3278 个 · 按相关度排序
Extract and analyze PDF text, tables, form values, and document properties while preserving their structure. Produce summaries, compare documents, or organize selected data as CSV or JSON, with uncertain extraction results clearly identified.
中文简介正在准备中。当前显示英语简介。
Create, edit, and reorganize PowerPoint presentations, or extract text from existing decks. Use templates or build slides from scratch, apply consistent visual styling, and inspect rendered slide images to find content and layout problems.
中文简介正在准备中。当前显示英语简介。
Extract decisions, lessons, recurring patterns, and unexpected findings from the artifacts of a completed development phase. It organizes these learnings into a LEARNINGS.md file using planning, summary, verification, acceptance testing, and state documents.
中文简介正在准备中。当前显示英语简介。
Extract text from images and PDFs, including handwriting, tables, invoices, and receipts. Return plain text, Markdown tables, or structured JSON fields, with options to select a recognition provider and specific PDF pages.
中文简介正在准备中。当前显示英语简介。
Automate Chrome using an existing login session through CDP, Chrome’s remote control interface. Open pages, click elements, enter text, extract page content, run JavaScript, and inspect authentication tokens with agent-browser.
中文简介正在准备中。当前显示英语简介。
Extract readable text from PDFs when ordinary file readers return garbled or binary content. The skill guides agents through detecting failed reads and using pdftotext, a command-line PDF text extractor, with layout-preserving options.
中文简介正在准备中。当前显示英语简介。
Extract text from Word DOCX files with unzip and sed, command-line utilities, when Python document libraries are unavailable. Read the document’s main text, remove XML tags, clean whitespace, and save the extracted content.
中文简介正在准备中。当前显示英语简介。
Read or create DOCX documents when standard file tools fail. This fallback extracts text from the document's internal XML and uses python-docx through shell commands to build new files with headings, paragraphs, and tables.
中文简介正在准备中。当前显示英语简介。
Extract text from Word DOCX files with shell commands when python-docx is unavailable. The workflow reads the document’s XML content, removes tags, optionally cleans whitespace, and saves plain text for inspection or further use.
中文简介正在准备中。当前显示英语简介。
Extract text from Word DOCX files and save it as plain text. The skill checks available tools, tries shell utilities, and falls back to Python’s standard library when needed.
中文简介正在准备中。当前显示英语简介。
Extract details from TikTok video URLs, including captions, author profiles, view and engagement counts, music, and hashtags. Process individual posts or a list of URLs, with image links available for slideshow posts.
中文简介正在准备中。当前显示英语简介。
Extract YouTube transcripts and analyze messaging, structure, intended viewers, emotional appeal, credibility, and calls to action—requests for viewers to act. Analyze one video or compare several keyword-selected videos to identify recurring strategies and content gaps.
中文简介正在准备中。当前显示英语简介。
Extract a YouTube video’s full transcript and metadata, meaning details such as its title, channel, and like count, through the BrowserAct API. Use the results as source material for summaries, content research, or knowledge bases.
中文简介正在准备中。当前显示英语简介。
Extract structured product details from Walmart URLs, including prices, availability, specifications, images, and color or size options. Gather fulfillment choices, return policies, and review summaries to support product comparisons and catalog building.
中文简介正在准备中。当前显示英语简介。
Find a company's official website and social profiles from its name, or extract social profile links from a website URL. Structured results help fill gaps in sales contact lists and research a company's online presence.
中文简介正在准备中。当前显示英语简介。
Extract wholesale product details from 1688.com, including quantity-based prices, product variants with dimensions and weight, seller information, shop scores, promotions, and review summaries. Organize these details to compare sourcing options and supplier metrics.
中文简介正在准备中。当前显示英语简介。
Extract product names, prices, shipping details, and seller ratings from eBay search or category pages. Collect listings across multiple pages and regional eBay sites to prepare data for price comparisons and listing research.
中文简介正在准备中。当前显示英语简介。
Automate browser work with a command-line tool for AI agents. Extract JavaScript-rendered content, fill forms, upload files, capture screenshots and network responses, and manage separate browser sessions for tasks involving multiple accounts or manual assistance.
中文简介正在准备中。当前显示英语简介。
Automates website navigation, form entry, and information extraction through browser commands. Helps test web applications, reuse saved login state, and capture screenshots, PDFs, or recordings of browser workflows for inspection and documentation.
中文简介正在准备中。当前显示英语简介。
Extract text and data from images of charts, tables, interfaces, and diagrams using a vision model, an AI that reads images. Turn the results into structured tables, recreate charts, or export data to Excel and CSV.
中文简介正在准备中。当前显示英语简介。
Extract one still image from a local video using FFmpeg. Choose the first frame, a timestamp, or a frame number, then save a JPG for sharing or a PNG for clear interface details.
中文简介正在准备中。当前显示英语简介。
Extract text, tables, and images from PDFs, combine or split documents, rotate pages, fill forms, and create new files. It also covers password protection and OCR, which recognizes text in scanned pages for searching and reuse.
中文简介正在准备中。当前显示英语简介。
Extract statistical values from research PDFs for meta-analysis, which combines results across studies. Track each value’s source and confidence, prioritize review, and manage human corrections and final approval in a shared data structure.
中文简介正在准备中。当前显示英语简介。
Coordinate meta-analysis, which combines results across studies, from data extraction to reporting. Validate effect sizes, check for duplicates and implausible values, and assess how individual studies or publication bias affect the combined result.
中文简介正在准备中。当前显示英语简介。