发现 AI Agent Skills

Convert EPUB books to high-quality formatted Markdown using pandoc and AI-assisted formatting. Use when the user provides an EPUB file path and wants to convert it to professionally formatted Markdown, similar to the Clean Code Collection formatting. This skill handles the complete workflow from EPUB extraction through AI-driven content formatting, including fixing PDF conversion artifacts, joining split paragraphs, correcting code blocks, standardizing headers, and creating proper Table of Contents.

Use when the user is explicitly working with Quarto, .qmd files, _quarto.yml, Quarto projects, or Quarto features such as callouts, cross-references, citations, Mermaid diagrams, extensions, websites, books, presentations, and reports. Also use for explicit migration from or comparison with R Markdown, bookdown, blogdown, xaringan, distill, or Jupyter notebooks to Quarto. Do not use for general R Markdown or related-format questions unless Quarto or migration to Quarto is explicitly mentioned.

Automatically transform requirement documents or natural language descriptions into complete full-stack projects (Java backend + Vue frontend) with MANDATORY interactive tech stack selection. Supports database schema design, REST API generation, CRUD operations, user authentication, and project scaffolding. ⚠️ TECH STACK SELECTION IS MANDATORY - Users MUST explicitly select or confirm each option, cannot skip by pressing Enter. Use when: (1) Converting PRD/requirements into working code, (2) Rapid prototyping of web applications, (3) Generating boilerplate projects from descriptions, (4) Bootstrapping CRUD applications, (5) Creating MVP projects from text specifications.

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

查看远程服务器 GPU 使用情况。SSH 连接服务器，展示每张卡的显存占用、运行进程、所属容器。当用户说查看 GPU、显卡占用、显存使用时使用

CiviCRM integration. Manage data, records, and automate workflows. Use when the user wants to interact with CiviCRM data.

Tests API parameters, headers, and request bodies for injection flaws — SQL injection, NoSQL injection, OS command injection, LDAP injection, and SSRF — by crafting payloads tailored to the target backend to extract data, execute commands, or reach internal services, mapped to OWASP API8:2023 and API7:2023 SSRF. Use when performing SQLi, NoSQL injection, command injection, or SSRF testing against APIs, or assessing API input validation.

Read and manage Google Tasks task lists and individual tasks via the Tasks v1 REST API. Use when the user mentions Google Tasks, todo / pending / overdue tasks, weekly task recap, grouping todos by list, adding or completing a task, or moving / deleting tasks.

Guidelines for building edge-first, high-performance APIs with Hono and TypeScript for Cloudflare Workers, Deno, Bun, and Node.js

Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go", "decouple from the database", "swap the framework without a rewrite", or "keep business rules independent". Also trigger when deciding which layer code belongs in, isolating core logic from infrastructure, defining module boundaries, or debating whether the framework should call your code or the reverse. Covers component principles, boundaries, and SOLID. For code-level quality, see clean-code. For domain modeling, see domain-driven-design.

Load test and scale Vercel deployments with concurrency tuning and capacity planning. Use when running performance tests, planning for traffic spikes, or optimizing serverless function scaling on Vercel. Trigger with phrases like "vercel load test", "vercel scale", "vercel performance test", "vercel capacity", "vercel benchmark".

Capture professional-quality remote interviews using double-ender technique and dedicated recording platforms for podcasts, media, and content production. Use when: Setting up remote podcast interviews with guests; Recording media interviews across distances; Creating customer interview content; Producing expert interviews for thought leadership; Conducting research interviews with high audio quality

Fast vector similarity search at billion scale.

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.

Command-line interface for Joplin workflows using the real joplin terminal backend

Audits business spreadsheet models (.xlsx, .xlsm, or Google Sheets exported to .xlsx) for structural integrity errors and explains each fix -- budgets, forecasts, pricing models, commission calculators, FP&A packs, ops trackers, not only banking models. A bundled openpyxl script finds hardcoded numbers inside formulas, typed values pasted over formulas, inconsistent formulas across a row or column,

Analyze and troubleshoot Alibaba Cloud AnalyticDB (ADB) Spark applications—execution monitoring, failure diagnosis, performance anomaly detection, and cross-application comparison. Use this Skill when users need to: 1. Check the execution status of AnalyticsDB Spark applications (running, succeeded, failed, etc.). 2. Analyze root causes of failed AnalyticsDB Spark applications (e.g., OOM, data skew, dependency errors, permission issues). 3. Identify Spark applications with abnormal execution duration by statistical analysis. 4. Compare similar Spark applications to pinpoint performance anomalies or detect SQL execution plan differences. Also applicable for "why did my Spark job fail", "which Spark app is running slow", "compare two Spark runs", etc.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.