r3dlex

Diagnose and fix build/CI failures automatically

Concurrent code generation via multi-model picker

UI/UX design and frontend component generation

OMP self-improvement — analyse own skills/agents and propose improvements

Visual diff/screenshot comparison verdict

Clone and adapt a web page/design to the codebase

Trace→deep-interview pipeline for deep investigation

Deep project initialization — full codebase onboarding

Produce a structured handoff document summarizing completed work and next steps.

Produce a phased execution plan aligned to the oh-my-gemini roadmap gates.

Perform a structured code review of recent changes or a specific scope.

Orchestrate parallel tmux workers for a multi-agent team task.

Verify that acceptance criteria are met and work is complete.

Run a focused Gemini advisor prompt and save the reusable result artifact. Use when the user wants a quick advisor-style answer without a full workflow.

Drive a task from clarified objective through implementation and verification. Use when the user wants end-to-end autonomous execution.

Stop active workflow state safely and preserve resumable context. Use when the user wants to stop, abort, or checkpoint ongoing work.

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".

Bootstrap AI-ready repo governance, traceability, cascade, catalog audits, validation. Deprecated compatibility aliases: init-ai-repo, ai-sdlc-init. Use when setting up AI SDLC.

Deprecated compatibility alias for ai-catapult-init. Use only when legacy prompts invoke "ai-sdlc-init"; otherwise use "ai-catapult-init".

Ship a northstar handoff's goals in an ai-catapult-init repo — ultragoal one-PR-per-goal, deterministic engine-pick, peer review, CI gate, fail-closed merge, cascade closure.

Scaffold a structurally valid eval triplet for a target skill under .ai/evals/. CI checks structure only; the LM-judge runs out-of-band, never in CI.

Deprecated compatibility alias for ai-catapult-init. Use only when legacy prompts invoke "init-ai-repo"; otherwise use "ai-catapult-init".

Intake intent into a tracked, sliced plan in an ai-catapult-init repo — deep-interview + skippable grill-me, always raise an issue, ralplan, write the A→B handoff.

Configure AGENTS/CLAUDE and docs/agents for tracker, triage labels, and domain docs. Use before issue, PRD, triage, TDD, or diagnosis skills.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

LLM knowledge graph with persistent wiki compilation