Explicit-only investigation and optional causal fix for hard, intermittent, performance, environment-only, production-only, or otherwise…
Test-driven development. Use only when the user explicitly requests TDD, test-first work, or RED-GREEN-REFACTOR, or applicable repository…
Write and debug Storybook stories and Chromatic snapshots for apps/web.
Run a managed pentest of a web app or API through the app.strix.ai REST API — no local Docker, LLM key, or install needed.
Surface the structural truth of the codebase: coupling, cycles, dead code, parallel implementations, deprecated paths, abandoned…
Verify that functionality migrated from Struts 2 to Spring works correctly in the running application from the API, client, and user…
TanStack React Start auth patterns with @clerk/tanstack-react-start
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test…
Classicist by default, pragmatic about doubles, strict about test purpose and boundaries.
Test-Driven Development (TDD) and Incremental Implementation discipline.
Enforceable test-first execution loop for features and bug fixes — red, green, refactor, with completion evidence.
Use when the user asks for TDD, red-green-refactor, tests-first implementation, or a bug fix/feature with tests first.
Enforce true RED/GREEN TDD workflow with fail-first testing methodology
Use when approved work changes caller-visible or user-visible behavior, adds a new behavior path, or an understood bug needs a new durable…
Spawn a test-writer teammate that owns test files while you keep implementing, so tests get written in parallel by an agent that cannot…
Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, language-native tooling, and optionally…
Technical debt inventory, prioritization, and audit for PHP/Laravel (MySQL) and Node/TypeScript/React projects.
Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows…
Test FastMCP servers through direct unit tests, in-memory MCP clients, elicitation handlers, and focused deployed-transport integration…
Test a running HTTP API end-to-end with hurl — write .hurl files with request + assert blocks, handle bearer-token auth and variables, run…
Run tests and auto-fix failures. Standalone test runner that diagnoses and repairs failing tests without manual intervention.