con un clic
oh-my-gemini
oh-my-gemini contiene 35 skills recopiladas de chanhee-kang, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
Automatically deploy oh-my-gemini to npm and GitHub
Full autonomous execution from idea to working code
Fix build and TypeScript errors with minimal changes
Cancel any active OMC mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline)
Run a comprehensive code review
Deep executor mode for complex goal-oriented tasks
Deep codebase initialization with hierarchical AGENTS.md documentation
Diagnose and fix oh-my-gemini installation issues
Token-efficient model routing modifier
Guide on using oh-my-gemini plugin
Configure HUD display options (layout, presets, display elements)
Analyze your OMC usage patterns and get personalized recommendations
Extract a learned skill from the current conversation
Set up and manage local skills for automatic matching and invocation
Configure popular MCP servers for enhanced agent capabilities
Save notes to notepad.md for compaction resilience
Setup and configure oh-my-gemini (the ONLY command you need to learn)
Activate multi-agent orchestration mode
Chain agents together in sequential or branching workflows with data passing
Strategic planning with optional interview workflow
Manage isolated dev environments with git worktrees and tmux sessions
Initialize a PRD (Product Requirements Document) for structured ralph-loop execution
Self-referential loop until task completion with architect verification
Iterative planning with Planner, Architect, and Critic until consensus
Automated release workflow for oh-my-gemini
Orchestrate parallel scientist agents for comprehensive research with AUTO mode
Run a comprehensive security review on code
Automatically improve and fix bugs in the oh-my-gemini project itself
Manage local skills - list, add, remove, search, edit
N coordinated agents on shared task list with SQLite-based atomic claiming
Test-Driven Development enforcement skill - write tests first, always
Parallel autopilot with file ownership partitioning
QA cycling workflow - test, verify, fix, repeat until goal met
Parallel execution engine for high-throughput task completion
Agentic memory system for writers - track characters, relationships, scenes, and themes