stock_agent

Debug frontend vanilla JS issues - console errors, rendering bugs, SPA navigation, WebSocket

Automates the process of setting up the first admin user or adding new admins via the bootstrap endpoint. Includes a Python script for easy execution.

Push to remote and wait for CI to pass. If CI fails, read logs, fix bugs, and re-push. Repeat until green.

Use when building or debugging LangGraph multi-agent systems - eval-first execution, task decomposition, model routing by complexity, and cost discipline

Use when AI agent modifies API routes or backend logic - catch systematic blind spots where the same model writes and reviews code

Use when making or recording significant architectural decisions - capture context, alternatives, and rationale as structured ADRs

Use when you have a written implementation plan to execute with review checkpoints between tasks

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - merge, PR, keep, or discard

Use when receiving code review feedback - verify before implementing, ask before assuming, technical correctness over social comfort

Use when completing tasks or implementing major features to verify work meets requirements before proceeding

Use when starting feature work that needs isolation or before executing implementation plans - creates isolated git worktrees with safety verification

Use when creating new skills or editing existing skills - follow TDD for documentation

REST API design conventions for FastAPI routers

API testing patterns for FastAPI endpoints using pytest and httpx

Use before any creative work - creating features, building components, modifying behavior. Explores intent, requirements and design before implementation

Generate changelogs from git history for releases and PRs

Use when session feels sluggish, output quality degrading, or after adding many skills/agents. Analyzes context window consumption

Use when building LLM-powered features - model routing by task complexity, budget tracking, retry logic, and prompt caching

Database migration patterns for PostgreSQL + Alembic + reconcile

Database migration: schema changes, column cleanup, Alembic

Deploy to production: run tests, push, verify health

CI/CD, Docker, health checks, production readiness

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when setting up Docker for local development, writing Dockerfiles, configuring Docker Compose, or troubleshooting container issues

Playwright E2E test patterns for SPA market pages

Add internationalization for new Chinese strings in JS files

PostgreSQL optimization: indexes, types, anti-patterns for this project

Python best practices: type hints, async, error handling, idioms

pytest patterns: fixtures, markers, async tests, mocking for FastAPI

Create git release with changelog and version bump

Trace issues backward through the call stack to find the true root cause, not just symptoms

Research before coding: check existing code, docs, and libraries first

Security audit: check secrets, XSS, auth, rate limits

Use when executing implementation plans with independent tasks - dispatch fresh subagent per task with two-stage review

Use when encountering any bug, test failure, build error, or unexpected behavior - 4-phase root cause process before proposing fixes

Test-driven development: red-green-refactor for this project

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR

Run test suite with proper flags and coverage

Use before claiming work is complete, fixed, or passing. Requires running verification commands and confirming output before any success claims

Post-change verification checklist: lint, test, security, diff review