AI & LLM Integration for Claude Code

Query the LLM Wiki — reads index.md first, drills into 3-10 relevant pages, synthesizes an answer with inline [[wikilink]] citations, and offers to. Slash command for Claude Code, Codex CLI, Gemini CLI.

Manage Claude Code, Codex, and Cursor sessions for the current project.

Run AI tasks through the low-latency fast client path.

Manage Codex/Claude skills for the current project.

List and discover project tasks from:

Inspect or crawl URLs into compact AI-friendly summaries.

Stops, cancels, or aborts the active skill improvement loop while preserving all changes made to skill files. Use to manually stop, cancel, abort, or kill the iteration process early.

Create a new Agent Skill from scratch with guided workflow

Create a new Agent Skill from scratch with guided workflow

Create a new Agent Skill from scratch with guided workflow

Improve and optimize an existing Agent Skill

Improve and optimize an existing Agent Skill, including content, workflow, and description triggering accuracy

Optimize skill description for better triggering accuracy

Optimize skill description for better triggering accuracy

Test and evaluate Agent Skill performance with benchmarks

Test and evaluate Agent Skill performance with benchmarks

Test and evaluate Agent Skill performance with benchmarks

Fan out multiple Codex implementer agents in parallel, one per subtask or per Linear epic child

Search 1,300+ curated AI image prompts for inspiration

Create a multi-agent group chat with AG2 using configurable speaker selection patterns

Scaffold an A2A-compliant AG2 agent with server wiring, card settings, and skill definitions

Scaffold a new AG2 ConversableAgent with tool functions, system prompt, and LLM config

Create a tool function for an AG2 agent with type annotations, docstrings, and JSON return contracts

Prompt optimizer — rewrite this request into an optimized prompt (ultrathink), then carry it out

Set up the Qwen Video Bridge (API key + dependencies)

Continue a completed/failed/cancelled Codex agent with a new prompt

Create a sequential multi-agent pipeline where each agent processes and passes results to the next

Launch a Codex agent in the background (implementer/reviewer/planner/generic)

Show status of Codex agents — one agent by id, or all

Design a complete multi-agent workflow from a natural language description, selecting the right orchestration pattern

Execute AI/ML task with intelligent automation

> Aggregate crypto news with sentiment analysis and market impact scoring from...

Create a new specialized AI agent with custom tools, handoff rules, and...

Initialize a multi-agent orchestration project with AI SDK v5 agents,...

Test your multi-agent system with a sample task, showing agent handoffs,...

> Set up comprehensive LLM monitoring, cost tracking, and observability

Execute AI/ML task with intelligent automation

Execute AI/ML task with intelligent automation

Execute AI/ML task with intelligent automation

Execute AI/ML task with intelligent automation