skills.rest
mazenyassergithub
mazenyassergithubCOMMUNITY
Explore all skills by this author →
GitHub

ralph

Route iterative development tasks to specialized agents with architect verification.

6|1|Updated May 9, 2022
Search Tags:#code review#verification#parallel execution#iteration#task completion#architect
One-click install
npx skills add https://github.com/mazenyassergithub/oh-my-claudecode --skill ralph-mazenyassergithub
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ralph
Source: https://github.com/mazenyassergithub/oh-my-claudecode/tree/main/skills/ralph
Command: npx skills add https://github.com/mazenyassergithub/oh-my-claudecode --skill ralph-mazenyassergithub

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of completing complex tasks by iteratively working on them, ensuring each step is verified by an architect before final completion.

Core Features & Use Cases

  • Iterative Development: Breaks down large tasks into manageable steps, allowing for continuous progress.
  • Architectural Verification: Integrates an architect agent to review and approve each stage, ensuring quality and adherence to standards.
  • Parallel and Background Execution: Optimizes workflow by running independent tasks simultaneously and long-running operations in the background.
  • Smart Model Routing: Selects the most appropriate AI model (haiku, sonnet, opus) based on task complexity to optimize token usage.
  • Use Case: Developing a new software feature that requires multiple code changes, testing, and architectural review. Ralph will manage the process, ensuring each code commit is reviewed and approved before proceeding to the next.

Quick Start

Use the ralph skill to continue working on the task, ensuring all previous steps are verified by the architect.

Frequently Asked Questions about ralph

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

FAQPage Schema
How do I automate iterative code review and task completion for complex software features?▼

Iterative code review and task completion can be automated by routing development cycles to specialized agents based on complexity tiers, enforcing parallel execution, and requiring architect verification of test runs and build outputs before final approval.

Can I route software development tasks to different AI models based on complexity?▼

Yes, task completion workflows can route development steps to different AI models, such as haiku, sonnet, or opus, based on task complexity tiers like LOW, MEDIUM, or HIGH to optimize token usage and processing efficiency.

How does architect verification work during parallel code execution?▼

Architect verification during parallel code execution enforces strict background task management, requiring fresh test runs, build outputs, and lsp diagnostics to pass review before the architect approves the current stage and allows final completion.

What is the best way to manage long-running background tasks during iterative development?▼

Managing long-running background tasks during iterative development requires strict parallel execution and background task management, ensuring independent operations run simultaneously while an architect verifies each completed step before proceeding.

Do I need to run fresh tests and lsp diagnostics before architect review?▼

Yes, comprehensive verification steps including fresh test runs, build outputs, and lsp diagnostics are mandatory prerequisites before architect review and the final task completion promise can be issued.

Related Skills

Explore More Software Engineering Skills→
blackwell-systemsblackwell-systems
102

lsp-verify

Verify LSP diagnostics, build, and tests after code edits.

Community
Advanced
lpjhelderlpjhelder

ralph

Iteratively complete development tasks with automated verification and architect sign-off.

Community
Advanced
ulpi-ioulpi-io
2

run-parallel-agents-feature-build

Orchestrate multiple specialized agents to execute independent features concurrently.

Official
Intermediate
Kling0012Kling0012
1

Verification & Quality Assurance

Automate verification checks with truth scoring and rollback for CI/CD pipelines.

Community
Advanced