Research & Learning skills

Turn research ideas and literature into a structured funding proposal. Supports KAKENHI and other funding programs, guiding literature positioning, research aims, methods, timelines, and budget justification, with external review to identify weaknesses in the draft.

• Drafting a KAKENHI proposal from a research idea
• Explaining gaps relative to literature and funded projects
• Organizing research aims, annual plans, and budget justification

Improve research through up to four rounds of external language model review, fixes, and reassessment. Use an OpenAI-compatible API to identify weaknesses, prioritize changes, and keep a cumulative record of reviewer responses, actions, and experiment results.

• Identify weaknesses before submitting research
• Revise research using an external model's feedback
• Track review scores, changes, and experiment results

Search blogs, documentation, news, and research papers with Exa, retrieving highlights, full text, or summaries alongside results. Filter by date or domain, or use a URL to discover similar pages.

• Search beyond academic databases
• Collect page text or summaries with search results
• Find pages similar to a known URL

Stress-test a paper with a focused rejection argument, then have a separate reviewer assess each objection against the current text. The report identifies unresolved weaknesses, their severity, and priority fixes for submission or rebuttal preparation.

• Stress-testing a theory paper before submission
• Preparing responses to the strongest reviewer objection
• Checking whether the title overstates the results

Search open-access academic papers through DeepXiv, then move from brief summaries to section outlines and individual sections. Find trending papers and focus reading on the parts needed to answer a research question.

• Find papers on a research topic
• Read only a paper's Introduction section
• Explore papers trending over the past two weeks

Search academic papers by topic, year, citation count, and free availability. Organize abstracts and publication details into a comparison table, and investigate author affiliations, funding sources, and citation links through OpenAlex.

• Finding papers on a research topic
• Filtering papers available to read for free
• Checking author affiliations and research funding

Search Zhihu, a Chinese knowledge-sharing platform, for answers, articles, people, and topics. Filter by content type and creation date, sort results, and collect structured records containing excerpts, authors, votes, and links across multiple pages.

• Finding Zhihu answers and articles on a topic
• Comparing highly upvoted answers
• Collecting recently created content

Check mathematical expressions, solve equations, and search bounded ranges for counterexamples using symbolic and numerical libraries. Record assumptions, commands, and results so calculations can be repeated, while keeping computational evidence distinct from general mathematical proof.

• Checking identities and integrals with exact arithmetic
• Searching a defined range for counterexamples
• Cross-checking numerical results at higher precision

Navigate a smart contract security knowledge base in a suggested reading order. Find guides covering audit preparation, vulnerability patterns, code searches, reproduction tests, reporting, case studies, and AI tools without losing track of the next topic.

• Finding a starting point for learning smart contract auditing
• Following guides from preparation through reporting
• Locating audit case studies

Turn scattered formulas and theory notes into a derivation that can be checked step by step. Keep definitions and assumptions consistent, distinguish exact identities from approximations, and make hidden conditions and limits explicit.

• Organize scattered formulas and theory notes
• Trace the steps behind an algebraic identity
• State conditions and error orders for approximations

Helps write and review mathematical proofs in natural language. It clarifies assumptions, maps dependencies between claims and lemmas, checks counterexamples and edge cases, and produces a traceable draft that identifies unresolved gaps or necessary changes to the statement.

• Filling gaps in a mathematical proof draft
• Mapping dependencies between claims and lemmas
• Searching for counterexamples and edge cases

Turn mathematical claims into definitions, lemmas, and proofs for Lean 4 and Mathlib. Check proofs with Lean’s trusted core, separately review whether the formal statement matches the original claim, and record verification evidence.

• Verifying an important lemma with Lean 4
• Breaking a theorem into definitions and supporting lemmas
• Checking proofs for sorry, admit, and unauthorized axioms

Clarify the next step in a mathematical research task by identifying what is blocking progress. Select one specialist skill for discovery, derivation, computation, proof, or formal verification, with required inputs and clear stopping conditions.

• Decide where to start with an open mathematical question
• Find the next step when papers, formulas, and code are mixed
• Choose between derivation, computation, proof, and formalization

Shape broad mathematical interests into precise research questions. Search prior work on definitions and theorems, record traceable sources, map supporting and conflicting evidence, and identify gaps that could lead to testable conjectures.

• Tracing a theorem’s variants and related work
• Checking prior work on an integer sequence
• Defining search terms and the scope of a research question

Research current news and financial markets through Helium MCP. Compare coverage using bias scores, read summaries combining different perspectives, retrieve live prices and AI analysis, estimate options values, and search trending memes.

• Compare news coverage and bias across sources
• Read a synthesis of different views on a current topic
• Research stock, ETF, and cryptocurrency prices

Gather information from multiple Notion pages and combine it into briefs, summaries, comparisons, or detailed reports. Include citations and source links, identify missing or conflicting evidence, and document findings in Notion.

• Summarize information scattered across Notion
• Compare options using existing internal sources
• Prepare reports with citations and source links

Research private companies with parallel agents covering business, finances, competition, governance, technology, and alternative evidence such as hiring trends. Combine findings into a valuation report that separates verified facts, estimates, conflicting sources, and unknowns.

• Researching a private company's business and risks
• Comparing funding valuations with estimated business value
• Finding operating signals in hiring and patent data

Research a defined topic within agreed limits and produce a cited report that distinguishes evidence, inference, contradictions, and gaps. Public web access requires consent, and saving findings or merging them into existing Obsidian notes receives separate review.

• Investigate a topic within agreed limits
• Compare conflicting claims and their sources
• Create a cited research report

Answer questions using a selected Obsidian vault, a collection of linked notes, without changing its files. Choose a search depth and receive answers with page references, clearly identified uncertainty, conflicting evidence, and any missing information.

• Find an answer in stored Obsidian notes
• Summarize knowledge in a vault
• Compare conflicting notes and their evidence

Create a small interactive HTML playground to explore how something works. It packages an explanation, simulation, or simple game into one screen, with clearly labeled keyboard controls and no network requests or external assets.

• Explore a mechanism through interactive controls
• Step through a simulation on one screen
• Explain an idea through a simple game

Search Notion for answers in existing documents and meeting notes. Read the relevant pages, identify the main reference using available evidence, and answer with source links while clearly reporting conflicting information or gaps.

• Look up internal policies and procedures in Notion
• Find the main reference among duplicate documents
• Check specifications or meeting decisions before writing

Explore research directions through ten structured thinking frameworks, then rank ideas by their importance, clarity, and feasibility. Turn a vague interest into a focused proposal with a short explanation, candidate experiments, and an initial feasibility study.

• Exploring a new research direction
• Finding fresh angles on a stalled project
• Assessing an early research idea

Creates figures for machine learning papers from draft text or experiment data. Extracts components for Gemini-generated diagrams, chooses suitable charts with matplotlib or seaborn, and adjusts colors, fonts, and export formats for publication.

• Turn a method section into an architecture diagram
• Create comparison charts from experiment results
• Plot training loss and accuracy over time

Turn papers, code, experiment logs, and notes into an ARA, a structured research package for AI agents. Organizes claims, evidence, verification plans, code stubs, and research decisions, then checks coverage and consistency across the generated files.

• Organize a paper and its code into a research package
• Link research claims to tables, figures, and verification plans
• Preserve failed approaches and research decisions