ClawHub

视频运镜分析工具

v1.0.0

分析视频镜头切分与运镜方式，生成每个镜头的英文AI提示词及详细运动数据，支持多格式视频文件。

⭐ 0· 63·0 current·0 all-time
by@winme99998
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the included Python script and SKILL.md: the code detects scene cuts, analyzes camera motion (optical flow), produces per-shot movement labels and English prompts, and writes JSON/thumbnail outputs. No unrelated credentials, binaries, or services are requested.
✓
Instruction Scope
Runtime instructions only ask to install common Python packages and run scripts/analyze_shots.py on a local video path. The script reads the provided video, performs frame analysis, and writes results to output/<video>/analysis.json and thumbnails. It does not read other system files, environment variables, or remote endpoints in the visible code.
✓
Install Mechanism
There is no package install spec embedded in the skill bundle; SKILL.md recommends pip installing opencv-python-headless, numpy, pillow — a normal, expected dependency set for local video processing. No downloads from arbitrary URLs or extract steps are present.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. The declared requirements align with its purpose (local video analysis).
✓
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent/system-wide privileges or modify other skills. It runs as an on-demand local script.
Assessment
This skill appears to be a local video analysis tool: it processes videos with OpenCV, generates JSON and base64 thumbnails, and does not request credentials or network access in the provided code. Before installing, consider: (1) installing opencv-python-headless may pull native binaries and increase disk use; (2) processing large videos is CPU- and disk-intensive — run in an environment with sufficient resources; (3) if you received this skill from an untrusted source, review the full script (the repository includes the complete analyze_shots.py) to confirm there are no hidden network calls in portions not visible to you; (4) run in a sandbox or isolated environment if you are concerned about running third‑party code.

Like a lobster shell, security has layers — review code before you run it.

latestvk97c6vct42md73t18023vw20g184brrg

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments