Write and improve beauty and skincare posts for 小红书 using product details and target audiences. Create titles, body text, relevant tags, and image-generation prompts that match the product and the post's visual style.
Write and revise product marketing copy using product details, audience needs, and distinctive selling points. Develop headlines, structured body text, and clear next steps, supported by supplied data and genuine customer feedback.
Analyze individual stocks using current quotes and historical price data. Calculate trend and momentum measures, identify price gaps and potential support or resistance levels, and produce a three-day outlook with trading scenarios and risk notes.
Add friendly conversation to OpenClaw during work breaks, task waits, or everyday chats. Generate brief, context-aware replies with Zhipu AI and optionally send prepared static images alongside messages through supported messaging channels.
Screen incoming files and URLs before document processing by checking blocked domains, open-access permissions, and file types. Produce a pass or reject decision, a risk report, and a tracking ID, with rejection when required checks cannot run.
Prioritize feature requests, analyze customer interviews, and draft product requirements documents. Use RICE scoring—a method weighing reach, impact, confidence, and effort—alongside templates and team capacity planning to turn findings into a quarterly roadmap.
Convert PDF, PowerPoint, Excel, and Word documents into structured Markdown for search and information extraction. Outputs include document metadata, a parsing confidence score, and the parser used, with fallback parsers available when earlier attempts fail.
Turn a topic or outline into presentation content, layout recommendations, image suggestions, and a PPTX file. A sequential seven-role workflow also supports improving existing content, refining wording, or producing only an outline and layout plan.
Score article ideas, create versions suited to different publishing platforms, and find cover images. Send articles to WeChat Official Account drafts, with other platforms requiring separate publishing endpoints and authentication setup.
Turn product details into short promotional videos through a workflow covering sales copy, storyboards, images, subtitles, and audio. Ten agent roles coordinate preparation, COZE API video assembly, quality checks, and improvement suggestions based on production feedback.
Develop blog posts, articles, newsletters, and technical documentation through research, outlining, drafting, and revision. Get source citations, stronger openings, and section feedback while preserving the writer’s voice and improving clarity, structure, and supporting evidence.
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.
Add illustrations to long articles by identifying concepts, steps, and comparisons that benefit from visuals. The skill plans and generates suitable images, then inserts them into the relevant sections of a Markdown article.
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.
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.
Prepare Markdown articles as drafts in the X Articles editor, converting text into formatted content and filling in the title. Saved browser authentication supports repeat use, while cover selection and final publication remain manual steps.
Understand software architecture, trace request flows, and assess the impact of code changes using Ontoly’s graph of software relationships. Answers include supporting graph evidence, confidence, and relevant limitations.
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.
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.
Convert PDF, Word, and Excel documents into structured Markdown for search and knowledge bases. The skill tries three parsers in sequence when needed and returns metadata, a confidence score, and the parser used.
Create a production materials package for a three-minute history or science explainer. Supply a topic, historical period, and scientific conclusion to generate narration, a storyboard, Veo2 prompts, and character design guidelines.
Build a new agent skill from a structured template. Copy the directory and edit SKILL.md to document its purpose, inputs, outputs, processing steps, precautions, and examples, replacing placeholders with concrete content.
Turn plain text or Markdown drafts into structured documents with headings, lists, and frontmatter metadata such as titles and summaries. Save a formatted copy and use scripts to correct spacing between East Asian text and English, plus emphasis punctuation.
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.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)