BC review-finished-ad
Final QC gate for a rendered 9:16 video ad, run before it is published. One script checks what a machine can decide — exact 1080x1920 size, a hook that moves and speaks in the first second, no frozen stretches, no dead air, no black frames, the brand's real logo on the end card (never a favicon, never a redrawn or wrong logo), end-card colours near the brand palette — and builds one contact sheet (frames with the TikTok/Reels UI safe zones shaded, beside the logo, product images and a font specimen) for the checks that need eyes — font, product likeness, product consistency across scenes, safe zones. A declared silent-text profile covers silent, text-led formats such as kinetic text (no audio track needed, short blank beats between text beats allowed within fixed bounds). Exit 0 PASS / 2 FAIL / 3 ERROR. Use on every finished video master before pinning it.
Final QC gate for a rendered 9:16 video ad, run before it is published.
As a process C 52/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
The same skill appears in 1 more place: goose-skills
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "status" - note
frontmatter-keyunknown frontmatter key "superseded_by"
Process rating: all ten parameters 52/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2825 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 868: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 8 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.