Route unresolved architecture blockers back into the existing governing Wayfinder effort, reopening that map when authoritative re-entry requires it, creating or reusing one decision ticket per independent architectural decision, and handing resolution to $wayfinder.
Classify, reclassify, relocate, or rename an existing non-ADR document under docs/, updating inbound references and Living Entity Wiki consequences when required.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Optimizes local code intelligence and discovery using a high-performance, Tree-sitter-backed structural knowledge graph instead of expensive token-heavy file searches. Use for understanding code architecture, tracing function call chains, finding cross-file dependencies, analyzing git diff blast radiuses, running…
Traces implicit function paths, event loops, framework decorators, and decoupled execution targets via CodeGraph tools. Use for tracing Python-specific routing (FastAPI/Django decorators), event emitters (emit/on loops), callback handlers, or abstract dispatch before tracing raw files manually.
Enforces strict adherence to the Conventional Commits 1.0.0 specification for staging and saving changes. Use when a user asks to commit files, draft a git message, or finalize code tasks.
Manage, generate, apply, and validate PostgreSQL schema migrations using SQLAlchemy and Alembic, including the pre-1.0 branch-baseline policy and targeted database verification.
Runs static code analysis and token-matching tools to detect duplicate code fragments and clone clusters. Use before extracting shared utilities, creating helper modules, or starting a refactor.
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Actively sharpen the project's domain model by resolving terminology, stress-testing concepts, reconciling domain language with implementation, and maintaining canonical vocabulary in CONTEXT.md.
Formats, cleans, and structures modified or newly generated files in the workspace. Use this skill whenever work is being performed on an individual active ticket (e.g., using the $implement-ticket skill) OR on-demand anytime current working files require code formatting, style compliance, and cleaning prior to…
Internal GitHub relationship helper used by $to-specs, $to-tickets, and $project-delivery-management for authorized native parent/child and dependency mutations. Documents current gh CLI relationship flags so lifecycle owners do not duplicate tracker mechanics.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Coordinate project-level delivery across Polaris Wayfinder efforts by owning durable focus and exact parallel-focus authorization, deriving the Wayfinder frontier from canonical tracker state, and providing fail-closed guard, cross-Wayfinder dependency, and reconciliation operations without becoming a delivery…
Invoked by Polaris lifecycle owners after a durable workflow transition to reconcile the public GitHub Project projection. Internal helper only; never determines workflow truth.
Queries local repository code, structural overviews, dead code references, and file risk markers via Repowise tools. Use before editing python files or when exploring existing codebase implementations or when the user asks questions about architecture, code structure, imports, or file relationships.