@ZJU-REAL
组织
REAL Lab is a research team at Zhejiang University focusing on Reasoning, Embodied, Agentic and Lifelong Evolving AI. △ Page: https://zju-real.github.io
114 个技能1 个仓库 3959
Research posts on 小红书 using search, engagement data, and creator profiles. Analyze successful content, compare topics, and check for possible visibility restrictions to inform content planning through a command-line tool.
中文简介正在准备中。当前显示英语简介。
Combine existing photos or images into an MP4 slideshow with slow zooms, transitions, optional background music, and captions for individual images. Choose portrait, square, or landscape dimensions, with music automatically adjusted to the finished video's length.
中文简介正在准备中。当前显示英语简介。
Create six alternative openings for social media posts from a topic or phrase. Each pairs an opening statement with a twist, follows a distinct formula, and is checked against a length limit using the supplied counting script.
中文简介正在准备中。当前显示英语简介。
Prepare and publish answers to 知乎 questions through browser automation. Check whether a question can be answered, use supplied text or a separate writing skill, preview the action, and record publication details.
中文简介正在准备中。当前显示英语简介。
Build a reference for consistent writing through a structured interview and analysis of writing samples. The skill creates two files documenting the creator’s positioning, tone, sentence rhythm, signature expressions, and patterns absent from the samples.
中文简介正在准备中。当前显示英语简介。
Collect trending topics from Chinese platforms such as 微博 and 抖音, identify those relevant to a creator’s focus, and suggest content ideas with distinct angles, suitable formats, and timing guidance.
中文简介正在准备中。当前显示英语简介。
Review monthly results across social platforms using CSV exports, screenshots, or verbal descriptions. Identify patterns in strong and weak posts, compare content formats, and produce a readable report with specific recommendations for the next month.
中文简介正在准备中。当前显示英语简介。
Check your signed-in social accounts in Easel and retrieve profile identities, follower counts, likes, and published posts. Supports 小红书, 抖音, 快手, 知乎, and 视频号, with available statistics varying by platform.
中文简介正在准备中。当前显示英语简介。
Build a social content strategy covering core themes, audience relationships, a 90-day operating approach, distribution channels, and performance measures. Receive a strategy document that guides future topic development and scheduling without assigning individual posting dates.
中文简介正在准备中。当前显示英语简介。
Add UTM tags, parameters that identify traffic sources and campaigns, to content or advertising links and shorten them through public services. Create separate links for each channel or creative variant to support traffic analysis.
中文简介正在准备中。当前显示英语简介。
Analyze publishing logs to compare posting times, tags, content formats, and follower growth. The skill produces tables and practical recommendations, while reporting sample sizes and missing metrics so readers can judge the strength of the findings.
中文简介正在准备中。当前显示英语简介。
Translate existing SRT, VTT, or ASS subtitles into a chosen language while preserving timing. Create bilingual or translation-only subtitle files, then optionally add switchable subtitles to a video or permanently render them into its frames.
中文简介正在准备中。当前显示英语简介。
Manage comments on 小红书 by listing your posts, fetching comments, drafting replies in the account’s voice, and sending them after confirmation. Preview replies or deletions before execution, and track replied-to comments to avoid duplicate responses.
中文简介正在准备中。当前显示英语简介。
Review text, images, and videos before publication for risky wording, platform restrictions, completeness, and readability. Receive an overall publication verdict, issue details, quality assessments, and the three most important fixes to address.
中文简介正在准备中。当前显示英语简介。
Gather news from Chinese industry media, filter it by topic or creator focus, and produce a structured daily briefing with summaries, context, and practical ideas for articles or videos.
中文简介正在准备中。当前显示英语简介。
Manage social media account profiles covering identity, writing style, audience, platforms, preferences, and accumulated findings. Create or edit profiles, switch between accounts, compare their differences, and export a structured Markdown summary.
中文简介正在准备中。当前显示英语简介。
Create 16:9 landscape images for sharing a quote or key figures on social media. The skill arranges text, attribution, supporting metrics, and branding in HTML, then renders the card as a PNG image.
中文简介正在准备中。当前显示英语简介。
Turn podcast clips, music, or spoken audio into MP4 videos with animated waveforms or frequency displays. Add a cover image and title to prepare audio content for sharing on video platforms.
中文简介正在准备中。当前显示英语简介。
Turn prepared text into a set of vertical knowledge cards for Xiaohongshu. Choose a visual style, organize each card around one main point, and export coordinated cover, content, and closing images.
中文简介正在准备中。当前显示英语简介。
Create vertical marketing posters for product launches, events, and social sharing. Arrange a large headline, key selling points, and a call to action in a 1080×1920 layout, delivered as an HTML file and a rendered PNG image.
中文简介正在准备中。当前显示英语简介。
Replace a green, blue, or specified color backdrop in recorded video with an image, video, solid color, or blurred version of the footage. Preserve the original audio while automatically fitting and looping the replacement background as needed.
中文简介正在准备中。当前显示英语简介。
Cut people or products out of photos and save them as transparent PNGs, place them on solid colors, or combine them with another background image. Choose general or portrait models, with optional edge refinement for hair and fur.
中文简介正在准备中。当前显示英语简介。
Combine narration, background music, and timed sound effects into one audio file. Background music can loop to match the narration and automatically become quieter during speech, a technique called ducking, with controls for relative volume.
中文简介正在准备中。当前显示英语简介。
Create new videos from written scene descriptions or still images using external AI services. Set the aspect ratio and duration, animate a character image, and request generated audio when the selected model supports it.
中文简介正在准备中。当前显示英语简介。