Generate platform-optimized video covers and insert them as the first frame.
npx skills add https://github.com/npc-live/clawfirm --skill cover-gen
Please help me install this Agent Skill. Skill: cover-gen Source: https://github.com/npc-live/clawfirm/tree/main/app/assets/skills/video-skills/cover-gen Command: npx skills add https://github.com/npc-live/clawfirm --skill cover-gen
Manually creating platform-optimized video covers and seamlessly inserting a branded first frame is time-consuming and error-prone. This skill automates the process to ensure consistency across platforms and saves time in video publishing pipelines.
Provide the path to your raw video and target platform to generate a cover and insert it as the first frame.
High-intent search queries and answers about installing and using this skill.
To generate platform-optimized video covers and insert them as the first frame, this skill automates the extraction of a reference frame, computes platform-specific specs, and concatenates a 0.1-second cover clip before the original video using FFmpeg. It outputs both a cover image and a ready-to-publish video.
Automating branded thumbnails for social media videos is best handled by this skill, which uses media_gen to create AI-generated covers tailored to platform guidelines like Douyin, Xiaohongshu, Bilibili, YouTube, and LinkedIn, then seamlessly integrates them into your video publishing pipeline.
Yes, cover-gen supports distinct aspect ratios for platforms like Douyin and YouTube by computing platform-specific cover specs during generation, ensuring your video thumbnails meet the required dimensions and text guidelines for each social media platform.
Yes, you can use FFmpeg to insert a 0.1-second cover clip before the original video, which this skill automates by generating the cover image with media_gen and then concatenating it with optional audio handling to create a ready-to-publish video file.
Generating AI-generated video covers requires extracting video metadata from the source file to compute platform-specific cover specs and extract a reference frame, which guides the style and composition of the final AI-generated thumbnail before FFmpeg concatenation.
A limitation when adding a first frame to a video for social media workflows is that the inserted cover clip is fixed at a 0.1-second duration with optional audio handling, meaning complex transitions or longer intro sequences are not supported by this automated concatenation process.
eggent-aiExtract video frames as JPEG or PNG images using ffmpeg.
xianmingyaoAutomate video publishing to Douyin, WeChat Channels, Xiaohongshu, Bilibili, and YouTube with Python and Playwright.
jholhewresProcess video and audio files using the ffmpeg command-line tool.
ElbertePlinioAutomate cinematic video showcases using preset-based Remotion configurations.
