Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Convert the video script into a more conversational style that is better suited for actual recording, removing formal language and adding a sense of naturalness and friendliness. Use this skill when t…
Agent Workflow Designer
YOLO (You Only Look Once) is a state-of-the-art object detection model
AI agent self-correction mechanisms enable agents to detect errors, validate
Analyze the content of the article and generate illustrations where visual aids are needed to assist understanding. The illustrations can be used to supplement information, concretize concepts, or gui…
Use ONLY when user wants to search for, find, or download free stock PHOTOGRAPHS. Searches Unsplash, Pexels, or Pixabay. NOT for fonts, music, audio, videos, icons, vectors, or any non-photo media.
Observe user interaction patterns, extract per-session facets, update a dual-matrix soul state, and periodically synthesize a personalized Soul profile for better collaboration.
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, optimizing for cost or latency, implementing long-running agent systems, agents…
Eliminate AI-generated writing patterns that erode reader trust. Activate when writing articles, documentation, press releases, or any content where AI patterns would undermine credibility. Essential …
Manages AI gateway for routing, securing, and monitoring AI service requests in ML operations.
Comprehensive guide for text embedding models and usage. This skill covers
TinyML Microcontroller AI enables deployment of machine learning models
Simulate a scenario where multiple AI agents collaborate in a meeting to discuss and make decisions. It is suitable for scenarios that require analyzing problems from multiple professional perspective…
Optimize and prepare 3D assets for web delivery. Use this skill when working with GLTF/GLB files, compressing 3D models, optimizing textures, setting up Blender exports, or preparing assets for Three.…
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integr…
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
Analyze incoming user requests to detect intent, request type (design/validate/debug/document), complexity level, and identify vague requirements or buzzwords that need clarification. Use when cto-orc…
OpenAI Whisper API: audio transcription, translation, structured output, large file handling
Video upload and processing handles file uploads, transcoding, thumbnail
AI Audit Trail & Accountability is a system that records and tracks
A product video creation system with 10 intelligent agents working collaboratively, featuring a full-process quality loop (creation → quality inspection → feedback iteration), and mandating the use of…
An AI interview-style content creation system. It's not written by a human, nor is it automatically generated by AI, but rather, after analysis by AI, the person is interviewed and the content is writ…
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding r…