Claude Code Commands

Build AI assistant application with NLU, dialog management, and integrations

Context Restoration: Advanced Semantic Memory Rehydration

Context Restoration: Advanced Semantic Memory Rehydration

Context Save Tool: Intelligent Context Management Specialist

>- Quick RunAPI generation. Use when the user runs /runapi:gen with a prompt and wants to skip broad exploration.

>- Quick image generation. Use when user runs /meigen-ai-design:gen with a prompt. Skips intent assessment, generates directly.

Agent Performance Optimization Workflow

Create LangGraph-based agent with modern patterns

Machine Learning Pipeline - Multi-Agent MLOps Orchestration

>- List and compare RunAPI models by modality, service, or action.

Multi-Agent Optimization Toolkit

Optimize prompts for production with CoT, few-shot, and constitutional AI patterns

This compatibility command keeps /oh-my-claudecode:ask available without loading the full ask skill description in every Claude Code session.

This compatibility command keeps /oh-my-claudecode:autoresearch available without loading the full autoresearch skill description in every Claude Code session.

Prepare OMC context for a manual Claude Code /compact handoff.

This compatibility command keeps /oh-my-claudecode:deep-dive available without loading the full deep-dive skill description in every Claude Code session.

This compatibility command keeps /oh-my-claudecode:deepinit available without loading the full deepinit skill description in every Claude Code session.

This compatibility command keeps /oh-my-claudecode:remember available without loading the full remember skill description in every Claude Code session.

This compatibility command keeps /oh-my-claudecode:sciomc available without loading the full sciomc skill description in every Claude Code session.

This compatibility command keeps /oh-my-claudecode:visual-verdict available without loading the full visual-verdict skill description in every Claude Code session.

Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.

Google Model Armor: Sanitize a user prompt through a Model Armor template.

Google Model Armor: Sanitize a model response through a Model Armor template.

/cs:aeo — Answer Engine Optimization workflow. Audit content for E-E-A-T + structure signals that drive LLM citation (ChatGPT, Perplexity, Claude. Slash command for Claude Code, Codex CLI, Gemini CLI.

/cs:aeo — Answer Engine Optimization workflow. Audit content for E-E-A-T + structure signals that drive LLM citation (ChatGPT, Perplexity, Claude, Gemini, Mistral). Optimize content in 3 modes (conservative/balanced/aggressive). Track which LLMs cite which pages via local ledger. Industry-aware thresholds (8 industries with YMYL calibration). Distinct from SEO — refuses to optimize one at expense of the other.

/cs:caveman — Activate persistent caveman-mode. Ultra-compressed responses with technical substance preserved. Auto-clarity exception for warnings + destructive ops. Stays active until 'stop caveman' / 'normal mode'.

Activate the claude-coach skill — personal Claude power-user coaching for the rest of the conversation.. Slash command for Claude Code, Codex CLI, Gemini CLI.

Compile a goal into a verified agent-harness loop for a domain and drive it to close — /cs:harness <domain> <goal>

/cs:notebooklm — NotebookLM browser automation. Action-routing intake (Q1: read / add source / Studio output / create new) + per-action Q2-Q4 branching. Fire-and-notify for slow Studio ops. Mandatory custom prompts (defaults are mediocre). Requires browser automation environment — fails clean on web.

/cs:notebooklm — NotebookLM browser automation. Action-routing intake (Q1: read / add source / Studio output / create new) + per-action Q2-Q4. Slash command for Claude Code, Codex CLI, Gemini CLI.

/cs:patent <invention> — Patent prior-art + landscape intelligence with mandatory sub-use-case commitment. 6-Q grill-me intake (Q2 picks one of. Slash command for Claude Code, Codex CLI, Gemini CLI.

/cs:research <question> — Default research entry point. Hybrid router: classifies question deterministically and either delegates to specialist. Slash command for Claude Code, Codex CLI, Gemini CLI.

/cs:workflow-build <task-description> — Design and write a deterministic Claude Code workflow (.js). Opens with intake questions, infers-and-proposes a topology when the request is vague, then scaffolds + validates the file. Use when building or running a custom Claude Code workflow.

/cs:workflow-build <task-description> — Design and write a deterministic Claude Code workflow (.js). Opens with intake questions, infers-and-proposes. Slash command for Claude Code, Codex CLI, Gemini CLI.

/cs:write-a-skill <name-or-description> — Author a new agent skill with Matt Pocock's 3-phase workflow (Gather → Draft → Review). Runs 6 review-checklist items + 3 validator tools as a gate. Use when starting a new skill in this repo.

/cs:write-a-skill <name-or-description> — Author a new agent skill with Matt Pocock's 3-phase workflow (Gather → Draft → Review). Runs 6. Slash command for Claude Code, Codex CLI, Gemini CLI.

Ingest a source file from raw/ into the LLM Wiki — read, discuss, write summary page, update cross-references across 5-15 pages, regenerate index. Slash command for Claude Code, Codex CLI, Gemini CLI.

Ingest a source file from raw/ into the LLM Wiki — read, discuss, write summary page, update cross-references across 5-15 pages, regenerate index, append to log. Usage /wiki-ingest <path-to-source>

Ingest a source file from raw/ into the LLM Wiki — read, discuss, write summary page, update cross-references across 5-15 pages, regenerate index, append to log. Usage /wiki-ingest <path-to-source>

Bootstrap a fresh LLM Wiki vault with the three-layer structure, schema files, and starter templates. Usage /wiki-init <path> --topic "<topic>" [--tool all|claude-code|codex|cursor|antigravity]

Bootstrap a fresh LLM Wiki vault with the three-layer structure, schema files, and starter templates. Usage /wiki-init <path> --topic '<topic>'. Slash command for Claude Code, Codex CLI, Gemini CLI.

Bootstrap a fresh LLM Wiki vault with the three-layer structure, schema files, and starter templates. Usage /wiki-init <path> --topic "<topic>" [--tool all|claude-code|codex|cursor|antigravity]