BC byted-las-audio-extract-and-split
Extracts audio tracks from video files and splits long audio into timed segments using Volcengine LAS. Audio extraction and separation from video — pull audio stream from mp4, wmv, avi, mkv, mov, flv video inputs, convert video to audio. Audio splitting, cutting, slicing, trimming, and segmentation — divide long recordings into chunks, clips, or fixed-length segments with configurable duration and indexed file naming. Use this skill when the user wants to extract audio from video files (mp4/wmv/avi/mkv/mov/flv) or separate audio track from video, split long audio into fixed-length segments/chunks, cut or trim audio files, segment podcasts/lectures into clips, or do batch audio splitting.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
-
high Dangerous commands
cmd-install-from-urlscripts/env_init.sh:41Installs a package from an untrusted URL / archivepip install --quiet --upgrade https://las-ai-cn-beijing-online.tos-cn-beijing.volces.com/operator_cards_serving/public/skills/sdk/las_…whl
Files scanned: 8. 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 55/100
- 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
- 40Consistency. Frontmatter name (byted-las-audio-extract-and-split) differs from the folder (byted-las-long-video-understand)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Execution cost. Instruction body is 849 tokens
- 100Running it twice. No mutating operations
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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 696: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.