資料庫

Query browsing history from all synced devices (iPhone, Mac, iPad, desktop). Supports natural language queries for filtering by date, device, domain, and keywords. Uses LLM classification for content categories. Can output to stdout or save as markdown/JSON to Obsidian vault.

Research and generate Azure deployment guide with EasyAuth (Google + Facebook) and CosmosDB. This skill searches for current documentation and screenshots to produce an up-to-date setup guide at .docs/azure-setup-guide.md.

When an application needs to store config, data, cache, or state files. When designing where user-specific files should live. When code writes to ~/.appname or hardcoded home paths. When implementing cross-platform file storage with platformdirs.

Router for systems-as-experience - emergence, sandbox, optimization, discovery, narrative, modding

Generate DBeaver configurations from Pydantic ClickHouse connection models. Use when user mentions "DBeaver config", "ClickHouse connection setup", "database client configuration", "generate connection JSON", "mise SSoT connection", or needs consistent connection configuration across development tools.

Run PostgreSQL queries and meta-commands via CLI

Diagnose world-level story problems. Use when settings feel thin, institutions feel designed rather than evolved, economies don't make sense, or non-human species feel like humans in costume. Applies systemic worldbuilding principles to identify specific gaps and recommend interventions.

Personal inventory management system for tracking possessions during decluttering and organization. Uses SQLite database for structured tracking of rooms, categories, items, and processing status. Use when organizing, decluttering, or managing personal belongings.

Control Notion via Python SDK. TRIGGERS - Notion API, create page, query database, add blocks, automate Notion. PREFLIGHT - requires token from notion.so/my-integrations.

Debug JIT-compiled code from Cranelift. Use when debugging crashes, memory corruption, or calling convention issues in dynamically generated code. Covers cdb.exe (Windows), lldb/gdb with SIGSEGV handlers (Unix), and disassembly analysis.

Use when pair programming with humans - enforces XP values (communication, simplicity, feedback, courage, respect) to deliver high-quality software; push back on YAGNI violations regardless of seniority or sunk cost

ChatGPT-style deep research strategy with problem decomposition, multi-query generation (3-5 variations per sub-question), evidence synthesis with source ranking, numbered citations, and iterative refinement. Use for complex architecture decisions, multi-domain synthesis, strategic comparisons, technology selection. Keywords: architecture, integration, best practices, strategy, recommendations, comparison.

Type-safe database ORM for TypeScript/Node.js. Use when you need database access with full TypeScript integration — auto-generated types from schema, migrations, and query builder. Best for PostgreSQL, MySQL, SQLite, MongoDB. Choose Prisma over raw SQL or Knex when type safety and developer experience are priorities.

Transform predictable story elements into fresh, original versions. Use when something feels generic, when feedback says "I've seen this before," when elements orbit the protagonist too conveniently, or when you want to make a familiar trope feel new. Applies the 8-step CTF process and Orthogonality Principle.

Log experiment metrics, parameters, and artifacts using MLflow Python API. Query and analyze runs with DataFrame operations. Use when user mentions "log backtest", "MLflow metrics", "experiment tracking", "log parameters", "search runs", "MLflow query", or needs to record strategy performance.

Diagnose research quality and guide systematic query expansion. Use when starting research on any topic, when stuck in research, or when unsure if research is complete.

Query Chrome browsing history with natural language. Filter by date range, article type, keywords, and specific sites.

Управление БД, миграциями, SCD Type 2 и Closure Table

Database schema design patterns and optimization strategies for relational and NoSQL databases. Use when designing database schemas, optimizing query performance, or implementing data persistence layers at scale.

Use the Gemini CLI to search the web for current information. Use this skill whenever the user explicitly asks to "ask gemini" or wants to query Gemini with web search capabilities.