claude-commands

/4layer - Four-Layer Minimal Repro Testing Protocol

Command system documentation & header requirements

Enhanced Command Aliases

Enhanced /learn Command - Implementation Summary

Enhanced command wrappers provide memory pattern integration for improved execution quality and consistency.

Claude Commands Directory

Claude Commands - Command Library Overview

Claude sometimes responds "I don't recognize command X" without verifying if the command actually exists in `.claude/commands/`.

The orchestrator MUST generate responses.json in this exact format:

**Execute these steps immediately. Use TodoWrite to track multi-phase workflows.**

/adde2e - Add or Update End2End Tests for New Features

Get a status report of all PRs agento is handling — merged vs not merged, green status breakdown

Alias for /agento_report — Get a status report of all PRs agento is handling

Antigravity computer use via Peekaboo — interact with the Antigravity macOS app. Also used by /eloop to babysit the Antigravity IDE and self-improve this skill.

The `/copilot` slash command workflow makes multiple GitHub API calls per run. As of this change, the workflow has been audited to remove unnecessary API calls, with a focus on preventing use of automatic conversation-thread resolution APIs.

/arch Command (Alias)

Architecture Review Command

/auto Command

Automation Audit Skill - Analyze PR automation job runs

Automation Package Publishing Command - Publish both orchestration and automation packages to PyPI

Run all crontab automation jobs and verify they worked

/automation - GitHub PR Automation System Integration

Diagnose WHY the jleechanclaw + AO system is NOT autonomously driving PRs to 6 green and merged. The system is supposed to do this without human intervention — if it isn't, something is broken.

/batchcopilot Command - Batch PR Processing

Branch Cleanup Command

/benchg-ts - TypeScript Migration Benchmark: Genesis vs Ralph

/benchg - Genesis vs Ralph Orchestrator Benchmark

Unified browser automation - intelligently uses Playwright or Superpowers Chrome

Generate large amounts of code using Cerebras (alias for /cerebras)

Cancel active Ralph Wiggum loop

Generate large amounts of code using Cerebras (alias for /cerebras)

Generate large amounts of code using Cerebras

Context Checkpoint Command

Claude-MD-Analyze Command - Comprehensive Directory Analysis for CLAUDE.md Deployment

Claude-MD-Validate Command - Comprehensive CLAUDE.md Quality Validation Framework

/claw - Send a task to ao spawn (parallel tmux) for coding, gateway HTTP for read-only

Clone PR, add TDD tests, and push to correct remote branch

Post "@coderabbitai all good?" comment on the PR associated with the current branch

Combinations Command

Combo Help Command

/commentcheck Command

/commentfetch Command

Comment Reply Command (Alias)

/commentreply Command

Context Estimation Command (Alias)

/cons Command (Alias)

description: /consensus Command - Multi-Agent Consensus Review

Context Usage Estimation Command

/conv - Convergence Alias Command

/converge - Iterative Goal Achievement Command

/copilot-expanded - Complete Self-Contained PR Analysis & Enhancement

/copilot-lite - Streamlined PR Processing

/copilot - Orchestrated PR Comment Processing

/copilotc - Convergent Copilot (Autonomous GitHub Comment Resolution)

/copilotl - Copilot Lite Alias

GitHub Copilot Super Command

Coverage Command

Alias for /coderabbit — Post "@coderabbitai all good?" on the current branch's PR (only after pushing fixes)

Debug Protocol Command

Debug Command

debugp - Alias for Debug Protocol

/deploy

/design - Product & Engineering Design Documentation

e

12-hour autonomous evolution loop — observe, measure, diagnose, fix, repeat every 10min. Drives zero-touch rate up by finding friction and dispatching fixes.

Alias for /evidence_review — Review evidence artifacts using the evidence-reviewer agent (codex dispatch, claude fallback)

Run this before pushing a PR to catch Evidence Gate failures locally instead of waiting for CI.

Review evidence artifacts for a claim using the evidence-reviewer agent. Dispatches to codex via orchestration library, falls back to inline claude analysis.

Autonomous evolution loop — observe AO ecosystem, measure zero-touch rate, diagnose friction, dispatch fixes. Adaptive — skips phases when system is healthy.

Execute Command - Plan-Approve-Execute Composition

/experiment - Triple-Blind AI Testing Protocol

/exportcommands - Export Claude Commands to Reference Repository

Fake Code Detection Command

Fake3 Command - Branch-Focused Iterative Fake Code Detection and Fixing

Fake Code Detection Command - /fakel (Light)

Guided feature development with systematic codebase understanding and architecture focus

/fixpr Command - Intelligent PR Fix Analysis

/fixprc - Fix PR Comments (Autonomous PR Comment Resolution)

/gen Command (Alias)

/gene - Genesis Execution (Auto-Execute)

---

/ghfixtests

/goal - Goal Definition and Validation Command

Alias for /gstatus command

Comprehensive PR status with GitHub MCP orchestration

Generate comprehensive, general-purpose test suites for any system component using systematic test design methodology

Guidelines Command - Centralized Mistake Prevention Consultation

/handoff Command

Analyze failures and fix the harness (instructions, skills, tests, CI) rather than just the symptom

Header Command

/headless - Enhanced Planning + Headless Development

/history Command

Alias for /investigatedice - Investigate dice integrity warnings for a campaign

Alias for /innovate - Single smartest innovative addition to the current plan

/innovate - Single smartest innovative addition to the current plan

Integration Command

Investigate dice integrity warnings for a campaign. Queries GCP logs, Firestore story entries, and game_state to diagnose dice fabrication issues.

/learn Command

List Commands Command

/localexportcommands - Export Project Claude Configuration Locally

/localserver

/memory Command - Native Claude Memory Interaction

Milestones Command

Moltbook Social Network Integration

/newbranch or /nb - Create new branch from latest main

/newbranch or /nb - Create new branch from latest main

Assess current context, update beads issues and roadmap docs to reflect recent work. Dispatches parallel subagents for speed.

Optimize Command

/orch - Alias for /orchestrate

/orchc - Alias for /orchconverge

/orchconverge - Autonomous Convergence via Orchestration

Orchestrate Command

1. **Register MCP Mail Agents**

The Pair Protocol uses MCP mail for asynchronous agent-to-agent coordination while maintaining human-in-the-loop oversight at critical decision points.

Launch ralph-pair (coder + deterministic verifier)

Legacy Python pair executor (pair_execute.py)

Launch LangGraph-based pair programming v2 with left/right contract gating

Parallel Tasks vs Subagents Reference Guide

Perp Command - Comprehensive Multi-Search

Plan Command - Execute with Approval

Plan-Execute Command - Execute with Approval

Playwright browser automation testing for Your Project

/polish - Iterative PR Green Loop (up to N iterations)

Capture visual evidence that a PR change works and attach it to the PR body. Inspired by Ryan's OpenAI Codex talk: "I'm expecting they did the job and that they can prove to me that the code is worth merging."

PR Command - Complete Development Lifecycle

/pres

/presentation

Principal Engineer Command

Principal Product Manager Command

/processmsgs - Intelligent Agent Message Processing with MCP Agent Mail

/puppeteer Command

Push Command

Push Lite Command (pushl alias)

Push Lite Command - Enhanced Reliability with LLM Intelligence

Legacy alias for Cerebras code generation (redirects to /cerebras)

Roadmap Command (Alias)

Start Ralph Wiggum loop in current session

Run Ralph automation portably across repositories with workspace targeting

ralph_benchmark_parallel

Execute Ralph orchestration system for autonomous task execution

ralph_iteration

ralph_pair_iteration

Red-Green Debug & Fix Command

/replicate

View Current Requirement

End Requirements Gathering

List All Requirements

Requirements Gathering Reminder

Start Requirements Gathering

Check Requirements Status

Research Command - Academic and Technical Research

Enhanced Code Review Command

Deep Review Alias

/reviewdeep Command

Enhanced Code Review Alias

Review Status Command - Check PR CI and Review Comments

/reviewsuper Command - Critical Architecture Reviewer

Update CLAUDE.md with learnings from this session

Red-Code-Green Debug Command (Alias)

Roadmap Command

Orchestration roadmap command — captures session ideas, checks upstream repos for existing functionality, and creates/updates roadmap/ docs + beads

Alias for /roadmap_orch — captures session ideas, checks upstream repos, updates roadmap/ docs + beads

/runlocal

Save evidence to /tmp structure

Repository Scaffolding Command

Scratchpad Command

Get multi-model second opinion on design, code review, or bugs

Get multi-model second opinion (alias for /second_opinion)

Alias for /simulate - Predict next user prompt

Async A/B simulation - runs predictions via claude -p subprocess

Predict next user prompt using $USER simulation

/slide

Run MCP smoke tests against preview server or local instance

Clarify Command - Specification Clarification Protocol

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Execute the implementation planning workflow using the plan template to generate design artifacts.

Spec Command - GitHub Spec Kit Integration

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

Split PR Command

Show comprehensive PR status including recent files, CI, merge conflicts, and GitHub state

**Purpose**: Display branch and PR status information using universal composition

/suba Alias - Dual Consultant Validation Sweep

/subagentvalidate Command - Dual Consultant Validation Sweep

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation.

Execute plan in batches with review checkpoints

Create detailed implementation plan with bite-sized tasks

/sync - Synchronize Local Branch with PR

Matrix-Enhanced Test-Driven Development Command

Create a Claude-native agent team with opus orchestrating sonnet/haiku workers

Create a minimax-only agent team with haiku for work

Enhanced Test Command

/teste - End2End Tests (Mock Mode)

/tester - End2End Tests (Real Mode)

/testerc - End2End Tests (Real Mode + Capture)

HTTP Tests (Mock) Command

HTTP Tests (FULL) Command

Integration Test Command

/testllm - LLM-Driven Test Execution Command

/testmcp - MCP Test Suite Execution Command

Test Server Command

Browser Tests (Mock) Command

Intelligent Regression Testing with Playwright MCP

Think Command

Think Ultra Command (Alias)

/timeout Command - Performance Optimizer

Query Firebase for the longest (most entries) campaigns within a date range.

Total Failure Protocol

Update `~/.claude/CLAUDE.md`, `~/.codex/AGENTS.md`, `~/.gemini/GEMINI.md`, and `~/.cursor/rules/` with a new rule or preference stated in the argument.

/usage Command

When this command is invoked, scan the specified test file (or all test files with "e2e" in the name) and check each against the 5 mandatory E2E criteria. Report violations honestly.

Send daily/weekly Your Project usage report email to $USER@gmail.com

Reference documentation for understanding and using the custom agent system

Design, test, and optimize AI prompts for NPCs, world generation, quest creation, and narrative elements. Use for any Gemini API prompt engineering.

Specialized agent for large-scale code generation using Cerebras infrastructure. Expert in creating complete implementations, complex algorithms, and multi-file project structures with high quality and performance.

Use this agent when the user explicitly requests Cerebras-assisted code generation, rapid scaffolding, or wants to leverage the `/cerebras` slash command for large or complex implementation tasks. The agent orchestrates Cerebras Model Studio via the official slash-command workflow for ultra-fast code production, architectural drafting, and automated documentation.

Claude CLI-powered pair programming coder. Delegates implementation to Claude CLI (claude --dangerously-skip-permissions) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["claude"]

Claude CLI-powered pair programming verifier. Delegates verification to Claude CLI (claude --dangerously-skip-permissions) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["claude"]

Specialist consultant for consolidating duplicate logic, reusing existing modules, and reducing codebase fragmentation. Defaults to Claude Code CLI, with fallbacks to Codex CLI and Cursor CLI if unavailable.

Specialized AI agent for comprehensive code analysis, security review, and quality assessment. Expert in multi-language code review with focus on bugs, security vulnerabilities, performance issues, and best practices.

Use this agent when the user asks to consult with Codex for code analysis, explanation, or insights. This agent is particularly useful when you need deep code understanding, architectural analysis, or when the user explicitly mentions wanting to 'consult with codex' or 'ask codex about' specific files or code patterns.

Codex CLI-powered pair programming coder. Delegates implementation to Codex CLI (codex exec --yolo) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["codex"]

Codex CLI-powered pair programming verifier. Delegates verification to Codex CLI (codex exec --yolo --skip-git-repo-check) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["codex"]

Specialized PR issue resolution agent focusing exclusively on implementing code fixes for GitHub PR blockers. Expert in file justification protocol, security fixes, runtime errors, test failures, and merge conflicts with actual code implementation.

Independent verification of /copilot run quality. Audits fix accuracy, scope discipline, tracking honesty, and KPI compliance without execution context contamination.

Use this agent when you need a Fresh Data Analysis Specialist who can tap into real-time context, surface emerging trends, and translate the latest signals into actionable guidance. The agent mirrors Cursor's fast-moving perspective by grounding every consultation in the freshest available data.

Cursor CLI-powered pair programming coder. Delegates implementation to Cursor Agent CLI (cursor-agent -f) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["cursor"]

Cursor CLI-powered pair programming verifier. Delegates verification to Cursor Agent CLI (cursor-agent -f) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["cursor"]

Specialized agent for comprehensive technical documentation generation. Expert in creating API docs, user guides, architectural documentation, and code documentation with professional quality and completeness.

Skeptical auditor of evidence bundles against .claude/skills/evidence-standards.md. Detects circular citations, empty artifacts, statistical weakness, unverified claims, and structural defects. Zero tolerance for assertions without raw proof. Use proactively after any evidence bundle is created or updated.

Manage Firebase Firestore operations, authentication, security rules, and real-time data synchronization. Use for any database or auth tasks.

Develop and refine D&D 5e game mechanics, combat systems, character progression, and rule implementations. Use PROACTIVELY for any game logic changes.

Use this agent when the user explicitly asks to consult Gemini, seek external AI guidance, or needs a second opinion on technical decisions.

Gemini CLI-powered pair programming coder. Delegates implementation to Gemini CLI (gemini -m ${GEMINI_MODEL:-gemini-3-flash-preview} --yolo) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["gemini"]

Gemini CLI-powered pair programming verifier. Delegates verification to Gemini CLI (gemini -m ${GEMINI_MODEL:-gemini-3-flash-preview} --yolo) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["gemini"]

Independent goal processing agent for /converge context optimization. Separates goal definition from main workflow to reduce context consumption.

Use this agent when you need a contrarian, unconventional analysis perspective that challenges assumptions and provides direct, practical insights. This agent simulates Grok-style analysis using available AI consultation tools.

Generic agent for medium and long-running tasks (>5 minutes). Executes independently, writes detailed results to files, and provides concise summaries to minimize context usage.

MiniMax-powered pair programming coder. Delegates implementation to Claude CLI with MiniMax API backend (ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic). Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["minimax"]

MiniMax-powered pair programming verifier. Delegates verification to Claude CLI with MiniMax API backend (ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic). Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["minimax"]

Pair programming coder agent for implementation tasks within a Claude Teams session. Works with a pair-verifier teammate: implements code using TDD methodology, then signals completion for verification. Use when orchestrating dual-agent pair programming via Claude Teams (as alternative to pair_execute.py tmux-based orchestration).

Pair programming verifier agent for code review and test validation within a Claude Teams session. Works with a pair-coder teammate: waits for implementation completion signal, then verifies code quality, test coverage, and correctness.

Specialized agent for comprehensive performance analysis and optimization. Expert in algorithmic complexity, database optimization, caching strategies, and system-level performance tuning across all major platforms.

Methodical test specification execution with evidence collection. Expert in browser automation, real authentication testing, and structured evidence packages.

Independent validation of test execution results against original specifications. Critical auditor for evidence analysis and requirement verification.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

Use Claude Code to run computer-use style UI automation loops with screenshot → decide → act cycles, safety guardrails, and step-bounded execution. Trigger when the user asks to make agents do Claude computer-use behavior, desktop/browser UI control, click/type/scroll automation, or iterative visual task execution in Claude Code.

Run or maintain the cmux approval worker that scans cmux terminal surfaces for approval dialogs, classifies them with `codex exec`, and sends the matching approval key. Use when testing or operating the launchd-based auto-approver, debugging missed prompts, moving the worker, or tuning candidate detection and approval heuristics.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Generate comprehensive, systematic test suites for any system component using a structured test design methodology. Creates tests that catch real bugs through state lifecycle, integration, and consistency testing.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

Use this skill when writing code, implementing features, refactoring, planning architecture, designing systems, reviewing code, or debugging. This skill transforms junior-level code into senior-engineer quality software through SOLID principles, TDD, clean code practices, and professional software design.

Set up and use the Symphony launchd daemon in repositories that include orchestration/symphony_overlay/daemon.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.