Goal: Find the way to a destination too big for one agent session and not yet visible, by charting a shared map of decision tickets and resolving them one per session until nothing is left to decide before someone builds.
For UI-bearing artifact reviews, read references/review-type-design.md → Shared UI protocol bodies at the review mode's UI gate; its Design-only UI/UX principles apply only to --type=design. Non-UI reviews keep their own rubric without loading UI depth.
Read the registry → workflows.workflow-implement-spec together with this skill. Call $start-workflow workflow-implement-spec to resolve the selected mode, pre-actions and fingerprint.
Read the registry → workflows.workflow-integration-test together with this skill. Call $start-workflow workflow-integration-test to resolve the selected mode, pre-actions and fingerprint.
Read the registry → workflows.workflow-planned-work together with this skill. Call $start-workflow workflow-planned-work to resolve the selected mode, pre-actions and fingerprint.
Read the registry → workflows.workflow-spec-to-mockup together with this skill. Call $start-workflow workflow-spec-to-mockup to resolve the selected mode, pre-actions and fingerprint.
Use when reviewing plans or code for features that call models — LLM calls, prompts, agents, RAG, tool use and MCP, evals, guardrails, cost and safety. Read-only, evidence-backed findings.
Use when writing, updating or statically reviewing performance/load/soak/ capacity tests and their reusable harness, workload/data profiles, resource constraints, telemetry or pass/fail evaluator.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: