BB audio-video
Expert audio/video processing with ffmpeg and ffprobe. Use when the user needs to convert, compress, edit, analyze, stream, or process any audio or video file. Triggers on: transcode, convert video, compress video, extract audio, trim clip, merge files, add subtitles, change bitrate, generate thumbnail, probe media, HLS stream, audio normalization, video filter, codec, fps, resolution, aspect ratio, waveform, spectrogram, ffmpeg, ffprobe, stabilize video, video stabilization, shaky footage, 360 video, VR video, equirectangular, cubemap, v360, HDR, tone mapping, HDR to SDR, bt2020, smpte2084, color space, SRT streaming, low latency stream, multi-destination stream, tee muxer, restream, DVR recording, rolling window, repair video, corrupt video, VFR to CFR, variable frame rate, fix sync, metadata, chapter markers, cover art, strip metadata, embed chapters, SMPTE bars, test signal, packet analysis, encoding benchmark.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, execution cost, 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 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-privilegeSKILL.md:54Privilege escalation / world-writable permissionssudo mv "$FFDIR/ffmpeg" "$FFDIR/ffprobe" /usr/local/bin/
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11371 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 40Execution cost. Instruction body is 11371 tokens: crowds the task out of the window
- 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
- 100Steps. 28 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 26 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)
- +3Description length 928: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 120 headings
- +3Step-by-step instructions: 28 items
- +3Output format is stated explicitly
- +4Has examples (85 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.