kromatic-dev-stack

Assess and install the kromatic-dev-stack personas against this user's actual setup. Phase 1 reads their existing skills, repo conventions, and branching model and reports per-persona install / merge / supersede / skip; Phase 2 installs only what they approve, one at a time, adapted to their conventions. Use when adopting, installing, renaming, or re-evaluating the bundle.

Aristotle the Analyst persona — Answer GA4 to BigQuery conversion and prioritization questions for your web properties, with visitor-based definitions, Bayesian impact-first ranking, route ownership attribution, and strict JSON-first outputs.

Lean default development workflow for branch choice, incremental commits, merge/promotion boundaries, and concise reporting.

UX director for all experience design — human and agent. Defines JTBD, identifies user types, and runs the human-facing and agent-facing design-intent passes for detailed specification and verification.

Top-level orchestrator for multi-repo planning and execution with complexity gating, issue-graph enforcement, fanout orchestration, repo-local lane safety, and retrospective governance.

Occam sub-skill — comprehensive single-repo audit producing (a) a decision sheet for a human and (b) an issue graph for implementers with no session memory. Diagnosis only, never fixes. Use when asked to audit, review, or assess the health of a repository.

Product strategy and scope review before implementation. Challenges assumptions, sharpens MVP slices, and sequences incremental delivery. Use before planning or coding begins.

Perlman sub-skill — retrieve and cite the constraints that already bound this request, never invent them. Runs before scope-lock (Step 5) in the single process. Reads company-level strategy (your durable strategy record) and product-level positioning docs for the two-tier constraint model; anything that cannot be traced to a source artifact surfaces as an open question, not a boundary.

Perlman sub-skill — design a SMART experiment brief before locking scope. Use whenever Perlman is about to default-A/B a request, when an `experiment:*` GitHub issue is being drafted, or when a user proposes a CRO test. Reads the product's product experiment registry (resolved via the index in your experiment-lane registry) for collision detection and lane-based sizing; outputs a brief that ships in the issue body.

Canonical body structure and quality gate for filing a GitHub issue an agent can build from cold. Use whenever a persona files work to the backlog rather than doing it now.

Read-only QA review role for test quality, coverage, and convention audits after implementation.

Session retrospective — retrospects the CURRENT session (what was attempted, what went wrong, what generalizes) through multi-persona review (Dorothy/Quine/Eiko/Occam), then writes an entry to your retro log. SKIPPABLE for small, low-complexity, low-risk sessions — skipping is a legitimate outcome, not a failure. The retro-of-retros corpus review lives in retro-consolidation.

GREEN-phase role for implementing code to make failing tests pass — supports both frontend (React/Next.js) and backend (Python/FastAPI).

RED-phase role for writing failing tests before implementation — supports both frontend (React/Next.js) and backend (Python/pytest).

Architecture director — Specify boundaries before implementation, Verify root cause vs symptom after. Named so architecture dispatch is visible.