論文

Use when encountering any bug, test failure, or unexpected behavior (including race conditions, deadlocks, concurrency issues) - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) with specialized techniques for deep call stack tracing and concurrency debugging

Search the web for content matching a query with AI-powered semantic search. Use for finding relevant web pages, research papers, news articles, code repositories, or any web content by meaning rather than just keywords.

Generate answers to questions with structured output using AI search and synthesis. Use when you need factual answers with citations from web sources, or when you want to extract specific structured information in response to a query.

Perform statistical hypothesis testing, regression analysis, ANOVA, and t-tests with plain-English interpretations and visualizations.

論文PDFをページ単位で画像化・テキスト抽出・和訳し、メモに出力するスキル。さらに章ごとの要約と新規性分析も自動生成。ユーザーが「論文を翻訳して」「PDFをページごとに翻訳」「この論文を日本語にして」などと指示した時に使用。ClaudeCLIを使って各ページのテキストを和訳する。

Generate publication-ready scientific figures for research papers.Use this skill when:- Creating any figures for manuscripts (Nature, Science, Cell quality)- Generating data plots from CSV/Excel/JSON datasets- Creating conceptual diagrams, flowcharts, or schematics- Composing multi-panel figures with letter labels (A, B, C, D)- Visualizing architectures, timelines, or workflowsThis skill handles THREE types of figures:1. DATA PLOTS - Line, scatter, bar, violin, heatmap, etc. from tabular data2. SCHEMATICS - AI-generated conceptual diagrams and illustrations3. COMPOSITIONS - Multi-panel figures combining plots and/or schematicsPrerequisites:- For plots: pandas, matplotlib, seaborn- For schematics: OPENROUTER_AI_API_KEY environment variable- For composition: matplotlib or PIL

Rigorous hypothesis testing process for data analysis - formulate hypotheses before looking at data, design tests, analyze systematically, interpret with skepticism

Systematic methodology for debugging bugs, test failures, and unexpected behavior. Use when encountering any technical issue before proposing fixes. Covers root cause investigation, pattern analysis, hypothesis testing, and fix implementation. Use ESPECIALLY when under time pressure, "just one quick fix" seems obvious, or you've already tried multiple fixes. NOT for exploratory code reading.

Create publication-quality scientific diagrams using Nano Banana Pro AI with iterative refinement. AI generation is the default method for all diagram types. Generates high-fidelity images with automatic quality review. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Proactively captures significant work into the journal for future reference

Execute the Recursive Thought Committee (RTC) protocol by generating and harmonizing inputs from 5 specialized cognitive personas.

Reconcile conflicting perspectives into unified frameworks that preserve what matters from each viewpoint while resolving tensions. Use when: (1) asked to synthesize viewpoints or reconcile conflicting ideas into coherent understanding, (2) facing perspectives that directly contradict each other and require resolution rather than choosing sides, (3) dismissing conflicting information as wrong instead of exploring what tensions reveal about the problem, (4) constraints pull in opposite directions and need alignment strategy rather than compromise.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions | バグ、テスト失敗、予期しない動作に遭遇した際、修正を提案する前に使用 - 4フェーズフレームワーク（根本原因調査、パターン分析、仮説検証、実装）により、解決策を試す前に理解を確保

Produce grounded audio briefs by chaining source-scoped input, citation verification, dialogue dramatization, and multi-speaker TTS orchestration. Use for “Audio Overview” style outputs.

Hypothesis-driven debugging with systematic investigation. Identifies root causes, creates minimal reproductions, and implements fixes. Use when investigating errors, bugs, crashes, or unexpected behavior.

Component skill for creating compelling data-driven presentations and whitepapers using marp and pandoc with proper citations and reproducibility

Discover structural and causal relationships between seemingly unrelated observations to reveal how things influence each other. Use when: (1) asked to find relationships between separate ideas or map how observations connect, (2) multiple observations seem unrelated but might share causal links or common mechanisms, (3) building system models that show interaction patterns and feedback loops, (4) seeking solutions by recognizing analogous mechanisms from different contexts.

[Debug] Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions. (project)

Generalize from specific examples to distill portable rules that apply across contexts and predict new situations. Use when: (1) asked to extract underlying principles or identify generalizable lessons from specific cases, (2) have multiple examples showing recurring patterns but no explicit rule explaining why the pattern holds, (3) need to create guidelines from experience that capture underlying truth rather than surface similarity, (4) applying lessons from past situations to new contexts and need to verify the principle actually transfers.