單元測試

Format code and keep style consistent using the repository’s canonical formatting/lint commands from `AGENTS.md`. Use after implementing changes or when formatting drift causes noisy diffs; keep formatting changes intentional and verified with build/tests.

Use when planning, executing, and logging nurture experiments and regression tests.

Create or update a feature spec under `docs/Features/` using `docs/templates/Feature-Template.md`: business rules, user flows, system behaviour, Mermaid diagram(s), verification plan, and Definition of Done. Use before implementing a non-trivial feature or when behaviour changes; keep the spec executable (test flows + traceability to tests).

Framework for briefing, testing, and scaling social creative variations.

Use when structuring paid media campaigns/ad sets to balance testing, delivery, and optimization constraints.

Systematic quality validation, test verification, and safe merging workflow for deployment/release operations. ALWAYS asks for confirmation when user wants to ship, deploy, merge, release, or complete features to production, merge to main branch, or finalize features. This is a DESTRUCTIVE operation (merges and deletes branches).

Create or update an ADR (Architecture Decision Record) under `docs/ADR/` using `docs/templates/ADR-Template.md`: context, decision, alternatives, consequences, rollout, and verification. Use when changing architecture, boundaries, dependencies, data model, or cross-cutting patterns; ensure it is self-contained, has a Mermaid diagram, and defines testable invariants.

Repository blueprint for managing clinical studies, testimonials, and citations.

Use when validating automation builds before launch or after significant changes.

Systematic bugfix workflow with regression testing, auto-retry logic, and comprehensive validation. Auto-executes when user clearly wants to fix, debug, repair, resolve, broken, not working, doesn't work, not showing up, not appearing, not displaying, not rendering, doesn't show, won't show, isn't showing, doesn't appear, doesn't display, failing, errors, bugs, issues, not loading, doesn't load, crashed, crashes, problem with, trouble with.

Law-driven abstraction protocol: evidence first, seam test, minimal algebra, executable law check.

Force at least one feedback signal after code changes (static checks, logs, tests, UI); prefer local over CI.

Guidelines describing how to test the code. Use whenever writing new or updating existing code, for example after implementing a new feature or fixing a bug.

Prioritizes tests based on ROI and critical user journeys. Use when: deciding test coverage, selecting test types, or budgeting effort.

Algebra-Driven Design (ADD): model domains via minimal algebra + laws; encode in types; test laws.

Zig runbook: build/test, comptime patterns, allocators, build.zig/build.zig.zon, zero-copy parsing, C interop.

Applies TDD process, test quality criteria, and mock guidelines. Use when: writing unit tests, using mocks, or reviewing test quality.

Designs integration and E2E tests with mock boundaries. Use when: writing E2E tests, integration tests, or reviewing test quality.

Gauntlet for absolute claims (always/never/guaranteed/optimal); pressure-test, then refine with explicit boundaries.

Generates production-ready C# script templates (MonoBehaviour, ScriptableObject, Editor, tests). Use when creating new scripts or setting up project structure.