oh-my-auggie

Manage OMA skills — list, add, remove, search, and edit skills

Socratic deep interview with mathematical ambiguity gating before autonomous execution

Remove AI slop - low-quality, generic, or verbose content. Use for "clean up", "remove fluff", and "make concise".

Consensus planning - agree before executing. Use for "ralplan", "consensus", "pre-execution review".

Setup routing and environment configuration. Use for "setup", "configure", and "get started".

N coordinated agents on shared task list using Claude Code native teams, with git worktree isolation per executor

QA cycling - test, verify, fix, repeat until quality. Use for "quality assurance", "test driven", and "verify thoroughly".

Parallel execution engine for concurrent agent tasks. Use for "run in parallel", "concurrent execution", and "ultrawork".

Load codebase context from knowledge graph instead of scanning raw files

Pattern for presenting numbered choices to the user in Auggie's conversational TUI

Deep exploration and architectural improvement via organic friction detection

Test-Driven Development with vertical slices and tracer bullets

HUD statusline and progress display. Use for "show status", "progress", "HUD", and "statusline".

Extract learned skills from conversations. Use for "learn this", "extract skill", and "capture knowledge".

Skill management and creation. Use for "create skill", "manage skills", "skill info", and "skill help".

2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection

Autonomous improvement loop — tournament selection with benchmark-driven iteration (HIGH COMPLEXITY — deferred)

Root-cause analysis — isolate regressions, interpret stack traces, and resolve build/compilation errors

Parallel document-specialist agents for external web searches and documentation lookup

Memory triage workflow — capture, organize, and retrieve persistent context

Evidence-driven verification discipline — verify claims before acting

Route questions to appropriate intelligence. Use for "ask", "query", and "external knowledge".

Claude-Codex-Gemini tri-model orchestration. Use for "multi-model", "codex", "gemini", and "tri-model routing".

Deep project initialization with hierarchical AGENTS.md. Use for "initialize project", "create agents", "hierarchical setup".

Diagnose and fix common issues. Use for "debug", "fix this", "what's wrong", and "doctor".

Socratic interview and ambiguity scoring. Use for "interview", "question", "socratic", and "ambiguity".

Configure MCP servers and integrations. Use for "setup MCP", "configure server", and "MCP integration".

Create and manage notes during work. Use for "take note", "remember this", and "save for later".

Configure notification delivery. Use for "notify me", "setup notifications", "alert", and "notification config".

Strategic planning and task decomposition. Use for "plan this", "break down", and "roadmap".

Automated release workflow and versioning. Use for "release", "version", "publish", and "changelog".

Research and investigation skills. Use for "research this", "investigate", "find out", and "deep dive".

Scientific analysis and data reasoning. Use for "analyze", "scientific method", "hypothesis", and "research".

Worktree and session management. Use for "new session", "worktree", "tmux", and "session management".

Evidence-driven tracing and execution tracking. Use for "trace this", "execution trace", and "track progress".

Visual QA verdict for screenshots and UI. Use for "verify UI", "visual check", "screenshot verdict", and "visual comparison".

Agentic memory for writers. Use for "remember this", "write from memory", and "context preservation".