skills.rest
camoneart
camoneartCOMMUNITY
Explore all skills by this author →
GitHub

executing-ai-development-workflow

Automate the end-to-end AI development workflow with planning, sub-agent implementation, multi-layer reviews, and PR creation.

5|Updated Aug 23, 2025
Search Tags:#automation#workflow#code review#github#ai development#coderabbit#mlops
One-click install
npx skills add https://github.com/camoneart/claude-code --skill executing-ai-development-workflow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-ai-development-workflow
Source: https://github.com/camoneart/claude-code/tree/main/skills/executing-ai-development-workflow
Command: npx skills add https://github.com/camoneart/claude-code --skill executing-ai-development-workflow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gh, coderabbit-cli, and includes assets (resource) components.

What problem does it solve?

Managing a high-quality, AI-driven development workflow with multiple review stages, automated fixes, and human oversight is complex. This Skill provides a structured 10-step workflow, ensuring robust implementation and quality assurance for new features and refactorings.

Core Features & Use Cases

  • Multi-layer Review: Integrates reviews from multiple Sub-agents, Claude Code /review, and CodeRabbit CLI for comprehensive feedback.
  • Priority-Based Fixes: Automatically addresses Critical/High priority issues, while seeking human confirmation for Medium priority items.
  • Full Documentation: Saves plans and review results to _docs/ for transparency and traceability.
  • Use Case: When implementing a security-critical feature, this Skill ensures a rigorous development process, from detailed planning and Sub-agent-driven implementation to multi-layered security audits and automated fixes, culminating in a well-reviewed Pull Request.

Quick Start

Example: Implement a new user authentication feature

"AI開発ワークフローでユーザー認証機能を実装して"

Claude will initiate the 10-step workflow, starting with planning, then implementation by Sub-agents, multi-layer review, automated fixes, and PR creation.

Frequently Asked Questions about executing-ai-development-workflow

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

FAQPage Schema
How do I automate an AI development workflow from planning through PR creation?▼

This Skill automates end-to-end AI development by executing a 10-step workflow: planning, sub-agent implementation, multi-layer review (via Claude Code, sub-agents, and CodeRabbit), priority-based fixes, and automated PR creation. It reduces manual effort and human error across features, refactors, and security-critical changes.

Can I use GitHub and CodeRabbit together for automated code review in my workflow?▼

Yes. This Skill integrates GitHub (`gh` CLI) and CodeRabbit CLI to enable multi-layer review: CodeRabbit scans for style and logic issues, Claude Code provides architectural feedback, and sub-agents validate implementation. Results are logged and fixes are applied before PR creation.

How does priority-based automated fixing work in code review?▼

The Skill categorizes review findings by priority. Critical and High priority issues are fixed automatically. Medium priority items prompt human confirmation before proceeding. All fixes and decisions are documented in `_docs/` for audit trails and transparency.

What's the best way to implement security-critical features with multiple review stages?▼

Use this Skill's structured workflow: detailed planning captures security requirements, sub-agents implement with constraints, multi-layer review (CodeRabbit, Claude Code, sub-agents) audits implementation, automated fixes address issues, and the final PR includes full documentation and traceability.

Do I need CodeRabbit CLI installed to use this Skill?▼

Yes. This Skill requires both `gh` (GitHub CLI) and `coderabbit-cli` as dependencies. CodeRabbit CLI enables automated code scanning and feedback as part of the multi-layer review process.

Where are planning decisions and review results stored for traceability?▼

All plans, review outputs, and fix decisions are saved to `_docs/` directory. This persistent documentation provides a complete audit trail of the development process and enables transparency across team reviews.

Related Skills

Explore More Software Engineering Skills→
delaanthoniodelaanthonio
1

coderabbit

Review local code changes with the CodeRabbit CLI.

Community
Advanced
yoanbernabeuyoanbernabeu
62

supabase-report

Generate a Markdown security audit report from collected findings.

Community
Advanced
arbazkhan971arbazkhan971
26

docs

Generate and audit API, code, README, and runbook documentation.

Community
Advanced
anthony-spruytanthony-spruyt
3

pr-review-fix-loop

Automate iterative pull request review and fix loops with parallel sub-agents.

Community
Advanced