리서치·학습 스킬

Search PubChem by compound name, CID, or structure notation, then retrieve molecular properties, identifiers, and bioactivity records. Find compounds with similar or matching substructures, compare batches of compounds, and download structure data for cheminformatics workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Looking up a compound from its name or structure
• Comparing molecular properties across compounds
• Finding similar compounds or matching substructures

Choose coding interview problems by company, difficulty, and problem-solving pattern. Track solved questions and weak areas, then get focused recommendations or a study schedule for interview preparation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a next problem based on practice progress
• Practicing questions for a specific company
• Finding weak algorithm topics to review

Retrieve and parse LeetCode problems with statements, examples, constraints, hints, difficulty, tags, and related questions. Use it to gather structured material for algorithm practice and interview preparation, including code templates and available problem statistics.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Gather details for an algorithm practice problem
• Find problems by topic, difficulty, or keyword
• Review daily challenges and related questions

Practice a coding interview through a timed problem, clarification, approach discussion, implementation, testing, and optimization. The skill can provide escalating hints, follow-up questions, realistic interviewer responses, and prompts to evaluate communication and performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Practicing a timed coding interview
• Getting hints without revealing the full solution
• Rehearsing follow-up problem variations

Turn an algorithm problem and its solution into a clear walkthrough for study, interviews, or documentation. Explain the strategy, code, time and space costs, edge cases, common mistakes, and alternative approaches, with optional visuals or interview-style formatting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing an explanation for an algorithm interview
• Learning how a solution works step by step
• Documenting an implementation and its complexity

Build and review algorithm correctness proofs using methods such as induction, contradiction, and loop invariants. The skill helps structure each argument, explain termination, and identify gaps in a partial proof or justification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Proving an algorithm correct by induction
• Writing a loop invariant proof
• Reviewing a partial proof for logical gaps

Analyze dynamic programming code and transitions, then apply suitable techniques such as convex hull trick, divide and conquer, Knuth, or monotonic queue optimization. It can also reduce memory with rolling arrays or bitmask compression and explain the resulting complexity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Speeding up a slow dynamic programming solution
• Reducing memory use in a DP implementation
• Choosing an optimization for a recurrence

Work with AtCoder contests and problems by fetching translated statements, difficulty ratings, editorials, and submission history. Submit solutions, join virtual contests, and review user statistics to track practice progress and identify areas to improve.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting problems and translations for a contest
• Checking a problem's difficulty rating
• Submitting a solution and viewing its result

Organize solved CSES Problem Set problems by topic, connect them to chapters in the Competitive Programmer’s Handbook, and identify gaps. Get progress reports and suggestions for what to solve next as you build your algorithm skills.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracking solved CSES problems by topic
• Finding a suitable next problem
• Reviewing progress and knowledge gaps

Use the official Codeforces API to retrieve contest problems, problem sets, submissions, standings, and user rating history. It supports contest practice and progress tracking, with API rate limits and authentication where required.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting problems for a specific contest
• Finding problems by tags or difficulty
• Reviewing submissions and rating history

Turn algorithm execution into visual steps, showing how arrays, trees, graphs, and dynamic programming tables change. Generate formats such as ASCII, SVG, GIF, or HTML to explain concepts, inspect behavior, or support debugging.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explaining sorting or search step by step
• Showing graph traversal or shortest-path execution
• Visualizing dynamic programming table changes

The listed concept covers coordinating web searches, synthesizing sources, forming hypotheses, and generating structured research reports. Its implementation is marked as pending, so specific workflows and capabilities are not yet described.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a structured research workflow
• Combining findings from multiple sources
• Drafting hypotheses from research material

Answer trivia and factual questions using general knowledge, commonsense reasoning, and analogy across different subjects. The supplied material describes this skill as a stub, so its implementation details are not available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Answer a general trivia question
• Make a commonsense inference
• Explain a topic through analogy

Create a personalized daily news brief using interests from a COG profile and context from its knowledge vault. It searches for recent sources, checks claims against source material and other reports, and labels each item with a confidence level.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting a brief based on a COG profile
• Reviewing developments from the past week
• Checking claims against source material

Capture information from URLs by extracting titles, summaries, key takeaways, and quotes. Assess source credibility, classify insights, and save them as Markdown in suitable vault sections with links to related entries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving an article's key points to a knowledge vault
• Assessing the credibility of a web source
• Classifying insights by topic or domain

Research public repositories for SKILL.md files and reusable workflows. It classifies projects by type and records findings, including processes and integration ideas that may be useful elsewhere.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Survey public repositories for agent skills
• Research a repository’s workflow patterns
• Identify reusable procedures in external skills

Query the Atlas knowledge graph through its MCP tools to inspect nodes, relationships, node and edge types, clusters, statistics, and wiki pages. Use the results to add best-practice context to systems already found by scanning real sources such as Azure, repositories, or directories.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Looking up a graph node after scanning a real system
• Checking relationships around a system component
• Reviewing graph types, clusters, or statistics

Break a research question into independent sub-queries and dispatch 5–10 agents in parallel. The skill combines their findings, identifies agreement and conflicts, checks results against the codebase, and flags low-confidence conclusions for human review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate an unfamiliar area of a codebase
• Gather findings from several independent research threads
• Research a topic before writing a specification

Research topics on the web by refining search queries, filtering results, and checking key facts across sources. It synthesizes findings, evaluates source credibility, and highlights contradictions or gaps for competitive analysis, fact-checking, and trend research.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Researching a topic across multiple sources
• Checking claims and cross-referencing facts
• Comparing competitors and market positions

Make complex code, algorithms, and system behavior easier to understand through clear summaries, step-by-step walkthroughs, diagrams, pseudocode, and examples. This skill is useful for learning, onboarding, debugging discussions, and explaining design patterns to developers at different levels.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding an unfamiliar codebase
• Explaining an algorithm step by step
• Preparing an onboarding walkthrough

Searches Notion pages for a topic, combines relevant findings, and creates a structured document as a new Notion page. It can produce a brief, summary, or fuller report with links to source pages, conclusions, and suggested next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing findings scattered across Notion pages
• Preparing a brief or report from internal research
• Comparing information across multiple sources

Chinese opera playwriting for the qupai (曲牌体) system — 元杂剧, 明清传奇, 昆曲, 川剧高腔, where sung text is filled into fixed tune patterns (填词) rather than built from paired lines varied by metre. Covers stage vs study (李渔 vs 吴梅/王季烈), the 清曲/剧曲 switch, the zaju branch (四折一楔子, one 宫调 and one rhyme per act, 一人主唱, 题目正名), the chuanqi branch (出, 副末开场, 南北合套, 集唐下场诗), tune-filling (格律, 前腔/换头/幺, 衬字, 务头, 尾声, 四十禁), the seventeen 宫调 and their affects, 套数, 排场 alternation, the spoken-to-sung cue, 帮腔, adaptation, and modern practice. From 李渔《闲情偶寄》, 吴梅《顾曲麈谈》《曲学通论》, 王季烈《螾庐曲谈》, 孔尚任's 凡例, 关汉卿, 汤显祖, 魏明伦. Use when writing or revising a 曲牌体 script, choosing a 宫调 for an emotion, laying out a 套数, filling one tune pattern, writing a zaju act or a chuanqi scene, cutting an old 传奇 into a playable version, writing a modern qupai opera, or judging whether a famous script's prosody may be copied. Not for 京剧/豫剧/越剧, which are the banqiang system; see sw-chinese-opera-banqiang.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up a paper-search MCP server through Docker MCP and add its usage guidance to a CLAUDE.md file. The server can search academic sources such as arXiv, PubMed, Semantic Scholar, and CrossRef, with tools to download and read some papers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up academic paper search for a project
• Searching across several scholarly databases
• Downloading and reading supported research papers

Work through an FPF cycle for a problem: develop competing hypotheses, check their logic and evidence, audit trust, and produce a decision record with a recommendation and rationale.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing competing approaches to a problem
• Recording evidence behind a decision
• Reviewing hypotheses before implementation