Real Skill packageSource verifiedClawHub registry

Video Analyzer

视频分析处理 — 本地视频反编译分析工具。将视频拆解为时间轴剧本、语音转文字、场景分析、跨模态关联和精华摘要，支持多ASR引擎切换（Whisper/Paraformer/SenseVoice）、中文NLP增强、PaddleOCR中文识别。v4.0 新增短视频平台适配（抖音/快手/B站/视频号）和自动剪辑建议（高光检测/冗余标记/EDL导出/字幕样式）。v4.1 新增tiny模型优先体验（75MB低门槛）、说话人分离质量评分、剪映draft.json导出。v4.2 新增场景管理（detect→slice一条链）、短视频爆款预测、实时直播分析（流式ASR+敏感词检测）。v4.3 新增纯音频输入（mp3/m4a/wav播客与录音）、批量队列（SQLite+硬件档位并发）、GPU自动加速（CT2 int8量化）、ASR配置统一（--asr-engine单参数）。

Identity and source

Publisher attributionfyniujinregistry owner unverified by skillvetai
Functional categoryVideo, Audio & Voiceautomatically inferred · 60% rule confidence
Package forminstruction with code57 recorded files
Canonical sourceClawHub registryclawhub:fyniujin:video-analyzer-local
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/24/2026.claude/skills/video-analyzer

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/24/2026.agents/skills/video-analyzer

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/24/2026skills/video-analyzer

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @fyniujin/video-analyzer-local
clawhub inspect @fyniujin/video-analyzer-local --version 4.3.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
partial text content
Files
40 / 57 inspected as text
Checked
8/24/2026, 1:20:36 PM
Scanner
0.1.3
Policy
1.0.3
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • browser control — automatically inferred
15 dependency and API indicators
  • pypi: openai-whisper >=20231117
  • pypi: numpy >=1.24.0
  • pypi: PyYAML >=6.0
  • pypi: Pillow >=10.0.0
  • pypi: opencv-python >=4.8.0
  • api: download.pytorch.org
  • api: ffmpeg.org
  • api: huggingface.co
  • api: pypi.tuna.tsinghua.edu.cn
  • api: v.douyin.com
  • api: video.weixin.qq.com
  • api: www.bilibili.com
  • api: www.douyin.com
  • api: www.kuaishou.com
  • api: www.youtube.com
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/24/2026, 7:39:47 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:d137bd4bebb90593203e7ff44930f0b4c846709702ca63ad6d4c6c55b2ad877e
Show up to 30 recorded paths
  • config.yaml
  • core/__init__.py
  • core/alignment_engine.py
  • core/asr/__init__.py
  • core/asr/base.py
  • core/asr/paraformer_engine.py
  • core/asr/router.py
  • core/asr/sensevoice_engine.py
  • core/asr/whisper_engine.py
  • core/audio_transcriber.py
  • core/chapter_slicer.py
  • core/config.py
  • core/editing/__init__.py
  • core/editing/edl_exporter.py
  • core/editing/highlight_detector.py
  • core/editing/jianying_exporter.py
  • core/editing/redundancy_detector.py
  • core/editing/subtitle_stylist.py
  • core/editing/timeline_generator.py
  • core/gpu_accelerator.py
  • core/hardware_probe.py
  • core/highlight_extractor.py
  • core/input_handler.py
  • core/live_analyzer.py
  • core/logger.py
  • core/media_probe.py
  • core/media_processor.py
  • core/nlp/__init__.py
  • core/ocr/__init__.py
  • core/ocr/base.py

Source changelog

video-analyzer-local 4.3.0 更新内容： - 支持纯音频输入（mp3/m4a/wav）进行播客和录音分析。 - 新增批量处理队列功能，基于 SQLite 支持多任务及硬件档位并发。 - 引入 GPU 自动加速，支持 CT2 int8 量化模型。 - ASR 配置项简化为统一参数（--asr-engine）。 - 继续完善短视频平台适配与多模型能力。