发现 Skills

Connects a .NET Infrastructure layer to PostgreSQL using EF Core and Npgsql. Use when configuring EF Core with a PostgreSQL provider, setting up Npgsql, mapping domain models to PostgreSQL conventions, running migrations against PostgreSQL, or writing PostgreSQL-specific integration tests. Use alongside dotnet-webapi and db-postgres — this skill bridges the two.

Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Elasticsearch integration and sync patterns.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task.

Injection vulnerability specialist — SQL, command, LDAP, XPath, NoSQL, ORM, template injection. Analyst role.

Dependency and supply-chain security specialist — known CVEs, typosquatting, lockfile integrity, suspicious install scripts. Analyst role.

Perform deep, concurrent web research using the Perplexity Search API.

PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.

Run Python code on cloud GPUs using the Modal serverless platform. Use this when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, downloading data inside functions, and result handling.

Migrate Spring Boot 2.x applications to Spring Boot 3.x. Use when updating pom.xml versions, removing deprecated JAXB dependencies, upgrading Java to 17/21, or using OpenRewrite for automated migration. Covers dependency updates, version changes, and migration checklist.

Comprehensive code review agent that performs systematic, multi-dimensional analysis of code quality. Conducts security, performance, maintainability, testing, and architecture reviews with detailed checklists and actionable recommendations. Use when reviewing PRs, auditing codebases, establishing review standards, or performing technical debt assessment.

Write idiomatic Python code using advanced features such as decorators, generators, and async/await. Optimizes performance, applies design patterns, and ensures comprehensive testing. Use for Python refactoring, performance tuning, or implementing complex Python features.

Use when deploying a React app or setting up a server — provisions VPS, configures Nginx reverse proxy, SSL certificates, domain DNS, and firewall rules.

API integration patterns for building robust HTTP clients, handling authentication, error handling, and rate limiting.

Generate dark-themed SVG diagrams of software systems as standalone HTML files. Semantic component colors, grid background, JetBrains Mono font. Use for architecture diagrams, cloud topology, microservice maps.

Run evaluations for Hugging Face Hub models locally using inspect-ai and lighteval on your hardware. Intended for backend selection, local GPU evaluations, and choosing between vLLM, Hugging Face Transformers, and accelerate. Not intended for HF Jobs orchestration, model-card PRs, publishing .eval_results, or automating community-evals.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Multi-mode structural Clojure code reader. Efficiently locate symbols, extract source code, and understand errors without full-file reads or inefficient grep patterns.

Use when building UIs leveraging the WordPress Design System (WPDS) and its components, tokens, patterns, etc.

Expert Rust code review agent that analyzes Rust code for correctness, safety, idiomatic patterns, performance, and best practices. Use when reviewing Rust code files (.rs), providing feedback on Rust projects, checking for unsafe code patterns, evaluating borrow-checker compliance, suggesting idiomatic improvements, or conducting thorough code quality assessments for Rust codebases.

Use this skill when the user asks to "update study", "analyze new experiments", "update experiment document", or "refresh study notes". It produces academic-paper-quality experiment reports with matplotlib plots, an executive summary with comparison tables, implementation structure and code snippets, experimental results with figure interpretation, proposed improvements with code examples, hypotheses, limitations, and LaTeX PDF export including figures. Features include incremental detection (only analyze NEW experiments), data extraction into a pandas DataFrame, automated plot generation, an iterative writing-improvement loop with quality criteria, zero-hallucination verification, and LaTeX PDF export. Usage - `/update-study logs/experiment.log study.md` or `/update-study "logs/exp1.log logs/exp2.log" results/ablation_study.md`

Systematic security review of an LLM application — injection surface, tool permissions, output handling, data flows.