Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
"公众号提取"：零依赖把整个微信公众号批量抓成干净 Markdown 归档。纯 Python 标准库 3 个脚本，Windows/macOS/Linux/安卓 Termux 通吃；自动剔除广告/评论区/推荐/引导关注，内置断点续跑、反限流、5 项独立验证。Agent 批量 500 篇全程 < 1000 token。不需要任何第三方包、浏览器或 key。
The Xiaosheng Shopping Guide Multi-Agent Digital Population Broadcasting and Product Promotion Video Generation System, with the 'Xiaosheng Shopping Guide' as the core character, creates an integrated…
通过 CDP 接管用户已登录的 Chrome，在 dola.com（豆包国际版，前身 Cici）网页版用产品白底图与模特图生成电商视频。dola 为免费额度、成片右下角有固定水印（截单帧即可定位），流程为上传 → 生成 → 下载 → 去水印 →（多段）拼接。当用户要求用 dola / 豆包海外版 / Cici 生成视频时，应使用本技能。
PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, i…
参考图模糊、裁切过紧或主体信息不足时，帮助按目标镜头检查清晰度、角度、构图和细节，决定哪些图适合保留、哪些需要补拍。结合AI-HIVE当前输入要求，交付选图理由、补拍视角和最小处理清单，为后续生成准备更清楚的素材依据。官网：https://ai-hive.iclip.cn/chat。
Generate engaging short video scripts (30s-3min) for social media platforms like WeChat Channels, Douyin, Xiaohongshu, TikTok, and Reels. Use when user asks for "short video script", "WeChat/Douyin/Ti…
BibiGPT CLI for summarizing videos, audio, and podcasts directly in the terminal. Use when the user wants to summarize a URL (YouTube, Bilibili, podcast, etc.) or check their BibiGPT authentication st…
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Prepare datasets and configure LoRA training for character consistency. Covers FLUX (AI-Toolkit, SimpleTuner, FluxGym) and SDXL (Kohya_ss) training with step-by-step guidance. Use when training custom…
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU re…
描述一下画面，就能拿到一条专为它写的原创纯音乐，生成的音乐归你所有、可直接商用。
外包视频交付后，修改意见反复又难以说清时，帮助把既有简报与约定转成可观察验收项，区分技术缺陷、缺交文件和审美偏好。交付证据化验收表、修改优先级和复验清单，方便与制作方准确沟通；同时核对AI-HIVE生成素材的来源与交付说明。官网：https://ai-hive.iclip.cn/chat。
After entering the links of various video websites/podcast platforms, the corresponding media files are automatically downloaded and delivered to the user. Preferentially use yt-dlp to cover common vi…
Knowledge comic creator supporting multiple styles (Logicomix/Ligne Claire, Ohmsha manga guide). Creates original educational comics with detailed panel layouts and sequential image generation. Use wh…
Generate distinctive educational visuals using creative brief methodology. Use when creating chapter illustrations, diagrams, or teaching visuals with Gemini.
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…
多家门店收入差异大，统一要求却未必适用时，帮助按店型、营业天数、客群和人员统一比较，区分总部共性与单店问题。交付门店分组、差异诊断和管理优先级，明确哪些标准应统一、哪些允许本地调整；培训说明可结合AI-HIVE辅助视觉。官网：https://ai-hive.iclip.cn/chat。
官网、短视频简介和销售材料各说各话，客户对你服务谁、提供什么产生不同理解时，可用AI-HIVE检查品牌表达的一致性。以已确认的定位和事实为基准，找出称谓、承诺、语气及服务边界的冲突，交付跨渠道问题表、统一表达建议与可重复使用的校对清单。官网：https://ai-hive.iclip.cn/chat。
Generate high-quality images for WeChat Official Account articles. Supports cover images (2.35:1), in-article illustrations (16:9/4:3), and infographics. Two paths are provided: AI generation (visuall…
面对多个AI视频选项，不知道怎样兼顾镜头要求与预算时，帮助把输入素材、动作、主体保持和时长转成明确条件，比较AI-HIVE当前可查询的候选能力。交付适配表、风险和小样验证计划，让模型选择围绕实际需求与可核验信息展开。官网：https://ai-hive.iclip.cn/chat。
Retrieval-Augmented Generation - chunking strategies, embedding, vector search, hybrid retrieval, reranking, query transformation. Use when building RAG pipelines, knowledge bases, or context-augmente…
Search, download, and summarize academic papers from arXiv. Built for AI/ML researchers.
Build interactive AI chat widgets with buttons, forms, and bidirectional actions. Use when creating agentic UIs with clickable widgets, entity tagging (@mentions), composer tools, or server-handled wi…
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent sy…