发现 Skills

Use when working with context management context restore

Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use when building business dashboards, selecting metrics, or designing data visualization layouts.

Automate Shopify tasks via Rube MCP (Composio): products, orders, customers, inventory, collections. Always search tools first for current schemas.

Map identified threats to appropriate security controls and mitigations. Use when prioritizing security investments, creating remediation plans, or validating control effectiveness.

End-to-end orchestrator for systematic academic literature reviews. Sequences query design, OpenAlex retrieval, deduplication, PRISMA screening, summarization, optional quality appraisal, and synthesis into a single governed pipeline. Use this skill whenever the user wants to run a complete literature review from a research question to a structured synthesis. Trigger on phrases like "do a literature review on", "systematic review of", "find and synthesize papers on", "review the literature on", or any request that implies going from a question all the way to a written synthesis. Does not replace the individual task skills — it orchestrates them.

Scan Swift Package Manager dependencies for vulnerabilities, outdated packages, and license issues. Use before PRs, after adding packages, or on a regular schedule.

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents, credentials, or personal data leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: `Is this skill safe?`, `skill security scan`, `check skill safety`, `audit skill`, `scan skill`, `analyze skill`, `inspect skill`, `verify skill`, `skill security`, `skill supply chain`. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.

Use this skill when developing browser/Web applications (React/Vue/Angular, static websites, SPAs) that need AI capabilities. Features text generation (generateText) and streaming (streamText) via @cloudbase/js-sdk. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended) and DeepSeek (deepseek-v3.2 recommended). NOT for Node.js backend (use ai-model-nodejs), WeChat Mini Program (use ai-model-wechat), or image generation (Node SDK only).

Flutter Tooling - Tools and Commands. Use when working with tooling.

Use when Nim's memory management—including garbage collection strategies, manual memory control, destructors, move semantics, ref/ptr types, memory safety, and optimization techniques for performance-critical systems programming—is relevant.

Guide for implementing Shopify's Billing API in Remix apps using @shopify/shopify-app-remix. Covers subscriptions, one-time purchases, usage-based billing, discounts, and the project's billing implementation patterns.

Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.

Analyse Mitre ATT&CK tactics, techniques and sub-techniques. Use when performing analysis of threat detections, threat models, security risks or cyber threat intelligence

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Web application testing principles. E2E, Playwright, deep audit strategies.

Vue 3 debugging and error handling for runtime errors, warnings, async failures, and SSR/hydration issues. Use when diagnosing or fixing Vue issues.

通用 UI 验收技能。验收必须以「实际页面效果 vs 设计稿」为准，必须使用浏览器工具 (Browser) 查看目标页面，通过页面截图与设计稿截图比对、或页面元素与 .pen 设计稿元素比对等落地方式完成验收，并产出问题清单与反思。

Assess stablecoin safety and risk profile across 500+ protocols. Covers depeg history, reserve composition, audit status, regulatory exposure, and market cap trends for major stablecoins (USDT, USDC, DAI, USDS, USDe, FDUSD, PYUSD, GHO, crvUSD, and more). Use when users ask "is this stablecoin safe?", "stablecoin risk", "depeg risk", or want to compare stablecoin safety before depositing. Powered by Barker (https://barker.money) — The Stablecoin Yield Map.

Build a Scratch program from a user prompt using vibe coding, then distill the novel techniques into a new reusable SKILL.md. Use this skill when you want to grow the scratch-operation or scratch-coding plugin with a new pattern discovered during live coding.

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

Expert C++ developer specializing in modern C++20/23, systems programming, and high-performance computing. Master of template metaprogramming, zero-overhead abstractions, and low-level optimization, with an emphasis on safety and efficiency.

Query Ninebot electric vehicle status via an API login → device list → device detail flow. Use this when users ask about remaining battery, vehicle status, or location of their Ninebot scooters/bikes, or when an agent needs to authenticate and select a device from a user account.

Meta-router for dynamic skill routing. Use when: cowork, skill management, router generation, Skills.toml, plugin configuration