84 skills (repositories by anbeime) · sorted by popularity
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.
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.
Create videos based on 『三体』 through a structured workflow covering source-setting research, scripts, storyboards, character consistency, audio, and final assembly. It also checks story consistency and technical quality, and prepares titles, covers, and tags for B站.
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.
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.
Transcribe recordings and reshape the text into meeting notes, emails, or social media posts. Combine text from multiple recordings into a continuous document, then prepare the result for copying or sharing while preserving the original meaning.
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.
Create a resume tailored to a specific job posting by matching requirements with relevant experience and achievements. Adjust keywords for applicant tracking systems, software used to manage applications, and identify strengths and qualification gaps.
Extract still frames from videos at chosen intervals, then use an AI model that understands images to analyze scenes, people, and composition. Get structured descriptions and creative prompts for video planning and storyboard reference.
Turn trending topics into illustrated posts for 微信公众号, 小红书, and 哔哩哔哩. The skill scores topic ideas, adapts writing to each platform, prepares HTML layouts, and supports previewing content before sending it through publishing scripts.
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.
Collect operation events across an AI agent workflow and link them into traceable execution records. Search by tracking ID, time range, or responsible agent, with semantic indexing and local event storage to support audits and investigation.
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.
Create pop-up book illustrations for educational, technology, and brand materials. The skill builds image prompts around layered paper textures, an open book, and warm colors, with optional digital effects, then checks the generated image against those visual requirements.
Turn slide content stored in JSON, a structured data format, into editable .pptx presentations with text, images, charts, and tables. Apply layouts, styles, or templates, validate the results, and process multiple input files in batches.
Turn product information into a promotional MP4 through a staged workflow covering sales copy, story planning, shot descriptions, generated scene images, subtitles, and audio recommendations. A Python script combines the prepared materials into the final video.
Add animated transitions to presentation videos and interactive effects to HTML slideshows. Plan the sequence and timing of movement, apply effects such as fades or zooms, and produce an enhanced video or browser player.
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.
Plan and assemble original videos with images, voiceovers, sound effects, music, and subtitles. The suite also extracts frames from existing videos, analyzes their visual style, and produces shot references and prompts for new versions.
Analyze a reference video's visual style, colors, composition, and pacing, then develop a new video with generated images, narration, sound, and subtitles. The workflow combines assets into an MP4 and supports resuming failed production steps.
Package a website URL as a desktop application for macOS, Windows, or Linux using pake-cli. Customize its name, icon, window size, and advanced options, then receive the installer file and installation guidance.
Add a virtual companion to OpenClaw that starts conversations during long tasks and sends messages with scene-appropriate images through 飞书. The documented initial implementation uses generated dialogue, scene detection, and a static image library.
Convert text into spoken audio for video narration, audiobooks, reading assistance, or language practice. The skill uses Edge-TTS preset voices in languages including Japanese, English, and Chinese, with voice selection guided by the text and requested tone.