The body is dense and policy-heavy without concept-teaching padding (no 'what a PDF is' style explanation), but at ~1200 lines it repeats the same constraints across 'Hard Rules', 'Start Gates', 'Completion Gates', and per-command 'may/must not' lists, which could be tightened. It is not a 1 because it does not explain known concepts or pad with fluff, and not a 3 because the redundancy and length exceed a lean every-token-earns-its-place standard.

Provides concrete, copy-paste-ready bash/node commands throughout (status JSON reads, ref resolution, run-dir creation, capped git diff/log commands, create-goal-scratchpad.mjs and check-complete.mjs invocations) plus explicit payload and plan-template shapes. Matches the 'fully executable code/commands; specific examples; copy-paste ready' anchor, so it is not a 2.

A clearly numbered 7-step process with explicit validation checkpoints ('prove ancestry', 'Only proceed when valid', Start/Completion Gates, check-complete.mjs) and feedback loops (review staleness verdicts, fix-and-revalidate, plan-then-stop-for-user-review boundary). Matches the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor, so it is not a 2.

Sections are well-organized with clear navigation (Commands, Scoped Planning, per-command sections, Hard Rules, Gates, steps 1-7, Output) and there are no 2+-level nested reference chains, but no bundle files exist and the body is a single ~1200-line monolith whose detailed per-command sections could be split into one-level-deep reference files. It is not a 1 because organization and navigation are present, and not a 3 because content is not split across well-signaled one-level-deep files.

Lists multiple concrete actions ('planning, status, review, dashboard, apply, and tracking', 'audit newer shadcn docs changes', 'compare ../shadcn/apps/v4 with apps/www', 'update the shadcn sync baseline', 'decide what to adopt, fork, defer, or exclude'), matching the 'lists multiple specific concrete actions' anchor. It is not a 2 because it goes well beyond naming a domain and a few actions.

Explicitly answers 'what' (Autogoal-backed planning/status/review/dashboard/apply/tracking for upstream shadcn docs syncs) and 'when' via an explicit 'Use when the user asks for...' clause enumerating concrete triggers, matching the highest anchor. It is not a 2 because the 'when' is explicit, not implied or missing.

Covers natural trigger terms a user would actually say ('sync shadcn docs', 'audit newer shadcn docs changes', 'update the shadcn sync baseline') plus exact command tokens ('sync-shadcn', 'sync-shadcn status', 'sync-shadcn review', 'sync-shadcn dashboard', 'sync-shadcn apply', 'sync-shadcn <feature>'). Good coverage of natural terms rather than generic jargon, so it is not a 2.

Occupies a clear niche (upstream shadcn docs syncs into Plate docs) with distinct command and feature-scope triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor. It is not a 2 because the scope is sharply product-specific rather than broadly overlapping.