agent

safety-scan — an installable skill for AI agents, published by ruvnet/ruflo.

memory-search — an installable skill for AI agents, published by ruvnet/ruflo.

Guides the agent through upgrading a Capacitor plugin to a newer major version. Supports upgrades from Capacitor 4 through 8, including multi-version jumps.…

session-persist — an installable skill for AI agents, published by ruvnet/ruflo.

Explain code functionality in detail.

design-doc — an installable skill for AI agents, published by diskd-ai/design-doc.

Initialize warehouse schema discovery. Generates .astro/warehouse.md with all table metadata for instant lookups. Run once per project, refresh when schema…

goal-plan — an installable skill for AI agents, published by ruvnet/ruflo.

Alibaba Cloud RDS Copilot intelligent operations assistant skill. Used for RDS-related intelligent Q&A, SQL optimization, instance operations, and troubleshooting. Calls RdsAi OpenAPI through Alibaba Cloud CLI to get real-time RDS Copilot responses. Triggers: "RDS Copilot", "RDS Assistant", "SQL optimization", "RDS troubleshooting", "RDS operations", "database diagnosis"

silicon-paddle-ocr — 一项适用于 AI 智能体的可安装技能，由 aotenjou/silicon-paddleocr 发布。

面向 AI 智能体的浏览器自动化 CLI。当用户需要与网站交互时使用，包括页面导航、填写表单、点击按钮、截图……

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up…

Command-line interface for Gimp - A stateful command-line interface for image editing, built on Pillow. Designed for AI agents and pow...

browser-scrape — an installable skill for AI agents, published by ruvnet/ruflo.

Core gameplay mechanics implementation, system interactions, feedback loops, and iterative balance refinement for engaging player experiences.

neural-train — an installable skill for AI agents, published by ruvnet/ruflo.

基于 opencli 命令的智能搜索路由器。当用户想要搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill

Use when iterative review-fix cycles are needed on a plan or implementation — bounded loop with severity gating, automatic fixes, and finding disposition.

Create and adapt Dynamic Agentic Architecture agents that learn and evolve

Extract actionable Linear tickets from ambiguous input — Slack conversations, call transcripts, screenshots, meeting notes, or any unstructured material. Proposes tickets in a scratchpad file for user review, then creates them in Linear on approval. Use when the user wants to turn conversations, transcripts, screenshots, or notes into Linear tickets. Also use when user says "create tickets from this", "send to linear", "make issues from this call/chat", or provides raw material and asks for tickets.