supergraph

Meta-orchestrator — dispatches to the right skill for the task. Use before any non-trivial work.

Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.

Structured 6-phase debugging. Build feedback loop first, reproduce deterministically, hypothesize with ranked falsifiable theories, instrument one variable at a time, fix with regression test, cleanup. Use when a bug exists, tests fail unexpectedly, or behavior is wrong and cause is unknown.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).

Run integration and e2e tests after unit tests pass. Use after /supergraph:fix when unit tests are green.

Plan-aware graph-enhanced code review before merge. CRITICAL issues block merge. Use after fix/verify.

Strict test-driven development for behavior changes. Requires verified RED before production code, minimal GREEN, and refactor only after passing tests.

Fresh verification gate before claiming done, fixed, passing, ready, or before commit/PR. Evidence before claims, always.

Dispatch and execute implementation plans with TDD and checkpoints. Use when plan is ready. Parallel by default for independent tasks.

Plan-aware auto-fix loop after coding. Runs tests, lint, format, and graph checks. Updates plan task status. Use after execute/tdd.

Proactive architecture review — explore codebase structure, generate a self-contained HTML report with Mermaid diagrams and candidate improvements, then grill the findings. Use when planning a large refactor, onboarding to an unfamiliar codebase, or before a major architectural change.

One-shot module map — go up a layer of abstraction and get a domain-vocabulary module map of the codebase. Use when lost in unfamiliar code, after a long deep-dive session, or when you need to re-orient before planning.

Risk analysis and approach selection before planning. Use when requirements are ambiguous, approaches vary, or work touches hub/bridge nodes. Skip for typo fixes.

Create graph-informed implementation plans before writing code. Use before any non-trivial task. Skip for small changes (1-2 files, <10 lines).

Scan project once per session. Run first — all other skills depend on this.

Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.

Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.

Activate persistent token-compression mode (~75% output reduction). Strips articles, filler words, and prepositions while keeping code, numbers, and names exact. Use when in a long session, on a token budget, or when responses feel too verbose. Disable with "normal mode" or "full mode".

Compact current session context into a handoff document for seamless continuation in a new session. Use when context window is exhausted, switching machines, handing work to another agent, or ending a long session mid-task.

Convert current conversation context into a structured Product Requirements Document (PRD) and optionally post it to GitHub Issues. Use before /supergraph:plan when requirements came from a conversation, user story, or feature discussion rather than a formal spec.

Build throwaway code to validate an uncertain approach before committing to a plan. Two branches — Logic (terminal state machine) or UI (multiple designs on one route with URL-param switcher). No persistence, no tests, single-command start. Use between analyze and plan when the approach itself is uncertain.

Apply a formal state machine to issues — assign category (bug/enhancement/question/spike) and state (needs-triage → needs-info → ready-for-agent → ready-for-human → wontfix). Issues marked ready-for-agent become inputs to supergraph:plan. Use when processing a backlog, reviewing new issues, or preparing work for automation.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.