Total 50,522 skills, Tools & Utilities has 8218 skills
Showing 12 of 8218 skills
Upload local images to a GitHub PR and embed them in the description or comments. Use when asked to "attach screenshots to PR", "add images to PR", "upload test results to PR", "embed screenshots in PR description", "add before/after images to PR", "attach UI screenshots", "show test results in PR", "add visual evidence to PR", or any request involving images and PRs. Always use this skill when the user wants to visually document changes in a pull request, even if they don't use the word "upload" — phrases like "put the screenshot in the PR" or "show the image in the PR" should trigger this skill. Supports Playwright MCP / Chrome DevTools MCP / agent-browser as browser automation backends.
DingTalk AI Table (multi-dimensional table) operation. This skill is used when users mention "DingTalk AI Table", "AI Table", "multi-dimensional table", "worksheet", "field", "record", "add record", "query record", "update record", "delete record", "new field", "delete field", "dingtalk AI table", "dingtalk notable", "able file". It supports all operations including worksheet management, field management, record CRUD, etc.
Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. MUST trigger when: (1) any task has failed 2+ times or you're stuck in a loop tweaking the same approach; (2) you're about to say 'I cannot', suggest the user do something manually, or blame the environment without verifying; (3) you catch yourself being passive — not searching, not reading source, not verifying, just waiting for instructions; (4) user expresses frustration in ANY form: 'try harder', 'stop giving up', 'figure it out', 'why isn't this working', 'again???', or any similar sentiment even if phrased differently. Also trigger when facing complex multi-step debugging, environment issues, config problems, or deployment failures where giving up early is tempting. Applies to ALL task types: code, config, research, writing, deployment, infrastructure, API integration. Do NOT trigger on first-attempt failures or when a known fix is already executing successfully.
Address tracker and analysis. Use this skill whenever the user provides an on-chain address or asks to track or query an address. Trigger phrases include: track this address, who owns this address, fund flow, check address. MCP tools: info_onchain_get_address_info, info_onchain_get_address_transactions, info_onchain_trace_fund_flow.
Triage and categorize findings for the CLI todo system
This skill should be used when the user asks to "set up a fresh Mac for development", "install Homebrew and Node on macOS", "prepare a new MacBook for coding", "install Xcode Command Line Tools", "install uv Python on Mac", or "fix missing node/npm/npx on macOS".
Extract and parse content from URLs. Triggers on: user provides a URL to extract content from, another skill needs to parse source material, "parse this URL", "extract content", "解析链接", "提取内容".
Manage smart alerts — list, create, update, toggle, delete. Use when setting up or managing token flow alerts, smart money alerts, or notification rules.
Submit URLs to Google for crawling via the Indexing API — supports manual URL lists, file imports (txt, CSV, sitemap.xml), and automatic route detection from the codebase. Generates terminal summary + HTML report. Use when the user wants to submit URLs to Google, request indexing, notify Google of new or updated pages, reindex pages, remove URLs from Google, "submit my sitemap", "tell Google to crawl these pages", "index my new pages", "submit routes to Google", or anything related to Google URL submission and indexing requests.
Framework Overview of Major Historical Events - A framework-based overview of one macro historical event per day. Prioritize linking to recent hot topics, form a systematic cognitive framework, and provide social talking points. The output includes six modules: Definition, Causes, Process, Impacts, Cognitive Framework, and Talking Points Cheat Sheet.
Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview. This is faster and more reliable than trying to read a raw PDF.
Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)