Research, academic papers, education, and exam prep (4.4K skills)
Grow a wiki by researching queued topics through web, arXiv, and GitHub sources. The loop checks claims against existing pages, writes or updates entries, and queues follow-up questions within budget, page-count, and research-depth limits.
Build a lasting wiki from papers, links, and notes, with Markdown pages that cite their sources. Original material stays separate from compiled explanations, while a full-text search index helps agents retrieve knowledge across sessions.
Search existing wikis for passages relevant to a question and return excerpts with source references. Use it to find recorded knowledge, check citations, and review existing coverage before drafting a new wiki page.
Build an AI or machine learning literature review from a public starting source. Organize real papers into topics and sections, generate a cited Markdown wiki page, and add bibliography records using a configured model provider.
Learn the basic skill format and check whether your skills setup is working. This minimal example responds with a friendly confirmation when you ask to test the setup or invoke the hello world skill.
Collect cryptocurrency headlines from more than 50 sources, then filter by coin, topic, and time range. The skill ranks matching articles by relevance and recency, shows source links, and can export results as JSON for further use.
Plan authorized external reconnaissance through a staged workflow, from asset discovery and enrichment to exposure analysis and reporting. Organize evidence, rate confidence and severity, map identity relationships, and prepare client findings with remediation guidance.
Turn a broad research topic into linked sub-questions, investigate independent questions in parallel, and follow up on important gaps before producing a synthesized report with sources and open questions. The workflow is designed for Claude Code and needs no external API.
Create detailed English prompts for AI image tools to depict ML or RL paper figures in a modern pastel style. Specify white panels, subtle shadows, rounded fonts, colorful tokens, inline illustrations, and flexible layouts.
Turn a paper or reference figure into detailed English prompts for AI image tools. Specify the diagram type, sections, data flows, formulas, dimensions, annotations, and restrained color palette for academic figures.
Use this reference to study the Market Sentiment method and understand its historical implementation notes. It does not fetch live data, call an API, refresh profiles, or create alerts, so it is suited to research rather than current market analysis.
Explain the documented Strategy Builder method for studying option strategies. This reference package does not make API requests, fetch live data, create alerts, or save account records, so it supports method research rather than live strategy analysis.
Explains a focused method for studying prediction markets as a reference. It does not make API requests, fetch live data, create alerts, or save account records, so readers can distinguish a documented technique from measured results.
Explains the volatility smile method as a focused reference for study. It does not connect to an API or fetch live data, allowing readers to learn the documented technique while keeping it separate from measured market results.
Study a reference method for finding supply-chain bottlenecks. It explains the documented approach for research and discussion, while distinguishing a technique from measured results; it does not fetch live data, run API requests, or create alerts.
Explain a documented method for understanding option Greeks, the measures that describe how option values respond to changing conditions. This reference package does not fetch live data or run API requests, so it helps with conceptual study rather than measured analysis.
Study the documented put-spread backtest method as a reference. This skill explains the technique and helps keep documented methods distinct from measured results; it does not fetch market data or run an API analysis.
Study the documented Unusual Options Activity method as a reference. It explains the focused research topic without fetching data, creating alerts, or treating legacy API notes as a current live analysis service.
Run a focused stock analysis through the published AlphaGBM interface. It returns the successful API response with asset identity, dates, units, missing-data flags, and score type, helping you inspect the result without invented demo data.
Break down a published research report into institutional views, original ratings, assumptions, and risks, keeping sources and dates attached. It helps readers verify what the report says and identify follow-up checks without triggering paid research.
Use AlphaGBM to find published research, institutional views, and related assets, then summarize them with sources and dates. The workflow preserves missing information and distinguishes institution opinions from disclosed facts and your interpretation.
Analyze a published news item with AlphaGBM by separating reported claims from impact inferences. Get related assets, evidence limits, and next verification checkpoints from the bundled Python runner, without substituting demo results for unavailable real output.
Use AlphaGBM to research a stock and organize returned fundamentals, sentiment, and risks into supporting and opposing evidence. The result preserves missing data and source dates, then identifies concrete questions to verify next.
Compare two authorized local AlphaGBM research records to identify changes in facts, scores, and judgments. The tool checks whether identities, versions, dates, and units match, and reports gaps without accessing account history or making a new paid query.