multi-llm-advisor
Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently displays all LLM calls.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Agents & models
25,188 results
telnyx-ai-assistants-go
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
claude-agent-sdk-context-management
Use when managing agent context, memory, and conversation state in Claude AI agents using the Agent SDK.
azure-drawio-mcp-diagramming
Create and edit architecture diagrams using Draw.io MCP (`drawio/create_diagram`) with reliable Azure icon rendering guidance and troubleshooting.…
agent-delegation
Fixed rules for handing work to subagents or external coding CLIs, usable from any host (Claude Code, Codex, Antigravity, OpenCode). This skill MUST be loaded…
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
meta-skill-creator
Use this meta-skill instead of answering directly only when the current user explicitly asks to create, compose, synthesize, or propose a new meta-skill that…
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an…
voice-clone-lab
Create and register cloned voices for later TTS only with the speaker's explicit consent. Use for voice clone, clone voice, 克隆音色 (clone a voice timbre), 复刻声音 (replicate a voice), or…
gsd planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification
gimble
Use Gimble to run agent workflows, author workflows in Go, or build and release the Gimble application. Routes to the appropriate sub-skill.
claude-reflection
Self-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences
project-real-estate-agent
Use for London residential property due diligence and investment second opinions (Zone 1-3 focus): mortgage comparison, conveyancing guidance,…
github-tools-agents
Give an AI agent GitHub access via @github-tools/sdk. Mount as an eve extension, or use with the AI SDK, Vercel Workflow, and Chat SDK. Covers tools, presets,…
ai-cost-optimizer
Master of LLM Economic Orchestration, specialized in Google GenAI (Gemini 3), Context Caching, and High-Fidelity Token Engineering.
agents-controller
AI development process master dispatcher, responsible for coordinating collaboration among the product manager, architect, UI designer, and full-stack development engineer skill packages. Handles process scheduling, state management, instruction routing, and quality control.
trade-fundamental
Fundamental Analysis Agent — valuation, growth, profitability, balance sheet, competitive moat, and management quality analysis with Fundamental Score (0-100)
dispatching parallel agents
Use multiple Claude agents to investigate and fix independent problems concurrently
bedrock-agentcore-policy
Amazon Bedrock AgentCore Policy for defining agent boundaries using natural language and Cedar. Deterministic policy enforcement at the Gateway level. Use when…
computer-use-linux
Linux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input…
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate…
godogen
Drive Godogen (htdt/godogen), the MIT-licensed publish-time generator that turns a game description into an autonomous Claude Code or Codex build for Godot 4…
continue-autonomously
Use whenever the user wants unattended progress over confirmation: "continue autonomously", "keep going", "don't stop to ask me", "work independently", "on…