发现 Skills

Extract structured data from web pages using CSS selectors. Use when the user asks to scrape a website, extract text or links from a page, or parse HTML content from a URL.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Novel writing, character design, plot design (three-act structure), dialogue generation, worldbuilding, and continuation. Use when you need story-writing capabilities. Triggers on: story writer; random character generation; plot seeds with twists; visualization of character arcs; varied results each run.

Complete toolkit for analyzing database performance, resolving N+1 queries, planning index strategies, and migrating schemas safely. Use this skill when ORM queries are slow, database CPU is spiking, or when designing relationships for high-traffic environments.

Use when defining relationships between Bknd entities. Covers many-to-one, one-to-one, many-to-many, self-referencing relationships, junction tables, options like mappedBy and inversedBy, and UI vs code approaches.

Creates React components and Next.js pages using Relay GraphQL inside admin-next/. Covers fragments, queries, dynamic pages, hooks, and project patterns.

Read and extract content from PDFs, images (OCR), and other document formats. Use when partner shares documents that need to be read.

CoreML diagnostics - model load failures, slow inference, memory issues, compression accuracy loss, compute unit problems, conversion errors.

Create tilemaps using the Tiny Swords asset pack. Supports a 64x64 tile grid, elevation layers, animated water foam, shadow placement, and terrain color variants. Intended for building game maps, level editors, or rendering terrain with the Tiny Swords tileset.

CSS architecture and styling expert with deep knowledge of modern CSS features, responsive design, CSS-in-JS optimization, performance, accessibility, and design systems. Use PROACTIVELY for CSS layout issues, styling architecture, responsive design problems, CSS-in-JS performance, theme implementation, cross-browser compatibility, and design system development. If a specialized expert is better fit, I will recommend switching and stop.

Windows infrastructure expert specializing in Active Directory, DNS, DHCP, GPO, server administration, and enterprise automation via PowerShell.

This skill empowers Claude to perform thorough evaluations of machine learning models, providing detailed performance insights. It leverages the `model-evaluation-suite` plugin to generate a range ...

Automate Google Ads analytics tasks via Rube MCP (Composio): list Google Ads links, run GA4 reports, check compatibility, list properties and accounts. Always search tools first for current schemas.

When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," "breadcrumb schema," "Google rich results," "knowledge panel," "star ratings in search," or "add structured data." Use this whenever someone wants their pages to show enhanced results in Google. For broader SEO issues, see seo-audit. For AI search optimization, see ai-seo.

Compatibility alias skill. Deprecated: use "architecture-designer".

Use for modern Ruby 3.4-era backend, scripting, and application engineering with clear object boundaries, concurrency awareness, and test discipline.

Production email service with templates, queuing, and delivery tracking. Supports transactional emails, marketing campaigns, and webhooks.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Project Guidelines Skill (Example)

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

Create user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.

Web search using Jina Search API. Returns search results with titles, URLs, and descriptions. Use for finding documentation, facts, current information, or any web content. Lightweight, no browser required.