Latest Agent Skills

Creates, edits, and analyzes spreadsheet files, applying professional formatting and ensuring zero formula errors.

Creates, reads, edits, and converts PowerPoint presentations, including design guidance and quality assurance workflows.

Creates, reads, edits, and converts Word documents (.docx) with formatting, tables, images, and tracked changes.

Analyzes codebases in depth and produces structured markdown analysis documents covering architecture, module design, call flows, data models, and design patterns.

Look up and compare LLM API pricing across Models.dev, OpenRouter, and official provider pages, including token costs and aliases.

Analyzes Claude Code features to uncover advanced usage patterns, best practices, and real-world applications, producing a structured guide.

Extracts clean markdown or text from one or more URLs using the Tavily CLI, with support for JavaScript-rendered pages and query-focused chunking.

操作青云 QingCloud 云资源，包括云服务器、硬盘、网络、负载均衡和对象存储，通过 qingcloud CLI 执行命令。

Reads, extracts, merges, splits, rotates, watermarks, creates, encrypts, and OCRs PDF files using Python libraries and command-line tools.

Search the web with LLM-optimized results via the Tavily CLI, returning relevant snippets, relevance scores, and metadata. Supports domain filtering, time ranges, and multiple search depths.

Operates Scaleway cloud resources through the scw CLI, covering instances, images, object storage, Kubernetes, and databases.

Reviews all uncommitted changes in the current Git repository and produces a structured code review report with findings and a verdict.

Crawls websites and saves content from multiple pages as local markdown files using the Tavily CLI, with options for depth, breadth, path filtering, and semantic focus.

Search the web, scrape pages, crawl sites, and interact with dynamic content via the Firecrawl CLI, returning clean markdown for LLM contexts.

Operates UpCloud cloud servers via the upcloud CLI, covering server, storage, network, and firewall management with read-only and confirmed write operations.

Operates Hetzner Cloud resources via the hcloud CLI, covering server, image, network, and load balancer management with read-only and write operations.

Generates comprehension questions and language exercises based on analyzed content to create a complete learning loop.

Provides a template for creating agent skills with usage guidance and step-by-step instructions.

Operates UCloud cloud resources through the ucloud CLI, covering hosts, images, storage, networking, and databases.

Converts structured Markdown into a standalone, split-screen interactive HTML page with original text and translation on the left and a six-point linguistic analysis on the right.

Discovers and lists all URLs on a website without extracting content, using the Tavily CLI. Faster than crawling, with options for depth, filtering, and natural language instructions.

Performs web search, content extraction, site crawling, URL discovery, and deep research via the Tavily CLI, returning JSON for LLM consumption.

Guides users through opening Hong Kong bank accounts with ZA Bank and HSBC HK.

Provides notes and a workflow for opening a brokerage account online from mainland China, including required documents and funding details.

Operates Vultr cloud resources directly via the vultr-cli command-line tool, covering instances, object storage, and account management with built-in confirmation for write operations.

Operate Upyun cloud storage via the upx CLI, covering file upload, download, deletion, directory management, sync, and CDN purge.

Operates Qiniu Cloud object storage and CDN through the qshell CLI, covering bucket listing, file upload/download, batch operations, and CDN refresh.

通过 ksyun CLI 管理金山云资源，包括云服务器、对象存储、负载均衡、云数据库和 VPC。

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Handles all network operations including search, web scraping, login-required access, and social media content retrieval via a real browser CDP proxy.

Creates standardized git commits using the Conventional Commits specification by analyzing the diff, staging files, and generating appropriate commit messages.

Operates Google Cloud Platform resources via the gcloud CLI, covering compute instances, storage buckets, BigQuery, Cloud Run, GKE, IAM, and billing. It checks the environment, authenticates, confirms destructive operations, and diagnoses common errors.

Operates AWS resources directly through the AWS CLI, covering S3, EC2, Lambda, and CloudFormation. Activates when AWS-related terms are mentioned and enforces confirmation for write operations.

Operates Cloudflare resources (Workers, Pages, R2, D1, KV) via the wrangler CLI, covering authentication, deployment, and data management commands.

将内容拆解为系列卡通风格信息图提示词，通过 Chrome DevTools MCP 自动化调用 Gemini web app 生成图片，并自动收集到本地临时目录。

Manage Hugging Face Hub resources via the `hf` CLI: download and upload models, datasets, and spaces; manage buckets, cache, collections, discussions, and inference endpoints; run SQL queries on datasets.

Provides guidance on Hong Kong's four mobile network operators for reference and selection.

Rereads code, specs, plans, reviews, or skill edits with fresh eyes to catch blunders, oversights, and omissions before closure, reporting concrete evidence-backed findings.

Generates a five-tier strategy portfolio (Quick Win through Moonshot) with accretive artifacts, signals, and escape hatches, then stops for human input before execution.

Analyzes code to separate essential complexity from incidental noise, then produces a ranked refactoring plan with a structural sketch and TRACE assessment, without making edits.

Systematically explore an unfamiliar codebase and build a reusable architecture summary with file:line evidence, starting from documentation and tracing data flow.

Loads Remotion best practices for React video creation, covering animations, composition setup, assets, audio, captions, sequencing, transitions, media metadata, Three.js, Tailwind, and rendering patterns.

Verifies that tests for already-implemented behavior are meaningful by temporarily breaking the production code and confirming the test fails for the expected reason.

Analyzes a class for primitive obsession and proposes value object extractions with validation, structure, and refactoring guidance.

Compile deep repository evidence into artifact-bound correctness doctrine, including authority/law/proof maps, owned invariants, failure archaeology, and knowledge routing, with an optional minimal repository-specific skill portfolio.

Refactors Swift code toward declarative functional programming with immutability, value types, pure functions, transformations, and closure-based APIs.

Performs comprehensive exploratory testing on a website using browser automation, covering user journeys, forms, errors, accessibility, responsiveness, performance, and security basics.

Audits AGENTS.md and CLAUDE.md files for bloat, redundancy, and ineffective rules, then runs A/B evals to prove which instructions are dead weight.

Refactors code by removing unused imports, variables, methods, redundant comments, and fixing formatting, with automatic test runs and commits after each step.

Guides adding characterization tests before modifying or refactoring untested legacy code, using the RGR workflow and strangler fig pattern to reduce risk.

Runs a structured product-discovery interview and publishes a two-page Opportunity Brief to Confluence, covering business objective, customer, problem, success metric, alternatives, assumptions, and open questions.

Define owned inductive invariants and enforce them at parse, construct, API, DB, lock, or transaction boundaries, with counterexample-driven verification.

Refactors long methods or large code blocks by extracting small, focused helper methods with clear names and narrow responsibilities.

Verifies test effectiveness by introducing small bugs into production code and running the test suite to find weak or missing tests.

Analyzes a class or module for code smells and produces a prioritized refactoring plan with phases, success criteria, and risk mitigation.

Classifies code review findings to choose the smallest correct response, preventing one-patch-per-comment churn.

Refactors code by renaming variables, methods, classes, and types to improve clarity and intent, with automatic testing and commits after each rename.

Refactors test files to improve behavioral coverage, clarity, structure, assertions, fixture setup, and mocking strategy, removing implementation-detail or low-value tests.

Runs a post-launch review of a shipped PRD against its success metrics, interviewing the user on metric movement, assumptions, and decisions, then publishing an outcome-review page to Confluence and updating linked artifacts.

Breaks applications or features into thin vertical user-story slices with clear acceptance criteria and user-observable value, suitable for backlog planning and feature decomposition.