論文

Use when asked to calculate statistical power, determine sample size, or plan experiments for hypothesis testing.

Use when user says "synthesize designs", "show design patterns", "UI patterns", "UX patterns", "update design docs", or asks about UI/UX design decisions - generates two markdown files summarizing UI/UX patterns from implemented stories and anti-patterns from rejected or problematic UI/UX stories.

Use when asked to create publication-ready scientific figures, charts for research papers, or academic visualizations.

Expert in ALL computational collage composition: photo mosaics, grid layouts, scrapbook/journal styles, magazine editorial, vision boards, mood boards, social media collages, memory walls, abstract/generative arrangements, and art-historical techniques (Hockney joiners, Dadaist photomontage, Surrealist assemblage, Rauschenberg combines). Masters edge-based assembly, Poisson blending, optimal transport color harmonization, and aesthetic optimization. Activate on 'collage', 'photo mosaic', 'grid layout', 'scrapbook', 'vision board', 'mood board', 'photo wall', 'magazine layout', 'Hockney', 'joiner', 'photomontage'. NOT for simple image editing (use native-app-designer), generating new images (use Stability AI), single photo enhancement (use photo-composition-critic), or basic image similarity search (use clip-aware-embeddings).

Generates property-based tests using Hypothesis (Python), fast-check (JavaScript/TypeScript), or QuickCheck (Haskell). Use when user asks to "generate property tests", "create hypothesis tests", "add property-based testing", or "generate fast-check tests".

Generate a reference architecture specification from analyzed frameworks. Use when (1) designing a new agent framework based on prior art, (2) defining core primitives (Message, State, Tool types), (3) specifying interface protocols, (4) creating execution loop pseudocode, or (5) producing architecture diagrams and implementation roadmaps.

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

Create production-grade, accessible Jekyll themes for researchers conducting "research in public." Generates complete lab notebook-style themes with Tufte-inspired sidenotes, KaTeX math rendering, and WCAG 2.1 AA compliance. Use when building Jekyll themes for scientific journals, experiment logs, field notes, or research documentation sites. Supports collections for organizing experiments and field notes, responsive sidenote rendering (sidebar on desktop, inline on mobile), and full-width layout options.

Recognize when synthesis has reached saturation through observable signals. Use when: (1) asked when to stop exploring or gathering data, (2) new examples reinforce existing patterns without new dimensions, (3) themes identified early hold across additional observations, (4) predictions about next observations prove accurate.

Systematic data validation, error detection, cross-source reconciliation, and query correctness checking for analytical work. Use when validating Snowflake queries, catching calculation errors, reconciling metrics across different data sources, checking for null values, ensuring date range validity, detecting statistical anomalies, validating metric calculations (median vs mean, rate normalization), checking aggregation grain (per-record vs per-entity), validating contribution analysis for non-additive metrics, or validating consistency across analysis sections. Essential when reviewing analysis before publication, debugging unexpected results, or ensuring data quality in reports. Triggers include "validate this query", "check for errors", "why don't these numbers match", "should I use median or mean", "why don't contributions sum to 100%", "reconcile these metrics", "verify data quality", or any request to catch potential issues in data or calculations.

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.

Recovers working context from the journal after /clear or at session start

This skill should be used when the user asks to "create a plot", "make a chart", "visualize data", "create a heatmap", "make a scatter plot", "plot time series", "create publication figures", "customize plot styling", "use matplotlib", "use seaborn", or needs guidance on Python data visualization, statistical graphics, or figure export.

Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select best practices, (3) designing a new agent system based on prior art, (4) documenting architectural decisions with evidence, or (5) conducting technical due diligence on AI agent implementations. This skill orchestrates sub-skills for data substrate, execution engine, cognitive architecture, and synthesis phases.

Comprehensive arXiv paper search and retrieval tool with keyword search, category filtering, date range filtering, and daily paper fetching capabilities for academic research tracking without keywords

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

Master statistical analysis with hypothesis testing, A/B testing, regression, and statistical methods for data-driven decisions.

Synthesizes research findings into design decisions via codebase investigation. Use when (1) translating research into implementation approaches, (2) selecting between design alternatives, (3) executing after /research or deep-research, or (4) preparing input for /plan phase.

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

Use when beginning a new conversation to work on an open-ended goal, loading context from previous iterations through iteration journals