glmv-prompt-gen
Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to gener…
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to gener…
上传一条短视频,选择目标画风,把实拍视频转绘成动漫、国漫、水墨、黏土、赛博朋克等风格,同时保留人物、动作和镜头。
Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to describe, caption, summarize, or interpret the c…
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector s...
为已有 AI 短视频做一次聚焦真实感精修,调整光影、材质、饱和度和重复细节,让镜头更自然、更耐看。
用两张审核好的图片生成一条转场视频——从首帧到尾帧做变装、产品揭晓、前后对比、昼夜切换等丝滑转场。
把一张人像和短脚本或语音,制作成适合讲解、公告、课程和产品介绍的数字人口播视频。
AI image generation and editing capabilities, based on Nano Banana (Gemini Image), enable text-to-image, image-to-image, and image editing. Suitable for creative design, marketing materials, social me…
只给一个选题,就拿到口播种草竖屏短片、可自行剪进版本的分镜静图和配音,全程零素材。
把一章小说或故事脚本改编成一组按顺序排好的带旁白竖屏推文视频片段,自动拆分镜、配插画、录旁白,同一个角色在每个镜头里长得一样。
用一首歌的情绪和节奏,制作一个短视觉短片——把音乐片段和视觉方向变成电影感宣传短片,让封面图随音乐动起来,或用松散参考构建氛围视觉。
A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image …
给一条短视频在开头或结尾补上衔接画面——向后续写、向前补长、延长镜头、补全结尾,让画面自然延续。
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
用一张清晰人像照片和一段简短歌曲片段,生成一段照片开口唱歌的短片。
聘才猫 - 简历优化 使用时调用Pincaimao简历优化API,根据目标职位描述自动优化或重写简历内容。需要设置PCM_RESUME_OPTIMIZE_KEY环境变量。
AI Resume Assistant — Polish, customize, export, and score Chinese/English resumes. Supports 40+ check items, a five-dimensional scoring system out of 100 points, and multiple export formats (Word/Mar…
Full Windows desktop control. Mouse, keyboard, screenshots - interact with any Windows application like a human.
从一个定稿的戏剧节拍和参考素材,生成一个电影感的竖屏短剧镜头——纯文本、确认的开场图、首尾两张图,或松散的演员和场景参考均可。
把产品图、人像、照片、插画或 AI 图片变成有明确动作和运镜的短视频。
Official skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equations, inline formulas, and formula blocks. Use…
A complete workflow to convert descriptive text into comic pages. Supports two styles: sketch (black and white line drawing) and color painting (color comics). Can read text from direct input or files…
用一张清晰的宠物照片和一段简短留言或配音,生成一段宠物说话视频。
基于 OpenVINO 与 PP-OCRv4 在本地识别 PDF、扫描件和图片中的敏感信息,输出可审计的风险报告,并在不覆盖原文件的前提下生成脱敏副本。所有内容只在本机处理。