SQL

Expert technical advisor with deep reasoning for architecture decisions, code analysis, and engineering guidance.

Use when editing Observable notebooks (docs/index.html), creating charts with Plot, adding SQL cells, loading data with FileAttachment, or working with DuckDB. Triggers on notebook editing, visualization, data loading.

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Git-backed JSONL files are the source of truth, with SQLite as local cache. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

Use the project's specific technology stack including Next.js, React, TypeScript, Hono, PostgreSQL, Chakra UI, and Temporal for workflow automation. When setting up new features, choosing libraries, or making architectural decisions. When working on frontend code using React and Next.js. When implementing backend APIs with Hono. When working with PostgreSQL databases via Drizzle or Prisma. When styling with Chakra UI components. When implementing authentication with better-auth or workflows with Temporal. When adding dependencies or configuring build tools. This skill ensures technology choices align with the project's established stack.

DevOps automation for a Next.js (Vercel) frontend, Fly.io backend, and Supabase Postgres. The agent should prefer `just` recipes as the invocation surface. Internally, recipes use a hybrid MCP+CLI approach: Supabase CLI for writes/migrations (local & prod), Fly MCP preferred for ops with flyctl fallback, and Vercel CLI for deploy with optional MCP for env/status. Secrets are loaded exclusively via 1Password CLI; values are never printed.

查询集成连接器和API配置（v3_openapi数据库）。使用 exec_sql 工具执行查询。

Test game mechanics via SQL. Use game_* tools for gameplay flow.

Armazena e consulta memória persistente de projetos em banco PostgreSQL.Use quando: (1) tomar decisões técnicas importantes, (2) identificar TODOs/melhorias,(3) documentar contexto do projeto, (4) consultar decisões anteriores.O Claude deve AUTOMATICAMENTE salvar decisões importantes e consultar memória relevante.Identificação do projeto é automática via git repo + branch.

Datti APIバックエンド開発ガイド。Go製PostgreSQL APIサーバーの開発、新機能実装、テスト、デプロイに関する標準フロー。契約定義、スキーマ設計、ユースケース実装時に自動的に使用。

ALWAYS USE when working with dbt models, SQL transformations, tests, snapshots, or macros. MUST be loaded before editing any .sql files, dbt_project.yml, or profiles.yml. Enforces dbt owns SQL principle - never parse SQL in Python.

Create learning paths for topics. Use when user says "learning path", "how do I learn", "roadmap for", "curriculum", "what should I learn first". Auto-trigger when onboarding or skill development discussed.

Neon PostgreSQL patterns for Pitchey. Raw SQL only, no ORM. Uses Hyperdrive for connection pooling. Activates for database queries, migrations, or schema work.

Alembic migration patterns for PostgreSQL. Use when creating migrations, reviewing autogenerated migrations, or handling schema changes safely.

Query and inspect the WaveCap SQLite database. Use when the user wants to run SQL queries, inspect transcription records, check event metadata, debug database issues, or analyze historical data.

Maintain approved technology stack including TypeScript/Python languages, React/Tailwind frontend, Node.js/FastAPI backend, PostgreSQL/Redis persistence, and Ansible infrastructure automation with enforced quality gates. Use this skill when selecting technologies, adding dependencies, configuring tooling, or ensuring infrastructure-as-code practices. Applies to package.json, requirements.txt, CI/CD pipelines, Ansible playbooks, linters, formatters, testing frameworks, and all technology choices requiring documented approval and migration strategies.

"Convert markdown files to Jupyter notebooks (.ipynb). Splits markdown by `---` delimiters into cells, extracts code blocks (```python```, ```sql```) as code cells, and handles YAML front matter removal. Use when converting documentation, tutorials, or structured markdown into interactive Jupyter notebooks."

This skill should be used when the user asks to "generate IDs", "create identifiers", "use nanoid", "add public_id", "prefixed identifiers", "short IDs", or discusses ID generation strategies, public vs internal IDs, or URL-friendly identifiers. Use nanoid for public identifiers and UUID for auth.users references.

Use when writing BigQuery queries, optimizing query performance, analyzing execution plans, or avoiding common SQL gotchas. Covers parameterized queries, UDFs, scripting, window functions (QUALIFY, ROW_NUMBER, RANK, LEAD/LAG), JSON functions, ARRAY/STRUCT operations, BigQuery-specific features (EXCEPT, REPLACE, SAFE_*), CTE re-execution issues, NOT IN with NULLs, DML performance, Standard vs Legacy SQL, and performance best practices.

Expert guidance for creating and working with marimo notebooks - reactive Python notebooks that can be executed as scripts and deployed as apps. Use when the user asks to create marimo notebooks, convert Jupyter notebooks to marimo, build interactive dashboards or data apps with marimo, work with marimo's reactive programming model, debug marimo notebooks, or needs help with marimo-specific features (cells, UI elements, reactivity, SQL integration, deploying apps, etc.).

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.