Automate searches, navigation, and form entry in a visible Chrome window using agent-browser. Connect through Chrome’s remote control interface, retain login sessions in a dedicated profile, and show screenshots after significant actions.
Publish text, images, videos, quote posts, and Markdown articles to X through a Chrome browser. Preview content before submitting, reuse a saved login session, and configure a preferred browser profile for posting.
Save web pages as clean Markdown with source details such as title, author, and capture date. Chrome renders JavaScript content, while a wait mode lets you finish logging in or loading content before capture.
Turn data findings into reports and presentations that explain why the numbers matter. The skill combines context, problems, recommendations, and visual guidance to help executives and nontechnical audiences understand evidence and decide on next steps.
Create Chinese and English prompts for 即梦 product videos featuring the digital presenter 小省导购员. Organize short scenes, check character and emotional continuity, and prepare matching prompts for Suno music and AI-generated images.
Connect product research, 1688 data collection, listing templates, advertising copy, and promotional video creation for cross-border ecommerce. It also supports finding secondhand deals on 闲鱼 and monitoring prices against selected requirements.
Create ecommerce video scripts that connect a customer's problem with a product demonstration and a resolution. The workflow defines audiences and selling points, then adds shot choices, camera movements, localization guidance, and suggestions for subtitles, music, and testing.
Prepare five-scene prompts and parameter tables for product videos featuring a digital presenter in InfiniteTalk. Specify timed movements, check character consistency, and plan audio and image preparation for a 25-second vertical video.
Generate talking-person videos from a portrait or an existing video and an audio track, aligning lip movements, expressions, and body motion with speech. It supports long-form generation and can create speech from text using Kokoro-82M.
Review Word contracts for textual inconsistencies, business terms, and legal clauses while preserving the original wording and formatting. Produce clause-specific comments, an objective contract summary, consolidated review opinions, and a business flowchart based on the contract.
Convert, resize, and compress videos and images, including batches of files. Combine steps such as scaling and compression, specify output formats and quality settings, and check that the resulting files match the requested parameters.
Create and edit visual boards for ideas, workflows, and research using .canvas files supported by Obsidian and other applications. Arrange text, files, links, and groups, with labeled connections that show how the information relates.
Create and edit Obsidian .base files to display notes as tables, cards, or lists. Configure filters, calculated fields, grouping, and summaries to organize reading lists, project notes, and task trackers.
Create and edit Obsidian notes with links between notes, embedded files, callouts for highlighted information, and properties such as tags and dates. Format documents with tables, task lists, equations, and diagrams using Obsidian’s Markdown syntax.
Process PDF forms, extract tables and text, and recognize text in scanned documents with OCR. Included scripts support data validation, batch workflows, merging, and page splitting, with table exports to CSV or Excel.
Create 15–30 second vertical pet product videos, from reference video analysis to scripts, shot plans, images, subtitles, and audio. The workflow combines materials through the COZE API and supports revisions based on feedback.
Turn plain-language descriptions or Mermaid diagrams into interactive, standalone HTML diagrams of systems, workflows, API exchanges, data flows, and state changes. Validate layouts, explore relationships, switch themes, and export diagrams as images or video.
Turn web articles into Markdown, a plain text format for structured documents, then refine headings and paragraphs, generate relevant illustrations, and publish to 微信公众号 and X/Twitter through a connected workflow.
Simulate a decision meeting with three to five AI roles with different expertise and personalities. Follow their debate and receive a meeting record covering conclusions, supporting arguments, risks, and suggested next actions.
Organize parsed documents into four color-coded cards covering facts, explanations, risks, and actions. Preserve source references and generation details so readers can review evidence, identify uncertainty, and consider next steps in research, financial, or legal analysis.
Write fictional short video interviews that place historical figures in a modern talk show. Combine historical traits with internet humor, then produce titles, host introductions, questions and answers, visual cues, and closing prompts for audience interaction.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)