Content creation
youtube-cover-nano-banana
Create high-converting YouTube thumbnail concepts, overlay text, image prompts, and optional AI-generated cover images from raw titles, hook...
youtube-transcribe
Transcribe YouTube videos with smart fallback: extracts captions first (fast, free), falls back to local Whisper transcription when no capti...
zhihu-cli
Command-line tool for searching, reading, and interacting with Zhihu (知乎). Supports hot topics, content search, article reading, user info...
ai-news-poster
Generate fixed-template daily AI news posters from five news items. Use when the user asks to create a poster, social card, or image summary...
ai-text-humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on...
animegarden
Anime Garden is a anime torrent resources aggregation platform, which is also a third-party mirror of 動漫花園, 萌番组, and ANi. Use when re...
autochatlogger
自动记录对话消息至 workspace/chat/YYYY-MM-DD.md,按需创建文件,始终追加不覆盖。
baoyu-image-gen
AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential b...
better-soul
Write powerful SOUL.md files for AI agents. Use when creating, revising, or improving SOUL.md (the personality document for AI agents). Base...
bpm-finder
Use this skill when the user needs BPM finder help inside Codex, including tap tempo estimation, BPM conversion, tempo normalization, lightw...
bullet-rewriter
Rewrite raw experience descriptions into stronger, clearer, and more job-relevant resume bullets.
chaos-engineer
Use when designing chaos experiments, implementing failure injection frameworks, or conducting game day exercises. Invoke for chaos experime...
chinese-novelist-skill
分章节创作引人入胜的中文小说。支持各种题材(悬疑/言情/奇幻/科幻/历史等),支持10-50章长篇创作,每章3000-5000字,结尾设置悬念钩子。强调深度润色去除AI痕...
cloud-architect
Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, c...
convertagent
Use ConvertAgent for file format conversions through the local CLI. Trigger for any request to convert files (documents, images, audio, vide...
cto-playbook
CTO & Engineering Excellence Playbook. Use for: architecture decisions, tech stack selection, database choices, API design, DevOps/CI-CD, co...
document360
Document360 integration. Manage Projects, Users, Roles. Use when the user wants to interact with Document360 data.
edison-youtube-full
Complete YouTube toolkit for agents: search videos, fetch metadata, browse channels and playlists, and pull transcripts. Use when you need c...
book-write
全流程小说创作工程化助手。专业、严谨、可落地的小说创作管理与内容生成系统,帮助用户从零到一完成高质量、强逻辑、人设稳定、剧情闭环的小说创作。当...
content-deai-engine
为小红书、X、知乎等平台生成“去 AI 味”的内容重写与新稿产出技能。用于用户要求内容更像真人表达、减少模板腔、提升口语感和观点力度的场景;也用于...
exr
Work with OpenEXR files — inspect channels, extract beauty/RGB passes, decode cryptomatte segmentation (material, object, asset), convert c...
felo-youtube-subtitling
Fetch YouTube video subtitles/captions using Felo YouTube Subtitling API. Use when users ask to get YouTube subtitles, extract captions from...
find-reference-video
从 frameset.app 搜索视频参考片段,找到合集页面和原视频链接。用于: (1) 根据关键词搜索广告/电影片段参考,(2) 获取原视频 YouTube/Vimeo 链接,(3) 下载...
gemini-watermark-remover
Remove visible Gemini AI watermarks from images via reverse alpha blending. Use for cleaning Gemini-generated images, removing the star/spar...
geminipdfocr
Extract text from PDFs using Google Gemini OCR. Use when extracting text from PDFs, performing OCR on scanned documents, or processing image...