AC brand-kit-to-video
Turn a brand's real assets into a short, on-brand showcase ad — the skill builds (or completes, or generates from scratch) a locked Brand Kit, then drives the same storyboard→video pipeline while keeping the logo, products, and palette strictly consistent. How it works: 1. Picks one of three on-ramps — the user brings ALL assets, SOME (you generate the gaps), or NONE (you generate the identity) 2. Builds and LOCKS a Brand Kit — logo, palette (named + hex), product heroes, type, style — as the reference set every later generation must honor 3. Can stop here (the kit is a deliverable), or go on to co-create a brand-ad shot plan 4. Generates a storyboard (GPT Image 2) referencing the LOCKED kit, then checks logo/product fidelity 5. Renders a short on-brand video (Seedance 2.0) — or composites the real logo back when the model can't reproduce it
As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 70Failures and branches. 5 branches
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3409 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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 854: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.