Quality

Domain-Driven Design models software around the business domain using bounded contexts, aggregates, and ubiquitous language. Use it when splitting a monolith, defining service boundaries, or aligning code with business processes.

Change Traceability Review audits how a code change traces from story/issue to spec, plan/tasks, commits/PRs, diff, tests, and risk, and reports traceability gaps. Use it for spec preparation, pre-merge review readiness, or retrospective analysis of recent commits.

Diagnose Backend Bug diagnoses bounded backend or multi-service failures by correlating evidence from issue trackers, logs, traces, and job records before repair, using the project's observability route.

Reproduce Frontend Bug builds a bounded, replayable browser or UI bug reproduction from GitHub Issues, Jira, Aone, or user-provided exports. Use it for browser, WebView, IDE or desktop UI defects that need evidence-preserving reproduction before diagnosis or repair.

Skill Review audits Codex, Qoder, or repo-local skills and their prompt chains for trigger quality, workflow clarity, progressive disclosure, duplicated instructions, template ownership, output readability, and validation gaps, then recommends the smallest safe edits.

Triangulate Spec Review runs multiple independent AI reviewers like Claude, Qoder, Codex, or Cursor Agent against the same architecture specs, ADRs, or design documents, normalizes P1/P2/P3 findings, and iterates only on blocking or high-risk issues.

Verify runs focused tests before the full suite to validate one bounded change. Use it to quickly check a specific change without running the entire test suite.

Perf Analyzer synthesizes performance investigation results into evidence-backed recommendations and decisions. Use it when you have baseline data, experiment results, profiling evidence, and hypotheses to turn into actionable next steps.

Perf Baseline Manager manages performance baseline storage, ensuring one JSON file per version under the state directory. Use it when consolidating results or comparing performance across versions.

Perf Benchmarker enforces sequential performance benchmarks with minimum durations and a JSON metrics output contract. Use it when establishing baselines or validating regressions without parallel runs.

Perf Profiler runs profiling tools to capture CPU and memory hotspots with evidence such as flame graphs or JFR/perf output. Use it when profiling hot paths or gathering profiler artifacts.

Perf Theory Gatherer examines recent git history and relevant code paths to produce up to five evidence-backed performance hypotheses for a given scenario. Use it when you need hypotheses instead of optimizations.