Conciseness

The body is lean and dense: every section carries operational constraints or exact commands, with no explanations of concepts Claude already knows and no padding. Phrases like "A locked-off real-time shot measures ~18x less motion than the reference and reads as a still photo" give decision-relevant rationale in one line, and the note "The Slack standup card above is an illustration of the schema, not a default" pre-empts a real misuse in a single sentence.

Actionability

Guidance is fully executable: the Run block gives copy-paste commands with flags, expected outputs ("card-no-cta.png, card-with-cta.png") and exit semantics ("exit 1 = reject"), card.json is a complete working example, and numeric thresholds are explicit throughout ("--speed (3-8x)", "rejects a mean under 1.5", "normalised to -15 LUFS", "7s", "2.0s").

Workflow Clarity

The three-step sequence (render_card.py → compose.py → measure_motion.py) is clearly ordered in one block, with an explicit validation gate ("measure_motion.py ad.mp4 --cta-at 2.0 # exit 1 = reject") and a failure-checklist guardrail section. It sits at 4 rather than 5 because the recovery loop when the motion gate rejects — re-run with a higher --speed or ask the user for different real footage — is implied ("If there is no real footage, ask the user for some") rather than spelled out as a validate → fix → re-measure step.

Progressive Disclosure

Structure is good: the body is a well-sectioned overview (Run, Choices, Guardrails, Rules for the b-roll, Audio) and implementation detail correctly lives in the bundle scripts, all of which are referenced by name with their roles ("render_card.py draws the two card plates… compose.py… measure_motion.py"). It is 4 rather than 5 because the body is ~84 lines with several dense rule lists that could split into a one-level-deep reference, and the bundled _fonts.py is never mentioned or attributed a role.

Specificity

The description lists multiple concrete actions covering the full pipeline: "render_card.py draws the two card plates with measured geometry and hard guardrails", "compose.py lays the card over the b-roll sped up to read as a timelapse", and "measure_motion.py gates the b-roll". It also pins concrete format details (7s, 9:16, CTA hard-cuts in at 2s, static black card, no voice), so coverage is comprehensive rather than gappy.

Completeness

The "what" is clear and detailed (draw the plates, compose over sped-up b-roll, gate with motion measurement), but there is no "Use when…" clause or equivalent explicit trigger guidance anywhere in the description, capping completeness at 3 per the rubric guidelines. The "when" is at best weakly implied by the format name itself.

Trigger Term Quality

Good natural domain keywords are present ("card ad", "partner icon + brand icon", "CTA", "b-roll", "timelapse", "9:16", "no voice"), which a user making short-form video ads would plausibly say. It falls short of the 5 anchor because "logo-equation card" is coined jargon with no synonyms, and natural variations like "vertical video", "social ad", or "product video" are missing.

Distinctiveness Conflict Risk

This is a clear niche — a named ad format with specific geometry, duration and gating scripts — so it is mostly distinct with minimal conflict risk. It scores 4 rather than 5 only because in a media-creation skill family other card-format renderers would overlap, and the absence of explicit "use when" phrasing leaves triggering to rely on the coined format name.