← All skill packs

AI Agent Workflow Collection

Skill pack
19 skills0 selected
itsprogamer974Skills in this pack

Systematically investigate and fix build errors, TypeScript errors, or test failures with minimal diffs.

English

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline,…

English

Diagnose babysitter run health - journal integrity, state cache, effects, locks, sessions, logs, and disk…

English

Frontend and UI/UX development guidance. Provides patterns for responsive design, accessibility, component architecture, state management, and visual consistency. Load this skill when working on any frontend task.

English

Shows available skills, common workflows, and quick reference for the plugin. Use when the user asks for help, what skills are available, or how to do something.

English

Configure HUD display options (layout, presets, display…

English

Setup and configure oh-my-codex using current CLI…

English

Deal-level coaching with diagnosis, stakeholder strategy, and next-step recommendations. Use when user says "help with this deal", "deal is stalled", "how to close", "competitive deal", "multi-thread", "deal coaching", or mentions a specific stuck deal.

English

Initialize a PRD (Product Requirements Document) for structured ralph-loop…

English

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before…

English

Launches an agent team with a task file.

English

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team…

English

QA cycling workflow - test, verify, fix, repeat until goal…

English

Parallel execution engine for high-throughput task…

English

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with $visual-verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

English

Structured visual QA verdict for screenshot-to-reference…

English

DEPRECATED: URL-driven website cloning has moved into $visual-ralph; use $visual-ralph for live-URL visual implementation workflows.

English

Persistent markdown project wiki stored under .omx/wiki with keyword search and lifecycle…

English

Execute beads autonomously within a track.

English

Includes Frontend UI UX, Ralph Init, Visual Ralph, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills19CategorygeneralStars0

What’s included

Build Fix

Systematically investigate and fix build errors, TypeScript errors, or test failures with minimal diffs.

Cancel

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)

Doctor

Diagnose babysitter run health - journal integrity, state cache, effects, locks, sessions, logs, and disk usage

Frontend UI UX

Frontend and UI/UX development guidance. Provides patterns for responsive design, accessibility, component architecture, state management, and visual consistency. Load this skill when working on any frontend task.

Help

Shows available skills, common workflows, and quick reference for the plugin. Use when the user asks for help, what skills are available, or how to do something.

Hud

Configure HUD display options (layout, presets, display elements)

Omx Setup

Setup and configure oh-my-codex using current CLI behavior

Pipeline

Deal-level coaching with diagnosis, stakeholder strategy, and next-step recommendations. Use when user says "help with this deal", "deal is stalled", "how to close", "competitive deal", "multi-thread", "deal coaching", or mentions a specific stuck deal.

Ralph Init

Initialize a PRD (Product Requirements Document) for structured ralph-loop execution

Ralplan

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Team

Launches an agent team with a task file. Usage: /team [task-file2 ...] [--lang en] Example: /team TASKSDD.md Example: /team TASKREVIEW01.md TASKREVIEW02.md

Trace

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Ultraqa

QA cycling workflow - test, verify, fix, repeat until goal met

Ultrawork

Parallel execution engine for high-throughput task completion

Visual Ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with $visual-verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Visual Verdict

Structured visual QA verdict for screenshot-to-reference comparisons

Web Clone

DEPRECATED: URL-driven website cloning has moved into $visual-ralph; use $visual-ralph for live-URL visual implementation workflows.

Wiki

Persistent markdown project wiki stored under .omx/wiki with keyword search and lifecycle capture

Worker

Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestra

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Build Fix skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • License details are not provided in these listings. Check the author’s terms before using the skills.
AI Agent Workflow Collection | Agent Skills Atlas