Loading...
Loading...
Found 46 Skills
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".
Expert guidance for natural language processing development using transformers, spaCy, NLTK, and modern NLP techniques.
Implements and debugs browser Language Detector API integrations in JavaScript or TypeScript web apps. Use when adding LanguageDetector support checks, availability and model download flows, session creation, detect() calls, input-usage measurement, permissions-policy handling, or compatibility fallbacks for built-in language detection. Don't use for server-side language detection SDKs, cloud translation services, or generic NLP pipelines.
Implements high-performance local machine learning inference in the browser using ONNX Runtime Web. Use this skill when the user needs privacy-first, low-latency, or offline AI capabilities (e.g., image classification, object detection, or NLP) without server-side processing.
Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols. Implements suicide ideation detection, automated escalation, and crisis resource integration. Use for mental health apps, recovery platforms, support communities. Activate on "crisis detection", "suicide prevention", "mental health NLP", "intervention protocol". NOT for general sentiment analysis, medical diagnosis, or replacing professional help.
Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP tasks, or optimizing transformer inference.
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.
Write and revise ML, CV, NLP, and systems research papers with strong claim-evidence flow. Use when drafting an abstract, introduction, related work, method, experiments, ablations, discussion, or rebuttal; structuring figures and tables; tightening reviewer-facing logic; or preparing a paper for submission. Triggers on: research paper, paper writing, academic writing, ML paper, CVPR paper, NeurIPS paper, ICLR paper, experiments section, rebuttal, abstract rewrite, contribution framing, reviewer response.
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot learning"
Apply Web Scraping with Python practices (Ryan Mitchell). Covers First Scrapers (Ch 1: urllib, BeautifulSoup), HTML Parsing (Ch 2: find, findAll, CSS selectors, regex, lambda), Crawling (Ch 3-4: single-domain, cross-site, crawl models), Scrapy (Ch 5: spiders, items, pipelines, rules), Storing Data (Ch 6: CSV, MySQL, files, email), Reading Documents (Ch 7: PDF, Word, encoding), Cleaning Data (Ch 8: normalization, OpenRefine), NLP (Ch 9: n-grams, Markov, NLTK), Forms & Logins (Ch 10: POST, sessions, cookies), JavaScript (Ch 11: Selenium, headless, Ajax), APIs (Ch 12: REST, undocumented), Image/OCR (Ch 13: Pillow, Tesseract), Avoiding Traps (Ch 14: headers, honeypots), Testing (Ch 15: unittest, Selenium), Parallel (Ch 16: threads, processes), Remote (Ch 17: Tor, proxies), Legalities (Ch 18: robots.txt, CFAA, ethics). Trigger on "web scraping", "BeautifulSoup", "Scrapy", "crawler", "spider", "scraper", "parse HTML", "Selenium scraping", "data extraction".
dontbesilent AI writing feature recognition. It scans for AI-generated traces in copy and outputs a detection report. By default, it only performs diagnosis without modification. Trigger methods: /dbs-ai-check, /AI检测, "Help me check if there is AI-like tone", "Detect AI features" AI writing fingerprint detection. Scans copy for AI-generated patterns and outputs a diagnostic report. Diagnosis only by default. Trigger: /dbs-ai-check, "check for AI writing", "does this sound like AI"