Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Fan-out tasks to multiple AI providers or agent instances in parallel, then consolidate the results into a single high-quality output. Use for parallel planning, multi-implementation code generation, and debug consensus across Claude subagents and external CLI providers.
Choose RouterBase model IDs and routing strategies for chat, image, video, audio, and embeddings workloads. Use when comparing providers, selecting GPT, Claude, Gemini, image, video, or audio models on RouterBase, designing fallback paths, checking pricing or availability, planning cost/latency/quality tradeoffs, querying the RouterBase Models API, or documenting how an app should route model requests through RouterBase.
Publish, submit, and verify local skills across public skill marketplaces, directories, and registries. Use when an agent needs to take a skill folder or skill repository, confirm current submission paths, prepare cross-market metadata, run verified live adapters, or generate manual submission bundles for markets such as AgentSkill.sh, Skillstore, SkillNet, agent-skills.md, SkillsMD, SkillHub, SkillHQ, and related registries.
Execute plans using fresh subagent per task with code review between tasks. Use for high-quality iterative implementation.
ERC-8004 Trustless Agents for on-chain agent identity and reputation. Resolve an agent by ID from the Identity Registry ERC-721 to its owner and AgentCard, list canonical registry addresses, and generate a specification-compliant registration-v1 agent card with x402 support and trust models. Custody-free read and scaffolding workflows. Use for ERC-8004, trustless agents, agent identity or registry, AgentCard, agent reputation, on-chain agents, A2A, agent discovery, agent cards, and 8004.
Generate AI chat completions using GPT-4o through the verging.ai proxy API with streaming (SSE) and non-streaming response support.
This skill is a practical, 'use-it-while-debugging' reference for getting a LiveKit + Letta voice agent working reliably.
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
Creates Claude Code hooks for automation and workflow customization. Guides through hook events, configuration, and script creation. Use when user wants to create a hook, automate Claude Code, or asks about hook events.
A guide to creating Claude Code Skills.