Conciseness

The body is dense and assumes animation/GSAP competence — no basic-concept padding — using compact tables and imperative rules ('Never run consecutive seams in opposing directions', 'Forbidden eases: bounce.out / elastic.out'), so every section largely earns its place. Not 5 because a few framing/elaborative phrases (the intro 'The failure this prevents...' and some anti-pattern prose) could still be trimmed; not below 4 since it is clearly efficient rather than verbose.

Actionability

Gives copy-paste-ready commands ('node <SKILL_DIR>/scripts/seam-stamp.mjs --ledger ledger.json --write index.html', 'seam-gate.mjs probe --t <cut>') plus concrete numeric parameters ('0.3–0.75s pause', '≤ ~800ms', 'exit ≈ 75% of entry', 'entry ~127% of exit', '≥50% through the notional path') and named eases (power4.in/out, back.out(1.4–1.7)). For a doctrine/law skill this is fully actionable guidance covering the common cases; not below 5 since code and specifics are both present and executable.

Workflow Clarity

The authoring order 'vector ledger → STAMP the master seams → sustained-motion route per phase → carriers and causes → build comps → VERIFY (scripts/seam-gate.mjs)' is an explicit sequence, with a hard validation gate ('run the verifier, exit 0 or the seam is not done'), a re-run-on-edit feedback loop ('Edits re-open the seam'), and an anti-patterns table as a checklist. Not below 5; validation is present so the batch/destructive cap at 3 does not apply.

Progressive Disclosure

References are well-signaled and verified real — 'references/seam-gate.md' (schema/usage), 'scripts/seam-stamp.mjs' and 'scripts/seam-gate.mjs', plus a route-map table delegating the catalog to 'cut-the-curve', 'oversized-cursor', and 'seam-craft' — all one level deep. Not 5 because the body still carries a substantial amount of doctrine inline (the full vector law, current, carriers, performance routes) rather than splitting more into referenced files, even though that is arguably appropriate for a gateway law skill; not below 4 since structure and navigation are genuinely good.

Specificity

Names a concrete domain (motion law for HyperFrames multi-scene video) and enumerates many specific sub-capabilities — 'the vector law (incl. the Z scale-sign rule), the film's current, carrier elements, causal motion, the Seam Gate (build-gate enforcement), the ban on idle wobble, stillness-before-climax, and the sustained-motion routes' — plus routes to named technique skills, giving comprehensive coverage. Not below 5 since coverage is exhaustive and concrete rather than just 'several' actions.

Completeness

Explicit 'what' ('The high-level motion law that makes a multi-scene video feel like ONE continuous camera move...') and explicit 'when' ('GATEWAY — load FIRST before composing any HyperFrames animation or video'), answering both with a concrete trigger phrase. Not below 5 because the 'Use when' equivalent is present and concrete, so it is not capped at 3.

Trigger Term Quality

The bracketed tag list '[continuity, direction, vector, momentum, seam, transition, ease, performance, idle-motion, narrative-motion, film-grammar]' plus 'animation', 'video', and 'camera move' gives good keyword coverage with relevant synonyms, but several terms (narrative-motion, film-grammar, momentum) are more technical than phrases a user would naturally say. Not 5 because a few natural user-facing terms are missing; not below 4 since most terms are genuinely natural for the motion/animation domain.

Distinctiveness Conflict Risk

It carves a clear niche (high-level gateway/law that 'SUPERSEDE generic / upstream motion guidance') and routes to low-level technique skills, making it mostly distinct; but trigger terms like 'seam', 'transition', and 'ease' overlap with the routed implementation skills (cut-the-curve, seam-craft), creating minor conflict risk. Not 5 due to that overlap with closely related skills; not below 4 since the gateway-vs-implementation split keeps it largely distinguishable.