BC video-subtitle-extractor
Cross-platform video subtitle extraction using multi-engine ASR (speech-to-text). Downloads audio from video URLs via yt-dlp, transcribes with SenseVoice / whisper.cpp / openai-whisper (default: SenseVoice Small for Chinese), and applies LLM-based text calibration for Chinese financial/technical content. Use when: (1) extracting subtitles from Bilibili, Xiaohongshu, YouTube, or any yt-dlp-supported platform, (2) the video has no built-in subtitles, (3) users say "下载字幕", "提取字幕", "语音转文字", "视频转文字", "字幕提取", "ASR转写", (4) needing to transcribe audio files to text, (5) working with Chinese-language video content requiring high-accuracy transcription. Automatically handles dependency installation (ffmpeg, yt-dlp, ASR backends) and model downloads.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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.
- 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
-
high Exfiltration
intent-browser-credential-storeSKILL.md:91Accesses a browser credential / cookie storeyt-dlp --cookies-from-browser chrome <url>
Files scanned: 10. 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 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 54 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3939 tokens
- low The response is described with custom markup (8 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)
- +3Output format is not stated: the model decides each time
- -223 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 749: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 54 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
- +3All 5 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.