BF video-rough-cut
Use this skill for fast rough-cut cleanup of a single talking-head or voiceover video using the local B-Roll Studio rough-cut pipeline. It uploads one raw video, removes pauses and breaths, trims head/tail clutter, optionally applies brightness correction, stabilization, centering, and beauty, then exports a cleaned draft. Triggers on: 粗剪, 去停顿, 去气口, 去头尾, 自动粗剪, 防抖, 人物居中, 亮度修正, talking head cleanup, rough cut, jump cut cleanup.
As a process F 56/100 · Will not run — References files that are not bundled: references/api.md, references/pipeline.md, scripts/run_rough_cut.py
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/api.md - warning
missing-refreference to a missing file: references/pipeline.md - warning
missing-refreference to a missing file: scripts/run_rough_cut.py
Process rating: all ten parameters 56/100
- 0Tools and files. 3 referenced file(s) missing: references/api.md, references/pipeline.md, scripts/run_rough_cut.py
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 41 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 756 tokens
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 429: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.