AI Skills Registry

dontbesilent 好问题生成器。把模糊问题改写成 Agent 可推理、可批评、可验证的问题说明书，并判断它能被自动化解决到什么程度。 触发方式：/dbs-good-question、/好问题、/问题说明书、/Agent可解性、「这个问题能不能自动化解决」「帮我把问题说清楚

Create 600x600 Instagram-style card news series automatically with optional background images. User provides topic, colors, and optional ima

Create a custom agent (.agent.md) for a specific job.

Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Ge

AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent

Manages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (u

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Au

When the user wants to configure, audit, or optimize robots.txt. Also use when the user mentions "robots.txt," "crawler rules," "block crawl

Migrate a Java application from the classic Elastic APM Java agent to the EDOT Java agent. Use when switching from elastic-apm-agent.jar to

Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent

PUA Loop alias for Codex. Codex subcommand mapping for Claude Code /pua:loop style usage; invoke with $pua-loop.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or wh

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type sa

This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from te

Create and maintain GitHub Agentic Workflows (gh-aw) for Prowler. Trigger: When creating agentic workflows, modifying gh-aw frontmatter, con

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

把一篇文章或口播稿，做成"看起来像视频"的点击驱动 16:9 网页演示，可选合成口播音频。流程：原始文章 → **一次产出**口播稿 + outline 开发计划 → 用户**一次对齐** 5 件事（稿子 / outline / 主题 / 素材 / 开发模式）→ 网页开发（逐章

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prom

多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。

Guides users through creating effective Agent Skills. Use when you want to create, write, or author a new skill, or asks about skill structu

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configur

Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and n