Scan to join WeChat grouppersonjakexiaoNo key required
livestream-engineer
Expert in live streaming, WebRTC, and real-time video/audio
download11deployed_code—star21
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
"digital-twin-sync"
Synchronize construction digital twins with real-time data. Connect BIM models with IoT sensors, progress updates, and field data for live project visualization and monitoring.
download11deployed_code—star57
personjakexiaoNo key required
speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time ap…
download11deployed_code—star23.1K
personjakexiaoNo key required
awq-quantization
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference…
download11deployed_code—star23.1K
personjakexiaoNo key required
inbox-commander
Email triage and organization system for Gmail. Use when user asks to "triage my inbox", "check my email", "process emails", "what needs my attention", "inbox zero", or any request to organize, classi…
download11deployed_code—star12
personjakexiaoNo key required
creating-data-visualizations
Generate plots, charts, and graphs from data with automatic visualization type selection. Use when requesting "visualization", "plot", "chart", or "graph". Trigger with phrases like 'generate', 'creat…
download11deployed_code—star576
personjakexiaoNo key required
"ai-evals"
Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). Use for LLM evaluation, benchmarks, rubrics, error analysis/open coding, and ship/no-ship quality gates for …
download11deployed_code—star4
personjakexiaoNo key required
portfolio-manager-agent
Portfolio allocation and rebalancing optimizer. Manages asset allocation across stocks/cash/bonds, performs periodic rebalancing, and ensures diversification according to market regime and risk tolera…
download11deployed_code—star4
personjakexiaoNo key required
RAG Implementer
Implement retrieval-augmented generation systems. Use when building knowledge-intensive applications, document search, Q&A systems, or need to ground LLM responses in external data. Covers embedding s…
download11deployed_code—star21
personjakexiaoNo key required
easyocr
OCR alternativo a PaddleOCR, excelente en caracteres especiales y múltiples scripts
download11deployed_code—star0
personjakexiaoNo key required
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-th…
download11deployed_code—star23.1K
personjakexiaoNo key required
quantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 fo…
download11deployed_code—star23.1K
personjakexiaoNo key required
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to sound natural and human-written. Based on Wikipedia's "Signs of AI writing" guide. Detects and fixes patterns incl…
download11deployed_code—star7
personjakexiaoNo key required
klingai-image-to-video
Generate videos from static images using Kling AI. Use when animating images, creating motion from stills, or building image-based content. Trigger with phrases like 'klingai image to video', 'kling a…
download11deployed_code—star574
personjakexiaoNo key required
chaterimo
Your Chaterimo API key. Generate at https://www.chaterimo.com/account/api-keys/
download11deployed_code—star4
personjakexiaoNo key required
ai-model-nodejs
Use this skill when developing Node.js backend services or CloudBase cloud functions (Express/Koa/NestJS, serverless, backend APIs) that need AI capabilities. Features text generation (generateText), …
download11deployed_code—star4
personjakexiaoNo key required
databricks-unstructured-pdf-generation
Generate synthetic PDF documents for RAG and unstructured data use cases. Use when creating test PDFs, demo documents, or evaluation datasets for retrieval systems.
download11deployed_code—star943
personjakexiaoNo key required
exif_metadata_analyzer
Analyze EXIF metadata to detect prior editing with Photoshop, GIMP or other editors
download11deployed_code—star0
personjakexiaoNo key required
mamba-architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_…
download11deployed_code—star23.1K
personjakexiaoNo key required
constitutional-ai
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, …
download11deployed_code—star23.1K
personjakexiaoNo key required
adarsh-skill
Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or …
download11deployed_code—star0
personjakexiaoNo key required
"distributed-training-setup"
Configure distributed training setup operations. Auto-activating skill for ML Training. Triggers on: distributed training setup, distributed training setup Part of the ML Training skill category. Use …
download11deployed_code—star574
personjakexiaoNo key required
"Directus AI Assistant Integration"
Build AI-powered features in Directus: chat interfaces, content generation, smart suggestions, and copilot functionality
download11deployed_code—star4
personjakexiaoNo key required
arxiv-reader
A skill to fetch and summarize the content of arXiv papers. Use it when the URL is in the format of arxiv.org/abs/{paperID}. It downloads the PDF and reads it using the Read tool.
download11deployed_code—star4