Pytest patterns for testing Python APIs (FastAPI, Flask). Covers httpx AsyncClient setup, conftest.py fixture organization, fixture scoping, parametrize for edge cases, factory fixtures, database isolation, testing error responses and auth flows. Triggers when writing tests for any Python web API, adding test coverage, or building a new API that needs tests.

Use when a debugging thread needs to be compressed into a reusable investigation ledger. Capture the target, evidence, attempted fixes, ruled-out hypotheses, viable hypotheses, and next experiments. Good triggers include "compact this debugging session", "summarize what we've tried", and "turn this into a debugging ledger".

Conduct an interactive discovery interview to produce a structured product specification. Triggers: write a spec, PRD, feature spec, requirements, product requirements, scope a project, brainstorm a feature, flesh out an idea, plan a new project. Uses AskUserQuestion for all user choices; WebSearch/WebFetch when the user wants research. Outputs: user stories, acceptance criteria, technical constraints, prioritized requirements in docs/specs/ per SPEC_TEMPLATE.md. Do NOT use for: implementation, code review, debugging, refactors, or when the user already has a complete spec they only want edited.

Configures NotificationClient handlers, implements async dispatch workflows, and handles DispatchError failures for the pidge v3 notification library in async Python services. Use when working with pidge, pidge v3, pidge notifications, NotificationClient, async notifications, or pidge integration — including setting up API keys, dispatching messages, and handling delivery errors.

Fetch the PyXLL documentation and use it as context for any task involving PyXLL. Invoke automatically before writing, editing, reviewing, or debugging any PyXLL code, and for release notes, changelog, or version history lookups. Training-data knowledge of PyXLL is incomplete and may be wrong — the live docs are the only authoritative source.

Reference for the Office CustomUI XML schema used to define Excel ribbon toolbars and context menus. Use this skill whenever writing, editing, reviewing, or debugging customUI XML — including ribbon tabs, groups, buttons, dropdowns, galleries, menus, context menus, the QAT, or the Backstage. Also use when working with PyXLL ribbon configuration. Training-data knowledge of the schema is incomplete and can produce invalid XML — the schema and these docs are the authoritative source.

Reference for the Microsoft Excel COM API via pywin32. Use this skill whenever writing or reviewing Python code that interacts with Excel using the Excel COM API via win32com, pywin32, or the PyXLL add-in — including code that calls pyxll.xl_app() or XLCell.to_range() — and when working with workbooks, worksheets, ranges, formatting, charts, pivot tables, shapes, and Excel constants.

PostgreSQL patterns for Python with psycopg 3 and asyncpg -- connection pooling, parameterized queries, transactions, bulk inserts, async context managers, server-side cursors, SSL config, and connection cleanup. Always apply when building or reviewing Python apps with PostgreSQL using raw database drivers (not an ORM), or when debugging connection pool or query issues.

Svelte 5 runes, SvelteKit patterns, component design, reactivity, and data loading. Use when building or reviewing Svelte/SvelteKit apps, especially with Svelte 5 runes ($state, $derived, $effect, $props), snippets, event handling, SvelteKit load functions, and form actions.

Jest testing patterns — test structure, mocking, async testing, snapshot testing, and configuration. Use when building or reviewing tests with Jest, when setting up Jest for a project, or when debugging flaky Jest tests.

NestJS patterns -- modules, controllers, services, dependency injection, exception filters, validation pipes, guards, interceptors, custom providers, testing, and configuration. Use when building or reviewing NestJS APIs, setting up a new NestJS project, or migrating from Express to NestJS.

Progressive concept teaching through three depth levels (Core → Mechanics → Deep Dive). Creates diagrams, provides annotated code walkthroughs from the current codebase, and builds explanations from fundamentals to production internals. Triggers: "teach me about [pattern/concept]", "how does [architecture/pattern] work", "walk me through [this implementation]", "tutorial on [concept]", "deep dive into [system/pattern]", "help me understand [this design]" Use when: user requests multi-level learning about code patterns, architecture, or implementation mechanics with checkpoint-based progression. Not for: quick answers, single-sentence explanations, code fixes, or "what does this line do" questions—those are standard assistance.

SQLAlchemy patterns — engine setup, session management, declarative models, relationships, eager loading, raw SQL safety, async patterns, bulk operations, and Alembic migrations. Use when building or reviewing Python apps with SQLAlchemy, when setting up a new database layer, or when debugging session, connection, or performance issues.

Playwright E2E testing patterns — web-first assertions, user-visible locators, network interception, fixtures, authentication, and parallel execution. Use when building or reviewing E2E tests with Playwright, when setting up browser testing for a web app, or when migrating from Cypress or Selenium.

Build EVM blockchain data indexers using Ponder (ponder.sh) - an open-source TypeScript framework for indexing smart contract events, transactions, and traces into custom database schemas with type-safe APIs. Use when the user mentions ponder, blockchain/EVM indexing, onchain data pipelines, subgraph replacement, or wants to index smart contract events into a queryable database.