Loading...
Loading...
Found 902 Skills
This skill helps users automatically extract complete Markdown content from any website via the BrowserAct Web Search Scraper API. The Agent should proactively apply this skill when users express needs like extract complete markdown from a specific website, scrape the content of an article link, get the text from a target url, convert a webpage to markdown format, fetch the main content of a blog post, extract data from a given web page, parse the html of a website into markdown, download the readable text from a news article, obtain the content of a tutorial page, extract all the markdown text from any http or https url, scrape documentation from a web link, or grab the text of a single webpage.
Convert legal texts (legal provisions or legal cases) into standardized Markdown format and remove promotional redundant information. This skill shall be used when users need to process legal provisions (such as the Civil Code, Criminal Law, etc.), organize legal cases (such as typical cases of the Supreme People's Court, judgment documents, etc.), or format legal documents from pasted text. Note: This skill is only responsible for formatting and content cleaning, and does not have content crawling capability. Content acquisition shall be completed by other skills (such as wechat-article-fetch), and AI will automatically determine the skill collaboration sequence.
PDF data extraction tool. Use it when users mention "PDF extraction", "PDF to Markdown", "PDF parsing", "extract PDF content", "PDF to JSON", "RAG PDF". OpenDataLoader PDF is currently the top-ranked PDF parser in benchmark tests, supporting local mode (fast, deterministic) and hybrid AI mode (for complex tables, scanned documents, formulas), with output formats including Markdown, JSON (with bounding boxes), and HTML. It is suitable for scenarios where structured data needs to be extracted from PDFs for RAG/LLM pipelines, or where batch processing of PDF documents is required.
Analyze Huawei Ascend NPU profiling data to discover hidden performance anomalies and produce a detailed model architecture report reverse-engineered from profiling. Trigger on Ascend profiling traces, NPU bottlenecks, device idle gaps, host-device issues, kernel_details.csv / trace_view.json / op_summary / communication.json. Also trigger on "profiling", "step time", "device bubble", "underfeed", "host bound", "device bound", "AICPU", "wait anchor", "kernel gap", "Ascend performance", "model architecture", "layer structure", "forward pass", "model structure". Runs anomaly discovery (bubble detection, wait-anchor, AICPU exposure) alongside model architecture analysis (layer classification, per-layer sub-structure, communication pipeline). Outputs a separate Markdown architecture report alongside anomaly analysis.
Integrate markstream-vue into a Nuxt 3 or Nuxt 4 app. Use when Codex needs client-only boundaries, SSR-safe setup, browser-only peer gating, worker-aware initialization, or a safe `MarkdownRender` integration inside pages, components, or Nuxt plugins.
Fill web forms by fetching form fields from a URL, deep-searching the user's local knowledge base for relevant info, and generating a markdown document with all answers pre-filled. Use when the user provides a URL to a web form (conference application, speaker submission, event registration, profile form) and wants help filling it out from their existing materials. Also trigger when the user mentions "填网页表", "fill web form", "网页填表", "表单填写", "申请表填写", "conference application", "speaker submission", "讲师申请", "报名表", or provides a URL with "form", "feedback", "apply", "register", "submit" in the path.
Directly publish local Markdown/HTML articles to WeChat Official Account draft box via WeChat Official Account API. Supports multiple themes, preset colors, and automatic image upload.
Use when working with Obsidian vaults, markdown notes with [[wikilinks]], ![[embeds]], callouts (> [!type]), YAML frontmatter/properties, #tags, block IDs (^id), ==highlights==, %%comments%%, Obsidian CLI commands (obsidian create/read/append/search/move/tags/daily/etc.), vault organization (PARA, MOC, flat+tags, Johnny Decimal), folder restructuring, daily notes, templates, task management, backlink analysis, or any file operations in an Obsidian vault directory. Trigger this skill whenever the user mentions Obsidian, .md files inside an Obsidian vault, knowledge base organization, or note-taking workflows — even if they don't explicitly say "Obsidian".
WeChat Official Account Layout | Markdown to HTML | Layout Themes | Paragraph Styles — One-click layout tool for WeChat Official Accounts, converts Markdown manuscripts to HTML that can be pasted into WeChat backend, supports multiple themes, font sizes, paragraph style switching, and WYSIWYG. Targeted at WeChat Official Account editors, independent authors, and layout specialists. Trigger words: 'layout', 'format', 'beautify', 'formatting', 'font size', 'paragraph style', 'change layout theme', 'change format', 'convert to HTML', 'make it look better', 'adjust format'. For changing preset packages/brand packages/complete theme color schemes, use aws-wechat-article-assets; for multi-link workflows (writing + review + layout + image matching + publishing), use aws-wechat-article-main.
When editing Markdown documents, add simple hash anchors to headings. Forcibly call this when the user mentions adding simple hash anchors.
Fetch a single URL and convert its content to Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. The content is returned as plain Markdown text on stdout.
Convert Markdown documents to professionally typeset PDF files. Primary engine: reportlab (cover pages, frontispiece, back cover, bookmarks). Fallback engine: pandoc + XeLaTeX (better table handling, LaTeX-quality typesetting). Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, clickable TOC, watermarks, headers/footers, and page numbers. Supports multiple color themes and is battle-tested for Chinese technical reports. Trigger when user mentions "markdown to PDF", "md2pdf", "any2pdf", "md转pdf", "报告生成", "导出pdf", or wants a professionally formatted PDF from markdown.