Web Research Agent Skills

Runs evidence-first research workflows, choosing the lightest useful path from search to deep synthesis, and labels facts, inference, and recommendations.

Optimizes content for AI search engines like Google AI Overviews, ChatGPT, and Perplexity by analyzing citability, structure, brand mentions, and technical accessibility, then generating a GEO analysis report.

Searches Polish marketplaces (Allegro, Ceneo, Google Shopping) to compare product prices and delivery options, presents a comparison table, and assists with checkout while leaving final payment to the user.

Traces design decisions and concepts through session history, handoffs, git, and artifacts, producing a chronological timeline report with citations.

Collects market data from Yahoo Finance and Exa, calculates technical indicators, scans watchlists, and generates market analysis reports to identify trading opportunities.

Searches for academic papers, downloads PDFs, and analyzes content through four core research assistant commands.

Finds businesses, software, and service providers for a given industry or workflow using Stripe Directory, and can purchase MPP-supported services with user approval.

Answers factual questions by searching the web, fetching primary sources, and cross-checking claims before citing them.

Reports current weather conditions and forecasts for a city using live data from wttr.in or meteorological services, with the source named.

Produces structured US equity research and trading support: company snapshots, earnings analysis, valuation scenarios, catalysts, risks, and action plans with falsifiable claims.

Searches, downloads, analyzes, and saves research papers using arXiv, Google Scholar, and Zotero.

Researches and recommends programming technologies, libraries, and architectural approaches with verified references from official documentation.

Discovers VC, accelerator, angel, and CVC investors via web search, evaluates thesis fit across four dimensions, and maps approach pathways for outreach.

Guides writing Korean government funding program business plans (사업계획서) from an evaluator's perspective, covering structure, scoring emphasis, and writing principles.

Researches VC funds and partners, providing thesis matching, portfolio analysis, and approach strategy for outreach.

Grounds legal drafting in verified government references across 29+ jurisdictions, providing templates and scaffolding for business formation, employment, and contracts.

Analyzes AI disruption pressure across a business, maps competitive exposure, and produces a 90-day defensive action plan.

Grounds legal drafting in verified government references across 29+ US, EU, and Canadian jurisdictions, with CLI tools for searching templates, fetching metadata, and generating contract scaffolds.

Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.

Analyzes federal contract competitors, incumbents, and obligation trends using live USAspending.gov data via the usaspending MCP, supporting black-hat competitor research and contract-number-first obligation analysis.

Conduct passive OSINT reconnaissance on target organizations using a MITRE ATT&CK framework. Discovers employees, email patterns, subdomains, infrastructure, leaked credentials, and cloud assets with confidence-scored findings.

Transforms a raw product idea into four planning files: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased execution plan with kill criteria.

Retrieve deterministic search results, metadata, and full-document Markdown from arXiv, PubMed/PMC, and US policy corpora with daily freshness checks.

Query Google NotebookLM notebooks using Gemini's source-grounded answers. Automates browser-based authentication, notebook management, and question-answering workflows.

Fans out web searches, fetches sources, adversarially verifies claims, and synthesizes a cited research report.

Refreshes paid media research by auditing platform claims, API policies, and evidence against primary sources, demoting stale or unsupported assertions.

Researches competitor paid-ad presence, messaging, creative, formats, landing pages, and strategic gaps using official transparency libraries and public sources.

Produces a deep research report on a product, company, concept, or person using the Horizontal-Vertical Analysis method, combining a longitudinal narrative with a cross-sectional competitive comparison, and outputs a beautifully formatted PDF.

Finds and exports podcast episode transcripts as cleaned TXT files from YouTube URLs, episode webpages, Apple Podcasts, X/Twitter links, direct audio URLs, or plain titles, with a deterministic decision tree and optional local ASR fallback.

Prüft Fristen, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen im Energierecht für Wärme, Quartier und Fernwärme; liefert eine Fristen- und Risikoampel mit Sofortschritten.

Search and retrieve book details, author information, and bibliographies via the Open Library API from the command line.

Interrogates a plan against real third-party documentation, extracting hard constraints and asking doc-cited questions before producing a constraints appendix.

Explains Solana's architecture and protocol internals, covering the SVM execution engine, account model, consensus, transactions, validator economics, data layer, development tooling, and token extensions using Helius blog posts, SIMDs, and Agave/Firedancer source code.

Search SAM.gov for contract opportunities and registered entities, and query USASpending.gov for federal award data.

Queries CDC open data and WHO Global Health Observatory indicators for public health intelligence, covering disease surveillance, vaccinations, and mortality.

Gather competitive intelligence on companies by searching SEC filings, recent news, federal contracts, and comprehensive profiles through an MCP server.