Agent Skills by kwt00
Showing 31 vetted skills indexed across 1 GitHub repositories.
cancel
Cancel active OMG modes with session-aware cleanup and forced file clearing.
deep-dive
Orchestrate a two-stage pipeline for causal investigation and requirements crystallization.
trace
Generate and evaluate hypotheses with evidence to diagnose complex issues.
skill
Manage local skills via a command-line interface for oh-my-grok.
ask
Route user queries to Claude, Codex, or Gemini CLI and persist responses as artifacts.
deep-interview
Clarify requirements through Socratic questioning and mathematical ambiguity scoring.
project-session-manager
Create Git worktrees and manage tmux sessions for isolated development environments.
omg-plan
Generate comprehensive work plans through interactive or direct planning methods.
ultraqa
Orchestrate automated QA cycles for testing, verification, and issue resolution.
ultrawork
Execute multiple independent tasks in parallel without state management.
omg-setup
Automate oh-my-grok setup and configuration for local or global settings.
setup
Run installation diagnostics and configure Multi-Channel Protocol server settings.
ralph
Monitor task completion with PRD-driven execution and reviewer verification.
release
Automate Grok plugin releases with version bumps, tests, tags, npm publish, and GitHub releases.
deepinit
Generates hierarchical, AI-readable AGENTS.md documentation for codebase directories.
omg-reference
Catalog OMG agents, tools, workflows, and commit protocols.
learner
Extract and classify learned skills from conversations into expertise and workflow sections.
ai-slop-cleaner
Refactor AI-generated code by simplifying and removing duplication without changing behavior.
team
Manage agent team lifecycles across pipeline stages in Grok Build.
sciomg
Orchestrate parallel scientist agents for multi-stage research workflows.
external-context
Decompose queries into facets and synthesize parallel agent search results.
omg-teams
Manage parallel CLI worker tasks across tmux panes.
visual-verdict
Generate JSON verdicts comparing UI screenshots to reference images via pixel matching and structural analysis.
ralplan
Coordinates Planner, Architect and Critic agents in iterative consensus planning workflows.