animation-prompt
Skill2 starsChanged 12 days agoMITView on GitHub
根据已审核关键帧和分镜编写动作提示词并调用可用视频工具生成单镜头动画,检查动作与连续性。
In this repository8 other files it gives its agents.
- character-bibleSkill
- guagua-animation-pipelineSkill
- ops-compilerSkill
- scene-generatorSkill
- sound-designerSkill
- story-writerSkill
- video-editorSkill
- visual-comedy-directorSkill
The file
Files
动画镜头生成
输入与输出
读取shots.json、characters.json和已审核关键帧。输出animation-prompts.md、clips/镜号对应视频,并记录实际model、task_id、generated_duration_s、取用区间和video_status。保留image_status;两种媒体状态均approved且文件及取用区间有效,才将镜头status设为approved。
提示与生成
- 每镜写出起始状态、主要动作、结果、表情变化、运镜和无对白约束。用“短腿快速倒腾、身体上下颠动”替代泛泛“跑”;动作只使用角色已有肢体。
- 默认全景稳定、中景适度跟随、特写轻推;以导演的明确运镜为准,追逐允许跟拍。嘴部可表达惊呼,不能生成语言对白或说话式口型。
- 使用对应视频工具前读取其技能并检查实际支持的参考图、时长、尺寸和模型。提示词完成不等于调用完成。关键帧路径必须真实,参考图上传遵循工具流程。
- 模型最短时长大于成片镜头时,可生成长片段再截取;不得随意倍速掩盖失败动作。若所需动作无法在短镜头完成,反馈导演拆镜。
- 记录提交任务并轮询到终态;只在原任务明确失败或镜头不合格后按已授权范围重试。达到预算或次数上限保留进度。
审核与交接
完整播放片段并查看关键动作,检查角色变形、穿模、闪烁、方向变化、道具消失、起止姿态和动作可读性。记录source_in_s/source_out_s,确保源时长足够覆盖成片运动部分。明确自带音频保留还是静音。 通过片段交付video-editor和sound-designer;失败镜头单独列出,不把静帧占位成片标为完成。
项目约定
本技能服务双主角反差、无对白视觉喜剧系列;默认约70秒、9:16竖屏,结尾留钩子。用户的新要求优先。保持已确认角色与画风,不把示例角色强加给其他项目。 每集在用户项目目录保存产物;镜号采用S001等稳定编号,修改内容不随意改号。沿用episode.json清单:episode_id、theme、target_duration_s、character_version、story_path、shots_path、audio_path、output_path、status。首次单独调用时只建立实际需要的文件,不要求先完成全部流程。 路径必须指向真实文件;未完成用null或“待生成”,不用虚构链接。提示词、生成素材、审核通过、导出成片是不同状态。已获授权内继续工作,不重复确认;付费工具遵循实际工具报价与授权流程。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

