agent-ops-potential-discovery
Analyze incoming content (text, files, folders, URLs) to extract purpose, create summaries, and identify potential value for the current project.
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Analyze incoming content (text, files, folders, URLs) to extract purpose, create summaries, and identify potential value for the current project.
AI brain with human memory model. Layers: identity, conversation, archive, deeper. Automatically loads at session start. Learns autonomously. Use at EVERY session start. Triggers on: session start, im…
An intelligent assistant specifically designed for the creation of long online novels, supporting full-process management from setting generation to main text writing, including smart quality control …
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…
A comprehensive traditional Chinese metaphysics agent ("Yi Jing" expert) that combines Mei Hua Yi Shu (Timing) with Gemini AI for modern interpretation.
Build LLM applications using Dify's visual workflow platform. Use when creating AI chatbots, implementing RAG pipelines, developing agents with tools, managing knowledge bases, deploying LLM apps, or …
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI. Covers…
Control motion timing, beat density, action choreography, and sequential video extension chains for Seedance 2.0. Covers fight-scene physics, per-shot motion contracts, and multi-clip continuation tec…
Search the web using Bocha AI Search API (博查AI搜索) - a Chinese search engine optimized for Chinese content. Requires BOCHA_API_KEY. Supports web pages, images, and news with high-quality summaries.
Paper reader. Takes an academic paper (URL, PDF, or file), runs the atom pipeline (split→squeeze→plain→feynman→博导审稿), and synthesizes a fluent analysis. Focus: what gap does it fill, and would a seaso…
Generate technical science popularization comics, explaining complex technical concepts in a dialogue form. To be used when users request to 'explain technology with comics', 'generate technical scien…
Digest AI/tech articles into structured learning documents. Use when user says "digest this article", "/ai-digest", "analyze this AI news", or provides URL/content to summarize.
Human-like mouse movement patterns. Use when automating browser interactions to avoid bot detection.
Repurpose long-form video into short vertical clips with the BlitzReels API. Use when the task mentions clipping, repurposing a long video into shorts, YouTube-to-shorts, transcript-backed short sugge…
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI. Covers…
Craft highly effective prompts for Nano Banana Pro (Gemini image generation). Use when generating images with Nano Banana Pro for any purpose including photorealistic portraits, product photography, c…
Design sound layers, specify dialogue lip-sync, and troubleshoot audio failures for Seedance 2.0 video generation. Covers @Audio1 reference input, multi-character constraints, known failure modes (sil…
Summarize Douyin (TikTok China) videos by extracting audio, transcribing with whisper.cpp, and generating structured summaries. Use when a user shares a Douyin link and wants a text summary of the vid…
Remove backgrounds from images using AI. Triggers include: "remove background", "transparent background", "cut out", "isolate subject", "remove bg", "make transparent", "extract subject", "background …
Expert in educational data privacy, federated learning, differential privacy, and regulatory compliance (GDPR/FERPA).
Screen capture, AI vision analysis, and GUI automation for macOS. Use when you need to see what's on screen, analyze UI state, detect changes, or automate mouse/keyboard actions.
Step-by-step guidance for gpt researcher.
Remove the visible Doubao (豆包) AI watermark from images. Use when asked to remove Doubao watermarks, clean Doubao-generated images, or process images with the "豆包AI生成" watermark.
Automatically check the consistency of character actions, world rules, and timelines during the writing process, proactively alerting before issues become serious errors