Research

ALWAYS USE when working with Pydantic models, BaseModel, Field, validators, or data contracts. MUST be loaded before creating any Pydantic schemas, configuration classes, or API contracts. Provides v2 syntax validation and SDK research steps.

This skill should be used when users need to create Jira tickets for the RD (Research & Development) project. It supports creating features, bugs, and tasks with proper field mapping including assignee, team, sprint, and state. The skill uses Jira CLI commands and provides templates for different ticket types.

調査→論点整理→出典付きレポート化。ユーザーが「調べて」「比較して」「根拠/出典付きで」等を求めたら使う。

Generate neat, clean flashcards in markdown table format from a topic title or reference file. Use when you need to create study materials, review cards, or learning aids for any subject.

This skill should be used when the user asks to "find something to write about", "brainstorm topics", "what should I write about", "find writing ideas", "gather sources for", "pull references on", or needs help discovering topics from their reading highlights. Leverages Readwise MCP to surface patterns and gather references.

Look up Fannie Mae underwriting guidelines for income, assets, credit, or collateral verification. Use when questions involve DTI, income documentation, asset requirements, credit standards, or any B3/B4 guideline references. Reads guidelines dynamically from configs/guidelines/ - never hardcodes content.

research-designer for evidence-based learning research and evaluation.

Training monitoring dashboard setup with TensorBoard and Weights & Biases (WandB) including real-time metrics tracking, experiment comparison, hyperparameter visualization, and integration patterns. Use when setting up training monitoring, tracking experiments, visualizing metrics, comparing model runs, or when user mentions TensorBoard, WandB, training metrics, experiment tracking, or monitoring dashboard.

Direct MySQL access to Splynx ISP management database.Use when querying or modifying Splynx tables: customers, leads (category='lead'), services, tariffs, invoices, payments, tickets, network.Faster than REST API for bulk operations. Reference: src/migration/loaders/splynx_mysql/

Provides three production-ready ML training examples (sentiment classification, text generation, RedAI trade classifier) with complete training scripts, deployment configs, and datasets. Use when user needs example projects, reference implementations, starter templates, or wants to see working code for sentiment analysis, text generation, or financial trade classification.

Master market analysis, competitive research, and user targeting. Learn to identify opportunities, understand market dynamics, and position plugins for success.

Playwright E2E testing patterns with chrome-devtools MCP integration.Reference for integration tests, A11y validation, and visual regression.

Documentation and code examples research expert using Exa AI and Context7. Finds official docs, production code examples, technology comparisons, and best practices. Auto-activates when new libraries mentioned or user requests "docs", "examples", "best practices", or technology comparisons.

Use when editing or improving discussion sections that lack literature comparison, mechanistic interpretation, or honest limitations - provides synthesis patterns, positioning strategies, and future directions framework

Comprehensive reference for understanding any repo fast. All patterns for docs, code, configs, git, and conversation history. The complete playbook.

User preferences learned by slipstream

Intelligent revenue opportunity discovery system for financial advisors. Extracts structured revenue scenarios from publications and matches them to client books of business to identify high-value opportunities. Use when analyzing industry articles to discover new scenarios, or when scanning client data to find revenue opportunities and generate Top 25 opportunity reports.

Generate JSON schemas and Python handlers for Qdrant-based retrieval tools used by the RAG agent to search sitemap-crawled textbook content with URL citations.

Systematic architecture analysis following Understand → Research → Specify → Decompose → Plan workflow. Use for system design, solution evaluation, build vs buy decisions, and task decomposition. Activate when users say "design", "architect", "break down", "best approach", or "should I build".

Use when encountering errors, investigating library APIs, troubleshooting issues, or needing up-to-date documentation. Prioritizes Context7 and WebSearch over outdated training data.