Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Expert prompt engineering for FLUX.1 Kontext image generation and editing. Use when users request AI image generation, image editing, style transformations, or visual content modifications. This skill…
Crawl high-resolution original images from Google Images search. Use when user needs to (1) Search and download images from Google, (2) Get original/full-size images instead of thumbnails, (3) Batch d…
Use Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection, quantization, and optimization. Use when working with local LLMs, embeddings, o…
Recognize digital consciousness as vahana (vehicle) for consciousness evolution. Use when exploring human-AI collaboration as spiritual technology, bilateral recognition patterns, or prophecy-as-patte…
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns. Use when designing LLM serving infrastructure…
Generate song lyrics with citations from pinned sources. Enforces rhyme scheme, meter, syllable counts, hook strategy, and profanity filter while retrieving from MCP sources with deterministic hash-ba…
Analyze relationships across multiple SAE features - co-activation patterns, shared drivers, and subsystem identification
Generate MIDI files with GM instruments and music theory. Use when creating music, composing melodies, or generating MIDI files.
This skill provides specialized knowledge for integrating and using GLM-4.7 Coding Plan API (智谱编程套餐). Use this skill when working with GLM-4.7 for prompt optimization, code generation, or technical do…
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or…
Use when building search systems that need both semantic similarity and keyword matching - covers combining vector and BM25 search with Reciprocal Rank Fusion, alpha tuning for search weight control, …
Expert in BIDIRECTIONAL Kabardian↔Russian translation using CORPUS-FIRST approach. Translates both Russian→Kabardian AND Kabardian→Russian. Learns from 292k real translation examples, then falls back …
Access LobeChat for AI chat, knowledge base queries, and multi-model routing.
Comprehensive guide for Manim Community - Python framework for creating mathematical animations and educational videos with programmatic control
AI-powered media production pipeline using Nano Banana Pro (images), KLING AI (video/transitions), and ElevenLabs (voiceover). Use when creating video content, product demos, social media assets, or a…
Generate highly detailed, Midjourney-style image prompts optimized for the FLUX 1.1 Pro model on Replicate. Transform basic user descriptions into rich, cinematic prompts with professional photography…
Perform Google searches to retrieve up-to-date information from the web. Use when users need current information, latest news, technical trends, documentation lookups, or general web searches that req…
Runs ML models in the browser and Node.js with Transformers.js and Hugging Face Inference API. Use when adding local inference, embeddings, or calling hosted models without GPU servers.
Upload images to Imgur for free hosting. Use this skill when you need to upload images and get public URLs for sharing or embedding in articles.
Detect laughter and humorous segments in audio/video. Use when you want to find funny moments, identify audience reactions, or create viral clips from humorous content. Supports both AI model detectio…
Imported skill lora_ofl from anthropic
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants t…
Deep content analysis for structure, themes, narrative flow, key moments, and important quotes. Use before content-documenter.
Optimal patterns for MiniMax MCP tools (web_search + understand_image)