AC taste-distillation
Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot-length distribution, hero stills, screen-blend overlay plates, and a text spec for a generative model. Use when the user wants to capture the look of reference footage, build a repeatable look, mint assets from references, or reproduce someone's grade and pacing.
Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot-length distribution, hero stills, screen-blend…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 15. 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 57/100
- 0Result and completion. Does not say what the result is
- 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
- 30Running it twice. 3 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2162 tokens
- low 11 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 373: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (3 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 11 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 8 не дошли до работы, и об их поведении мы ничего не узнали.
scripts/distill.py | не запустился: distill.py: error: the following arguments are required: --genre |
scripts/mint.py | не запустился: ModuleNotFoundError: No module named 'numpy' |
scripts/taste/assemble.py | не запустился: ImportError: attempted relative import with no known parent package |
scripts/taste/cadence.py | не запустился: ModuleNotFoundError: No module named 'numpy' |
scripts/taste/falapi.py | ничего за пределами своей папки |
scripts/taste/frames.py | не запустился: ModuleNotFoundError: No module named 'cv2' |
scripts/taste/grade.py | не запустился: ModuleNotFoundError: No module named 'cv2' |
scripts/taste/pack.py | ничего за пределами своей папки |
scripts/taste/plates.py | не запустился: ModuleNotFoundError: No module named 'cv2' |
scripts/taste/render3d.py | не запустился: ModuleNotFoundError: No module named 'numpy' |
scripts/taste/timeline.py | ничего за пределами своей папки |
6 Oct 2026