llm-coding-workflow
CommunityAI-guided coding workflow for reliable results.
System Documentation
What problem does it solve?
This Skill provides a structured, AI-assisted software engineering workflow inspired by Addy Osmani's methodology. It helps teams plan, chunk work, manage context, switch models strategically, maintain human oversight, and commit frequently to avoid wasted cycles and low-quality output.
Core Features & Use Cases
- Structured Planning: Rapid, waterfall-style planning before implementation.
- Chunked Execution: Small tasks with quick feedback loops.
- Context Management: Systematic provision of relevant context to the AI.
- Model Selection: Strategic switching based on task needs.
- Human Oversight: Review-first approach to AI-generated code.
- Granular Commits: Frequent save points and easy rollbacks.
- Continuous Learning: Learnings captured to amplify future work.
Use Case: Deploy AI as a productive partner to plan, implement, and review features, fixes, or refactors with human oversight.
Quick Start
Plan a feature with AI: /llm-workflow plan "Implement user authentication with JWT"
Decompose tasks and implement in chunks: /llm-workflow decompose "Build authentication system" /llm-workflow implement --chunk-size small
Review and commit changes: /llm-workflow review --commit
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: llm-coding-workflow Download link: https://github.com/ericporres/llm-coding-workflow-skill/archive/main.zip#llm-coding-workflow Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.