ac-tdd-runner

Use when working with api-codegen-runner

Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.

Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Create apps following contract-port architecture with composition roots. Use when creating new apps in apps/, scaffolding CLI tools, setting up dependency injection, or when the user asks about app structure, entrypoints, or platform-agnostic design.

Verify code correctness before claiming done or committing. Run 6-dimension checklist: requirements coverage, concurrency safety, error handling, resource management, boundary conditions, and security. Output PASS/FAIL per dimension with final DONE/NOT DONE verdict. Use after implementation as pre-commit gate. Triggers on: is it done, ready to commit, verify correctness, did I miss anything, pre-commit check.

Simplify complex code through the Error Reduction Hierarchy: Define out > Mask > Aggregate > Crash. Use when code is too complex, has scattered error handling, configuration explosion, or callers doing module work. Produce technique analysis table with gate checks before simplified code. Triggers on: too complex, simplify, scattered errors, configuration proliferation, verbose error handling. Complements cc-defensive-programming with design-level error elimination.

Evaluate module design using APOSD principles with 40-item checklist. Detect complexity symptoms (change amplification, cognitive load, unknown unknowns), shallow modules, information leakage, pass-through methods, and structural anti-patterns. Produce categorized design review (Critical/Moderate/Observations/Positive). Use when reviewing code, assessing interfaces, during PR review, or evaluating 'is this too complex?' Triggers on: code review, design review, module complexity, interface assessment, PR review, structural analysis.

Optimize performance through mandatory measure-first workflow with 3 stages: MEASURE (gate) -> FUNDAMENTAL FIX -> CRITICAL PATH REDESIGN. Use when code is too slow, laggy, hangs, doesn't scale, has timeouts, OOM errors, or high CPU/memory. Emphasize that simpler code usually runs faster. Triggers on: performance issues, optimization needed, takes forever, profiling. Produces profiling-backed optimization with verified improvement.

Enforce strategic programming discipline when modifying existing code. Guide through STOP-ASK-DECIDE-VERIFY workflow with urgency tier assessment (trivial/minor/standard/emergency). Include when NOT to refactor (Chesterton's Fence, performance-critical, no tests) and block tactical shortcuts via anti-rationalization tables. Use when fixing bugs, extending features, or tempted to make quick fixes. Triggers on: modify code, fix bug, extend feature, quick fix, tactical change.

Enforce comments-first workflow for new code and improve naming/documentation for existing code. Use when writing new classes, methods, or functions; when code is 'confusing' or 'hard to understand'; when naming precision is poor; or when variable documentation lacks units, bounds, or ownership. Triggers on: new code, comments-first, naming review, documentation review, not obvious, hard to understand. Produces well-documented code with precise naming, or identifies design problems when comments/names are hard to write.

Enforce Design-It-Twice workflow: generate 2-3 radically different approaches, compare them, then implement. Use when designing modules, APIs, or classes before implementation. Triggers on: design, create class, add module, implement feature, new service, API design, before implementing. Produces structured design document with approaches, comparison table, choice rationale, and depth check.