git-worktree-decisionDecide whether a piece of work deserves its own git worktree, before creating one. Use when about to start work that would disturb a dirty or warm working tree, when an urgent fix interrupts work in progress, when launching concurrent/parallel agent sessions on one repo, when tempted to `git stash` or `git switch` to make room, or when worktrees have accumulated and you need to know which should never have existed. Covers the concurrency test, the shared-external-state blocker that makes worktrees backfire, and the teardown commitment. Not a worktree how-to: mechanics, per-worktree ports, and dependency symlinking are out of scope.
typed-decisions-around-llmsDecide WHERE a typed judgment model (TypeSafe's Jev or any System One model) belongs relative to a generative LLM, and who is allowed to authorize what. Use when adding a guardrail, router, verifier, or approval gate around an LLM; when converting a free-text 'LLM-as-judge' step into a typed decision; when a model's own confidence score is being used to authorize its own output; when choosing thresholds, confidence bands, or fallback behavior; or when reviewing an agent/tool-calling pipeline for who holds authority. This is the architecture question — placement, ordering, and authority. For API mechanics, primitive selection, and question wording use the typesafe-ai skill and the live docs instead.