研究

Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.

Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved to Notion. Helps you arrive prepared with comprehensive background and structured meeting docs.

Guide for creating effective skills, adding skill references, skill scripts or optimizing existing skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, frameworks, libraries or plugins usage, or API and tool integrations.

Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.

Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.

Conducts in-depth analysis of a specific source or topic, producing comprehensive summaries for research synthesis. Use when you need detailed analysis and documentation of individual sources as part of a larger research effort.

Systematically debug issues with reproduction steps, error analysis, hypothesis testing, and root cause fixes. Use when investigating bugs, analyzing production incidents, or troubleshooting unexpected behavior.

Writes and edits content in Ben Swift's distinctive voice for any type of writing including blog posts, emails, technical documentation, and academic content. Use when the user wants writing in Ben's voice or style.

Create exceptional, publication-quality Mermaid diagrams for ERDs, flowcharts, sequence diagrams, and system visualizations. Use this skill when the user needs to visualize data models, processes, or architecture. Generates clear, refined diagrams that communicate complex systems with precision.

Implement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, retrieve page metadata, or build applications that process web content. Supports automatic content extraction with title, HTML, and publication time retrieval.

Long-term memory across sessions. Always use memory_search at the start of any user request (unless the user explicitly says not to), especially for questions about the user (profile/personal info/preferences), prior constraints or decisions, and resuming ongoing work; use memory_write only when the user explicitly asks to store memory.

Use Hypothesis for property-based testing to automatically generate comprehensive test cases, find edge cases, and write more robust tests with minimal example shrinking. Includes Polars parametric testing integration.

UK legal research using the Lex API. Search UK legislation and legal provisions. Use when researching UK law, analysing statutory instruments, or grounding responses in authoritative legal sources.

Persistent memory management for Claude Code via AutoMem. Use this skill when: - Starting a session (recall project context, decisions, patterns) - Making architectural decisions or library choices - Fixing bugs (store root cause and solution) - Learning user preferences or code style - Completing significant work (store summary) - Debugging issues (search for similar past problems)

Curate and validate BibTeX bibliographies against academic databases.

ATRIS workspace navigation and task management. Use when user mentions atris, TODO, tasks, backlog, navigator, executor, validator, MAP.md, journal, inbox, or asks "where is X?" in an atris-enabled project.

Technical reference for using IDA Swarm MCP tools. Covers system constraints, architecture, TRUE CONTEXT principle, result interpretation, and debugging. Use when analyzing binaries via IDA Swarm or troubleshooting sessions.

Guide for using git according to my preferences. Use it when you're asked to commit something.

Automated data visualization for EDA, model performance, and business reporting. Activates for "visualize data", "create plots", "EDA", "exploratory analysis", "confusion matrix", "ROC curve", "feature distribution", "correlation heatmap", "plot results", "dashboard". Generates publication-quality visualizations integrated with SpecWeave increments.

Automated machine learning with hyperparameter optimization using Optuna, Hyperopt, or AutoML libraries. Activates for "automl", "hyperparameter tuning", "optimize hyperparameters", "auto tune model", "neural architecture search", "automated ml". Systematically explores model and hyperparameter spaces, tracks all experiments, and finds optimal configurations with minimal manual intervention.