oh-my-claude-code
Persistent memory, enforced workflows, and self-learning for coding
All Skills in This Repository (28)
Pure Emerald Level Indicatorsdebug
Reproduce software bugs and analyze root causes with knowledge base integration.
research
Perform multi-level web research with fallback to the Tavily Research API.
using-git-worktrees
Create isolated Git worktrees with directory selection and automated setup tests.
mermaid-diagrams
Generate software diagrams from text-based Mermaid syntax.
test-driven-development
Enforce the Test-Driven Development cycle by writing failing tests before implementation code.
systematic-debugging
Enforce a four-phase debugging process prioritizing root cause identification before fixes.
doc-coauthoring
Guides users through a structured multi-stage workflow for co-authoring documents.
dispatching-parallel-agents
Dispatch multiple independent agents to work on distinct problem domains concurrently.
find-skills
Search for agent skills by keyword and provide installation commands.
executing-plans
Execute implementation plans in batches with review checkpoints between steps.
finishing-a-development-branch
Verify test status and present branch integration options for merging or pull requests.
java-architect
Guide enterprise Java application architecture with Spring Boot 3.x and reactive programming.
Frequently Asked Questions
FAQPage SchemaHow to install oh-my-claude-code?โผ
Run `npx skills add KaimingWan/oh-my-claude-code --all -g -y` in your terminal to install all skills in this suite globally.
How to stop AI coding agents from forgetting instructions?โผ
This framework stores corrections and rules in persistent knowledge files and re-injects them into every session, so the agent remembers your preferences across days and projects.
How to enforce tests before code commits?โผ
Built-in hooks hard-block unsafe actions and auto-run lint and tests on every file save, so the agent cannot skip verification or claim success without evidence.
What is the Ralph Loop in oh-my-claude-code?โผ
Ralph Loop is an outer execution loop that keeps spawning fresh agent instances until every plan checklist item passes its verify command, so crashes or full context windows never lose progress.
Does oh-my-claude-code work without coding experience?โผ
Basic terminal use is enough to install it, after which you drive planning, coding, review, and debugging through simple natural-language commands like @plan and @auto.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core