AB video-overlay-cleanup
Use this skill when the user wants to clean a video or screen recording by removing overlays such as status bars, notification banners, floating controls, subtitle bars, fixed watermarks, or other surface UI elements. Especially useful for FFmpeg-based frame extraction, region mask generation, fixed-overlay removal with ffmpeg removelogo, and orchestrating frame-by-frame restoration workflows that use Gemini Nano Banana 2 before rebuilding the video.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Glob Grep
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (video-overlay-cleanup) differs from the folder (cleanup-video-overlay)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 89 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 2255 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)
- -32 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 454: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 89 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.