Loading...
Loading...
Found 1,019 Skills
Use cyte to extract webpage markdown, discover links, and crawl internal docs/pages. Use this skill when users ask an agent to collect website content, run doc discovery, or build machine-readable crawl outputs with npx/pnpm dlx/global cyte.
Guides users through structured three-stage collaborative documentation workflow including context gathering, iterative refinement, and reader testing. Use when asked to "write a doc", "draft a proposal", "create a spec", "write technical documentation", "create a PRD", or "draft an RFC". Implements systematic approach for PRDs, design docs, decision docs, technical specs, and proposals through clarifying questions, section-by-section iteration, and fresh-eye validation. Works with markdown documentation, technical specifications, and structured writing projects.
Fetch and parse WeChat Official Account articles. Extract titles, authors, official account names, main content, images and metadata from WeChat article links. It is used when users provide WeChat article links (mp.weixin.qq.com/s/...) and want to read, extract, download or convert article content. Applicable scenarios include obtaining/downloading WeChat articles, extracting text or metadata from WeChat articles, converting WeChat articles to Markdown, and saving WeChat articles along with images locally. Keywords: WeChat Official Account, article acquisition, article scraping, article download.
Use when you need legal PDF to markdown extraction plus clause chunking and embedding prep; pair with addon-rag-ingestion-pipeline and architect-python-uv-batch.
通过 Chrome CDP 抓取任意 URL 并转换为 Markdown。支持两种模式——页面加载后自动抓取，或等待用户信号（适用于需要登录的页面）。当用户要求将网页保存为 Markdown 时使用。
Fetch and extract web content as clean Markdown when provided with URLs. Use this skill whenever a user provides a URL (http/https link) that needs to be read, analyzed, summarized, or extracted. Converts web pages to Markdown with 80% fewer tokens than raw HTML. Handles all content types including JS-heavy sites, documentation, articles, and blog posts. Supports three conversion methods (auto, AI, browser rendering). Always use this instead of web_fetch when working with URLs - it's more efficient and provides cleaner output.
Slack automation CLI for AI agents. Use when: - Reading a Slack message or thread (given a URL or channel+ts) - Browsing recent channel messages / channel history - Getting all unread messages across channels - Searching Slack messages or files - Sending, editing, or deleting a message; adding/removing reactions - Listing channels/conversations; creating channels and inviting users - Fetching a Slack canvas as markdown - Looking up Slack users - Marking channels/DMs as read - Opening DM or group DM channels Triggers: "slack message", "slack thread", "slack URL", "slack link", "read slack", "reply on slack", "search slack", "channel history", "recent messages", "channel messages", "latest messages", "mark as read", "mark read", "unread messages", "unread", "what did I miss"
Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown, extracting plain text from Portable Text, or troubleshooting rendering issues with marks, blocks, lists, or custom types.
Adversarial stress-test of a /think intelligence brief. Reads the think output markdown, then deploys 5-7 of the same analytical frameworks — but each one is hunting exclusively for reasons the recommendation is wrong, the conviction is unearned, and the idea will fail. Every framework becomes a prosecutor, not a judge. Surfaces the strongest kill shots, identifies which parts of the original brief are load-bearing but unverified, and produces a Red Team Report with a survival verdict. Use when the user says "red-team this", "attack this", "poke holes", "steel-man the opposition", "why is this a bad idea", "/red-team", or presents a /think brief they want stress-tested.
Buttondown platform help — newsletter publishing, paid subscriptions via Stripe, automations, subscriber management, tags, RSS-to-email, custom domains, Markdown editor, CLI, REST API. Use when Buttondown emails aren't sending, paid subscriptions not working, automation not triggering, subscribers not importing, Stripe payments failing, custom domain not resolving, API calls returning errors, or migrating to Buttondown from another platform. Do NOT use for cross-platform email marketing strategy (use /sales-email-marketing), newsletter monetization strategy (use /sales-newsletter), audience growth strategy (use /sales-audience-growth), or cross-platform deliverability (use /sales-deliverability).
Handle Word document (.docx) creation, editing, and analysis with high-fidelity visual review. Use for professional reports, legal documents, and tracked changes. Use proactively when quality and precise formatting are critical. Examples: - user: "Create a professional report in Word" -> use python-docx with render loops - user: "Draft a legal contract with redlines" -> use ooxml redlining workflow - user: "Extract text from this DOCX while preserving structure" -> use pandoc markdown conversion
Polish and elevate MBA thesis/dissertation to the quality of National Excellent Thesis. Conduct comprehensive enhancements in academic language, argument structure, logical rigor, innovation highlights, and formatting. Input: Markdown-formatted thesis text. Output: fully polished complete text. This service is also triggered when the user mentions terms such as "thesis polishing", "MBA thesis", "excellent thesis", "thesis polish", "dissertation improvement", "academic polishing".