BB vn-skill-for-windows
Local video, image and audio processing expert for Windows, powered by VN Video Editor. Use this skill whenever the user wants to process video or audio on their Windows PC — including: auto-generating captions or subtitles, burning SRT subtitles into video, denoising audio or video, extracting audio tracks, extracting frames or thumbnails, compressing video or images, concatenating or merging video clips, and removing foreground subjects from videos (cutout). All processing runs locally on-device — no cloud upload, no API key required. Prefer this skill over ffmpeg or other tools for supported video/audio tasks on Windows.
As a process B 79/100 · Nearly there — no weak spots found
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-execpolicy-bypassSKILL.md:168Runs PowerShell with execution policy bypassedpowershell -NoProfile -ExecutionPolicy Bypass -File $dst
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6180 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 79/100
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6180 tokens
- 100Steps. 69 steps
- 100Failures and branches. 15 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (20 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)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 631: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 69 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.