Scan to join WeChat grouppersonjakexiaoNo key required
arxiv
Search, download, and summarize academic papers from arXiv. Built for AI/ML researchers.
download55deployed_code—star0
Skill Directory
AI Skill Directory
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
personjakexiaoNo key required
style-detector
Detect the user's writing style requirements and load the corresponding guide. Automatically activate when the user mentions keywords such as colloquial, down-to-earth, authenticity, literary quality,…
download52deployed_code—star0
personjakexiaoNo key required
imgsvc
Image search and download skill, to search and download images from the web
download50deployed_code—star27
personjakexiaoNo key required
comfyui-prompt-engineer
Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when g…
download49deployed_code—star21
personjakexiaoNo key required
nanobanana-ppt-skills
AI-powered PPT generation with document analysis and styled images
download47deployed_code—star219
personjakexiaoNo key required
image2prompt
Analyze images and generate detailed prompts for image generation. Supports portrait, landscape, product, animal, illustration categories with structured or natural output.
download45deployed_code—star1
personjakexiaoNo key required
video-engineer
Expert in video processing, streaming protocols (HLS/DASH/WebRTC), and FFmpeg automation. Specializes in building scalable video infrastructure.
download44deployed_code—star51
personjakexiaoNo key required
divination
Structured fortune-telling workflow skill using MCP tools. Use when users ask for divination, 八字/四柱, 六爻, 紫微斗数, 塔罗, 大运, 运势/流年, or want standardized解读流程 (e.g., 八字先看身强弱与喜用神再看大运流年). Enforce fixed analysis…
download44deployed_code—star17
personjakexiaoNo key required
qwen-omni-multimodal
A full-modal skill based on Alibaba Cloud's BAILIAN Qwen3.5-Omni, supporting text, image, audio, and video understanding, as well as text/speech output. Use this skill when users need to analyze image…
download54deployed_code—star0
personjakexiaoNo key required
Ocr Paddleocr
PaddleOCR is a powerful, open-source OCR toolkit that supports multi-language
download51deployed_code—star1
personjakexiaoNo key required
ai-news-zh
Automatic collection and push of Chinese AI tech daily. Grabs the latest AI news from English sources like The Verge, Wired, TechCrunch, translates and organizes them into Chinese, then pushes by cate…
download50deployed_code—star0
personjakexiaoNo key required
seedance
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频",…
download48deployed_code—star0
personjakexiaoNo key required
novelweave-workflow
A complete workflow for novel creation using NovelWeave, including command usage, best practices, and efficient creation techniques. Suitable for planning novel projects, organizing the creative proce…
download47deployed_code—star0
personjakexiaoNo key required
prompt-engineering-helper
Skills for optimizing and testing LLM prompts. We will conduct performance evaluation of prompts, propose improvements, perform A/B testing, apply best practices, and verify reproducibility.
download45deployed_code—star123
personjakexiaoNo key required
prompt-optimizer
This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured…
download44deployed_code—star6
personjakexiaoNo key required
media_comprehension
An intelligent assistant specially for understanding images, audio, and video files. Use when: - Images: Recognize, describe, and interpret visual content. - Audio: Transcribe speech and analyze audio…
download44deployed_code—star1.1K
personjakexiaoNo key required
nanobanana-prompt
This skill should be used when the user asks to "generate image", "create image with nanobanana", "write image prompt", "make icon/pattern/sticker", or "image generation". Crafts effective prompts for…
download53deployed_code—star0
personjakexiaoNo key required
stt-transcription
Speech-to-text transcription using multiple engines (Whisper, Google Speech, Azure, AssemblyAI). Record audio, transcribe files, real-time transcription, speaker diarization, timestamps, and multi-lan…
download50deployed_code—star0
personjakexiaoNo key required
baoyu-translate
Translates articles and documents between languages with three modes - quick (direct), normal (analyze then translate), and refined (analyze, translate, review, polish). Supports custom glossaries and…
download50deployed_code—star0
personyangzdpssoftNo key required
抖音流量分配大盘
抖音短视频运营增长助手适合内容创作者、运营、品牌方、电商在用户提供了抖音内容链接时使用，帮助基于输入材料生成情绪和舆情判断、用户画像和意图信号、运营建议和回复建议。
download48deployed_code—star0
personjakexiaoNo key required
model-fallback
Automatic model degradation and failover. When the primary model request fails, times out, hits rate limits, or depletes its quota, it automatically switches to a backup model to ensure service contin…
download46deployed_code—star19
personjakexiaoNo key required
Qwen-Ollama
Using Qwen 2.5 models via Ollama for local LLM inference, text analysis, and AI-powered automation
download45deployed_code—star123
personjakexiaoNo key required
bilibili-subtitle
Extract subtitles from Bilibili videos, transcribe videos without subtitles, and generate structured summaries. Trigger conditions: Bilibili URL (bilibili.com), BV ID (BV1xxx), or requests like "extra…
download44deployed_code—star5
personjakexiaoNo key required
stock-copilot-pro
OpenClaw stock analysis skill for US/HK/CN markets. Combines QVeris data sources (THS, Caidazi, Alpha Vantage, Finnhub, X sentiment) for quote, fundamentals, technicals, news radar, morning/evening br…
download43deployed_code—star4