全部能力

When the user wants to analyze Google Search Console data, use the GSC API, or interpret search performance. Also use when the user mentions "GSC," "Search…

Next.js SEO optimization guide. Use when building Next.js apps, optimizing for search engines, fixing Google indexing issues, implementing metadata, sitemaps,…

使用受 x402 保护的 API 进行神经网络搜索和内容提取。在深度研究方面优于 WebSearch，在突破网站封锁方面优于 WebFetch。适用于：- 深度网络研究与调查 - 查找与参考 URL 相似的页面 - 从网页中提取纯文本 - 抓取屏蔽标准抓取工具的网站 - 获取事实性问题的直接解答 - 需要多个来源的研究 - 抓取网站的多个页面 触发条件：- "research"、"investigate"、"deep dive"、"find sources" - "similar to"、"pages like"、"more like this" - "scrape"、"extract content from"、"get the text from" - "blocked site"、"can't access"、"paywall" - "what is"、"explain"、"answer this" - "crawl"、"crawl site"、"scrape entire site" 针对 stableenrich.dev 端点，请使用 `npx agentcash@latest fetch`。语义/神经搜索优先使用 Exa，直接抓取优先使用 Firecrawl。

使用 Playwright 进行 E2E 测试 - Page Objects、跨浏览器、CI/CD

Guidelines for fixing unhandled errors from the VS Code error telemetry dashboard. Use when investigating error-telemetry issues with stack traces, error…

Vision-driven HarmonyOS NEXT device automation using Midscene. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Control HarmonyOS devices with natural language commands via HDC. Perform taps, swipes, text input, app launches, screenshots, and more. Trigger keywords: harmony, harmonyos, 鸿蒙, hdc, huawei device, harmony app, harmony automation, harmony phone, harmony tablet, test harmony app, verify on harmonyos, QA on 鸿蒙, check the app on harmony, test on huawei device, see if the app works on harmony, end-to-end test on harmonyos, visual verification on 鸿蒙 Powered by Midscene.js (https://midscenejs.com)

Find and explain company policies in plain language. Trigger with "what's our PTO policy", "can I work remotely from another country", "how do expenses work",…

在编写、审查或调试 Terraform/OpenTofu 模块、测试、CI、扫描或状态操作时使用——诊断故障模式（身份变动、机密泄露、爆炸半径……）

Design and draft multi-email sequences with full copy, timing, branching logic, exit conditions, and performance benchmarks. Use when building onboarding, lead…

Analyze pipeline health — prioritize deals, flag risks, get a weekly action plan. Use when running a weekly pipeline review, deciding which deals to focus on…

Specialized skill for building production-ready serverless

Expert in building browser extensions that solve real problems -

Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or…

Prepare journal entries with proper debits, credits, and supporting detail. Use when booking month-end accruals (AP, payroll, prepaid), recording depreciation…

Evaluate SaaS unit economics and capital efficiency. Use when deciding whether the business can scale efficiently or needs correction.

Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes,…

用于：(1) Blave 市场 Alpha 数据 — 筹码集中度 Holder Concentration, 多空力道 Taker Intensity, 巨鲸警报 Whale Hunter, 挤压动能 Squeeze Momentum, 市场方向 Market Direction, 资金稀缺…

Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when…

用于 SPEC.md 及相关规范编写的极简编码。由 /spec、/build、/check 加载。在保持精确的同时，相比散文式文本可减少约 75% 的 token。在对 SPEC.md 进行任何写入，或当用户说“caveman”、“compress this”、“be brief”时触发。

Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary…