asynchronous agent collaboration?▼

Asynchronous agent collaboration is supported through state tracking and code map accumulation that keeps agents aligned with project conventions. Agents contribute independently while phase gates ensure consistency before merging.

What's the best way to enforce code review and security audits in AI development cycles?▼

Code review and security audits are enforced by running parallel QA checks during the review phase and synthesizing results into a trust ledger. Phase gates prevent progression until audits pass, ensuring rigorous quality control.

Related Skills

Explore More Software Engineering Skills→
jkomorosjkomoros
9

session-startup

Initialize Claude Code sessions by fetching updates, loading workspace config, and starting servers.

Community
Basic
zhaow-dezhaow-de

merge-pr

Merge reviewed GitHub pull requests with a merge commit.

Community
Intermediate
rpelizzarpelizza

pelizzai-domain-modeling

Maps project-specific domain logic and architectural constraints for AI agents.

Community
Intermediate
danieldev24danieldev24

ci-cd-and-automation

Automates CI/CD pipeline setup and quality gates for code verification.

Community
Advanced