全部能力

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural…

Transform comprehensive written content into purposeful spoken guidance. Use when adapting for speech, converting to spoken format, optimizing for listening,…

Diagnose and calibrate tonal delivery for tabletop RPG sessions. Use when narration feels flat, tone shifts jarringly, descriptions overwhelm play, or energy…

Integrate Resend email service via MCP protocol for AI agents to send emails with Claude Desktop, GitHub Copilot, and Cursor. Set up transactional and…

Use this skill whenever users want to build, inspect, debug, automate, or publish workflows in Agentforce Grid (AI Workbench) using Salesforce plus the Grid…

Your external brain and memory. ALWAYS invoke this tool to search memory whenever you are unsure about the user's intent, past context, or if you don't know…

Expert children's book writer creating delightful, engaging books for ages 2-9. Specializes in rhyming books, stories, songs with proper values, educational…

当实现完成、所有测试通过、需要决定如何集成工作时使用——通过提供合并、PR 或清理等结构化选项来引导开发工作的收尾

eve-project-bootstrap — an installable skill for AI agents, published by incept5/eve-skillpacks.

Next.js 16 Cache Components guidance — PPR, use cache directive, cacheLife, cacheTag, updateTag, and migration from unstable_cache. Use when implementing…

Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore…

Agent skill that faithfully reproduces Hummingbot CLI commands (connect, balance, create, start, stop, status, history) via Hummingbot API. V1 focuses on core…

no-use-effect — 一款可安装的 AI 智能体技能，由 alejandrobailo/no-use-effect 发布。

Troubleshoots failing applications by discovering and analyzing CloudWatch log groups to identify error patterns, root causes, and actionable solutions. Use…

Vercel Marketplace expert guidance — discovering, installing, and building integrations, auto-provisioned environment variables, unified billing, and the…

Instagram Agent 允许用户从 Instagram 提取数据，包括帖子、个人主页、话题标签和评论，以突破手动研究的限制。…

Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via amplihack.memory.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用

跨运行时 Agent Teams 编排手册，适用于 Claude Code、Codex、OpenClaw 和 Cursor。当用户要求"create agent teams"、"use agent swarm"、"setup multi-agent collaboration"、"orchestrate agents"、"coordinate parallel agents"、"organize team collaboration"、"build agent teams"、"implement swarm orchestration"、"setup multi-agent system"、"coordinate agent collaboration"，或需要关于自适应团队组建、质量门禁、技能发现、任务分发、团队协调策略或 Agent Teams 最佳实践的指导时，应使用此技能。或者当用户说"多agent"、"agent协作"、"agent编排"、"并行agent"、"分工协作"、"拉团队"、"拉个团队"、"多代理协作"、"swarm编排"、"agent团队"时也应使用此技能。 注意："swarm/蜂群"是通用行业术语；Claude Code 的官方概念为"Agent Teams"；Codex、OpenClaw 和 Cursor 应将此手册映射到其原生或宿主提供的 agent 能力，不得删除任何工作流阶段。

Build and publish npm packages using Bun as the primary toolchain with npm-compatible output. Use when the user wants to create a new npm library, set up a…