Compress any GIF to meet 微信公众号正文 GIF 规范 by default (≤6MB in practice — official limit 10MB but uploads near 9MB often fail; ≤300 frames / 640px width / 12-20fps): merge long-staying/static frames, drop redundant near-static frames (timing preserved), cap fps and frame count, then walk an adaptive palette/lossy/scale encode ladder, quality first. Use this skill when the user asks to 压缩GIF, GIF太大, GIF超过6M/6MB/10M/5M, 公众号GIF规范, 公众号正文GIF, 减少GIF帧数, GIF帧数超过300, 合并重复帧, 微信/公众号/飞书/X GIF上传大小限制, shrink/compress/reduce GIF size, or make a GIF small enough to upload/share.
$npx -y skills add joeseesun/qiaomu-tiny-gif --skill qiaomu-tiny-gifInstalls into the current project.
Run `npx skills use "https://github.com/joeseesun/qiaomu-tiny-gif" --skill "joeseesun/qiaomu-tiny-gif"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/joeseesun/qiaomu-tiny-gif" that are relevant to the current task. Run `npx skills add "https://github.com/joeseesun/qiaomu-tiny-gif"` and select the relevant skills, then follow their instructions.