Results for “research”

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page.

Extract structured review data from Google Maps search results using the BrowserAct API, enabling local business analysis, reputation monitoring, and competitive benchmarking.

Extract structured best-selling product data from Amazon, including titles, prices, ratings, reviews, sales volume, and promotions, using the BrowserAct API.

Write academic papers with a 12-agent pipeline supporting full drafting, revision, citation checks, and LaTeX/DOCX output across multiple disciplines and paper types.

Build production RAG and semantic search systems with a high-performance vector database written in Rust, supporting hybrid search, filtering, and horizontal scaling.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Train LLMs with reinforcement learning using verl (Volcano Engine RL), supporting RLHF, GRPO, PPO, and other algorithms for scalable post-training with flexible infrastructure backends.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution on local Docker, Slurm HPC, or cloud platforms.

Pretrains large language models from scratch using PyTorch-native distributed training with 4D parallelism (FSDP2, TP, PP, CP) and Float8 support on H100 GPUs.

Map user Jobs-to-Be-Done with functional, emotional, and social dimensions plus outcome expectations to reframe product decisions around user motivations.

Scrapes public web data from LinkedIn, Twitter, GitHub, YouTube, and other sources, sends and reads email, performs deep research, generates images, and searches the web through the DeepAPI service.

Bootstraps a two-part _docs directory (_build/ for technical docs, _public/ for research and proposals) with a CONSTITUTION.md governing the split, and can audit or migrate an existing structure.

Monitors websites, RSS feeds, and e-commerce pages for content changes and price drops, with social listening and custom scraping for competitive intelligence and market research.

Run an AI Lab division meeting with research and build agents (no AI Startup agents). Use when the user requests to "start a lab meeting", "convene the lab", or "run a sprint retrospective for the lab".

Use when a complete research workflow — its instructions, skills, data boundaries, and tool connections — must be assessed for portability across AI agents or environments, so each component is explicitly mapped before migration rather than assumed to transfer.

Extract clean, readable content from one or more URLs using Tavily Extract via AIsa API. Useful for reading full articles without visiting the page. Use when: the user needs web search, research, source discovery, or content extraction.

Search X/Twitter profiles, tweets, trends, lists, communities, and Spaces through the AIsa relay, then support approved posting workflows with OAuth. Use when the user asks for Twitter research, monitoring, or posting without sharing passwords.

This skill should be used when the user asks to "swap tokens", "trade ETH for USDC", "exchange tokens on Uniswap", "buy tokens", "sell tokens", "convert ETH to stablecoins", "find memecoins", "discover tokens", "research tokens", "tokens to buy", "find tokens to swap", "what should I buy", or mentions swapping, trading, researching, discovering, buying, or exchanging tokens on any Uniswap-supported chain. Supports both known token swaps and token discovery workflows (discovery uses keyword search and web search — there is no live "trending" feed). Generates deep links to execute swaps in the Uniswap interface.

Analyze diverse user feedback to identify at least 3 distinct behavioral and needs-based user segments based on jobs-to-be-done, behaviors, and motivations.

Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis for read-only gap analysis.

Analyze Amazon competitor listings by ASIN to produce structured competitive intelligence and strategic opportunity points for your own go-to-market.

Write scientific manuscripts in full paragraphs using IMRAD structure, with citations (APA/AMA/Vancouver), figures/tables, and reporting guidelines (CONSORT/STROBE/PRISMA) for research papers and journal submissions.

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

Generate images from text prompts, perform image-to-image translation, inpainting, and build custom diffusion pipelines using Stable Diffusion models via HuggingFace Diffusers.

Compress large language models using knowledge distillation from teacher to student models, covering temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Scans US equities for daily +20%/-20% movers, classifies catalysts and chart context, updates forward outcomes, and summarizes cohort patterns for research.

Builds a strategic SEO plan for new or existing websites, covering competitive analysis, site architecture, content strategy, technical foundation, and a phased implementation roadmap.

Creates a strategic SEO plan for new or existing websites, covering competitive analysis, site architecture, content strategy, technical foundation, and a phased implementation roadmap.

Use the Python-based ddgs CLI (via `uvx ddgs`) for ad-hoc, unlimited web searches across multiple search engines. Trigger this skill when the user asks you to look something up online, compare sources, or gather search-based research.

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

Route business growth prompts to the right skills. Use when prompts mention fundraising, investors, market research, campaigns, SEO, lead intelligence, social graph ranking, connection optimization, sales outreach, or when the user wants an easy group invocation for growth skills.

Advanced web search via Tavily through AIsa API. Supports search depth, topic filtering (general/news/finance), time ranges, domain inclusion/exclusion, and LLM-generated answers. Use when: the user needs web search, research, source discovery, or content extraction.

Agent A5 - Paradigm & Worldview Advisor - Philosophical foundations for research design. Covers ontology, epistemology, axiology, and methodology alignment. Use when: establishing philosophical foundations, justifying methodological choices, writing positionality statements Triggers: paradigm, 패러다임, ontology, epistemology, worldview, 세계관, philosophical foundations, 철학적 기초

Identify the first beachhead market segment for a product launch by evaluating segments against burning pain, willingness to pay, winnable market share, and referral potential.

Self-host an open-source research notebook with AI-powered note generation, multi-speaker podcast creation, and context-aware document chat, supporting 16+ AI providers.

Analyze customer needs by identifying the 'job' they hire a product to do, covering job statements, forces of progress, and competitive landscapes.