map2-audio

Integrity sweep of the MAP2 Audio Platform (Python FastAPI backend, JUCE/C++ engine, React/Carbon frontend, device-packs): find dead/unreachable code, stubs, mockups passing as features ("Coming Soon" cards, placeholder tabs), convention violations (raw hex vs Carbon tokens, unregistered routes, stale OpenAPI pins, untracked migrations), and doc/worklist drift — each finding gets a FINISH-or-REMOVE verdict. TRIGGER when the user asks to "audit", "evaluate compliance", "check for dead code/stubs", or "find what's not really done". Produces a findings table; it does NOT fix things unless asked.

Design-thinking + survey + worklist-scoping skill for the MAP2 Audio Platform. Use when the user asks to scope an epic, run an N-question AskUserQuestion survey, lock a non-trivial design decision, audit the worklist for drift, rescue dead modules, lift design-doc actions into worklist tasks, or draft a design document — i.e. PLAN before any code lands (CLAUDE.md Plan-First Meta Rule). Defers to map2-worklist-management for the canonical task schema. Sister skills: ship (drains the queue), audit (integrity sweep), build-installer-rpm (the RPM cut).

Autonomously drain the MAP2 worklist: a rescue pass to catch dead/mock code, then implement open tasks fully (no stubs), gating each (pytest · jest · typecheck · web build · cmake for engine changes), committing + dual-pushing (origin + gitlab) + rebuilding/restarting port 3000 as you go. TRIGGER when the user says "ship it", "execute", "continue", "drain the worklist", or "work through the backlog". Do NOT use for a single scoped edit (just do it) or a release/RPM cut (use /build-installer-rpm).

Run a full JUCE callback-path soak using 10 random native effects at once, rotating serial/parallel flow topologies and blend strategies between flows while collecting xrun, jitter, and CPU evidence. Use when validating engine stability after graph/device/lifecycle changes, reproducing post-start_audio regressions, or generating release-grade performance proof.

Track and enforce MAP2 licensing posture as full-project AGPLv3 for MAP2-owned code, with third-party license overrides preserved, including compliance audits, documentation checks, and required remediation task creation in docs/PROJECT_WORKLIST.md. Use when changing code, preparing releases, updating README/legal docs, or answering licensing-status/compliance questions.

Reassess and modernize MAP2 installer and packaging on Fedora Server by auditing a current MAP2 host against a documented stock Fedora baseline, computing evidence-backed deltas, and generating an idempotent verbose installer plus RPM/repository scaffolding. Use when revisiting full installer builds, updating Fedora deployment automation, validating AVB/TSN readiness, or preparing MAP2 package and repo release workflows.

Build a production-grade MAP2 Audio Platform installer RPM. Creates a clean build workspace outside the source repository, improves packaging artifacts inside the repo (spec, .gitattributes, config files, map2-setup wizard), then runs rpmbuild and produces a distributable RPM. The original source repository is never deleted from, restructured, or broken.

Execute remaining project tasks from the canonical worklist with aggressive parallelization, completeness-first implementation, and explicit tech-debt capture. Use when the user asks to continue work, complete remaining steps, move quickly, bundle tasks, or proceed without repeated confirmation.

MAP2 Copilot-specific collaboration rules and user preferences, especially git workflow requirements. Use when handling commit/push/sync requests, applying user workflow preferences, or following .github/copilot-instructions.md behavior in this repository.

MAP2 Audio core engineering guidance and memory protocol. Use when working in this repository on architecture, coding standards, build/test/deploy commands, server management, performance and latency constraints, and when asked to remember new fixes or patterns.

Enforce a single canonical project worklist with strict task schema, status tracking, and restart-safe handoffs. Use when planning, executing, or reporting project work; when adding new ideas, bugs, or features; when coordinating parallel subtasks across AI threads/humans; and when the user asks to apply the Cortex AL worklist rule.