Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Rename documents and files (PDFs, images, screenshots, etc.) by reading their content to extract the effective/publication date, then renaming them with a "YYYY-MM-DD - Clear descriptive title.ext" format. Use when the user wants to organize files with date prefixes based on document content.
根据分镜描述生成视频片段。支持多个 AI 视频生成后端：即梦 Jimeng、Kling 可灵、Runway、Pika、Vidu。输入场景描述+可选的数字人口播，输出视频片段。触发词：AI视频、生成视频、分镜视频、scene video、text to video、图生视频。
Prepare and fill federal and state tax return PDF forms
视频片段拼接和后期处理。输入视频片段列表，输出完整视频。支持转场效果、背景音乐、字幕叠加。底层使用 FFmpeg 或 Remotion。触发词：拼接视频、合并视频、视频剪辑、video stitch、concatenate videos、add transitions。
声纹克隆和语音合成。上传音频样本克隆声纹，用克隆声纹或预设声纹生成语音。支持多个后端：MiniMax、ElevenLabs、Fish Audio、Azure TTS、OpenAI TTS。支持情绪控制、语速调整、批量生成。触发词：语音合成、TTS、声纹克隆、voice clone、text to speech、配音、旁白。
Apply a professional Fujifilm ETERNA-inspired cinema color and composition treatment to generated or edited raster images. Use when the user asks for ETERNA, Fujifilm ETERNA, ETERNA/CINEMA, ETERNA Bleach Bypass, muted cinema stills, filmic image-to-image color grading, cinematic composition, anti-AI image polish, movie screenshots, war/drama/romance/editorial frames, or restrained film color. 适用于用户要求富士 ETERNA、电影感图生图、电影截图、降低 AI 味、低饱和电影调色、电影构图、战争/爱情/剧情/时装片质感等场景。
Rewrite a memory or context file (CLAUDE.md, AGENTS.md, notes) into Honey-terse form to cut per-session input tokens. Backs up first.
Distil accumulated experience records (experiences.jsonl) into updated domain knowledge summaries (knowledge.md) for any chip-design domain. Run after every 10 orchestrator sessions, or on demand when a domain has collected new issue/fix patterns.
同步历史 PRD/需求文档。先修正旧知识文件格式，再从 PRD 中提取业务概念，对照当前代码确认实际实现，合并更新 .repomind/concepts/ 的业务卡片与元数据；必要时再交给 repomind-summary 补充模块侧知识。