Bilibili Audio Transcribe
v0.1.0Download audio from Bilibili or b23.tv links and transcribe it into txt, srt, and segment JSON with yt-dlp, ffmpeg, and faster-whisper. Use when a user asks...
⭐ 1· 51·0 current·0 all-time
by@yizh4ng
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description state downloading audio from Bilibili and transcribing with yt-dlp, ffmpeg, and faster-whisper. The bundle contains a downloader+ASR Python script, a bootstrap script, and a requirements.txt listing yt-dlp and faster-whisper. Required binaries (ffmpeg/ffprobe) are documented in SKILL.md. There are no unrelated environment variables or credentials requested.
Instruction Scope
SKILL.md restricts use to bilibili.com and b23.tv, instructs running the included script, and documents outputs and failure modes. The Python script validates hosts, sanitizes filename stems, downloads media via yt-dlp, probes audio with ffprobe, and runs faster-whisper for transcription. It writes files to a relative downloads/ directory. There are no instructions to read unrelated local secrets or to exfiltrate data to external endpoints.
Install Mechanism
There is no platform install spec; the repo provides a bootstrap shell script that creates a virtualenv and pip-installs packages from a local requirements.txt (yt-dlp, faster-whisper). This is a moderate-risk but expected mechanism for Python tooling; packages come from PyPI rather than arbitrary personal URLs or archives.
Credentials
The skill declares no required environment variables or credentials and the code does not attempt to read secrets. Network access is limited to fetching media via yt-dlp (expected). No unrelated service keys or config paths are requested.
Persistence & Privilege
always is false, model invocation is allowed (normal for skills). The skill does not request permanent presence, does not modify other skills, and does not alter system-wide agent config. It writes outputs to the local file system within a relative downloads/ directory.
Assessment
This skill appears coherent with its purpose. Before installing/run: 1) ensure you trust running yt-dlp and faster-whisper from PyPI in your environment; run the provided bootstrap script inside an isolated Python virtualenv; 2) install ffmpeg/ffprobe from your OS package manager; 3) be aware the script will download the media you point it at and write files to a relative downloads/ directory (so don’t point it at private or authenticated links unless you expect that); 4) transcription can be CPU/GPU- and time-intensive for longer videos—prefer smaller models for quick results; and 5) inspect the scripts yourself if you need higher assurance (they validate hosts and sanitize filenames, which is good).Like a lobster shell, security has layers — review code before you run it.
latestvk977k8yfppcs3xv8mtvjvj8dnd83zawq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.