Real Skill packageSource verifiedClawHub registry

video2text-ai

处理一切「视频→文字」需求：把本地视频文件或抖音、小红书等公网视频链接，转写成剔除冗余的干净文字稿，并按任意 Prompt 定制总结、小红书/抖音/公众号文案、金句提取、会议纪要、课程拆解、直播复盘、采访整理、中英互译等衍生内容。当用户提到视频转文字、字幕提取、语音转写、视频总结、提取文案、视频翻译或短视频二创时触发；不适用于直播流、需登录/会员/加密的链接、纯音乐视频或批量处理。

Identity and source

Publisher attributionengheng-artregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 56% rule confidence
Package forminstruction with code17 recorded files
Canonical sourceClawHub registryclawhub:engheng-art:scripts
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 · 9/16/2026.claude/skills/video2text-ai

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 · 9/16/2026.agents/skills/video2text-ai

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 · 9/16/2026skills/video2text-ai

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 @engheng-art/scripts
clawhub inspect @engheng-art/scripts --version 1.0.0

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
full text content
Files
17 / 17 inspected as text
Checked
9/16/2026, 4:52:07 AM
Scanner
0.1.3
Policy
1.0.3
5 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • external write action — automatically inferred
2 dependency and API indicators
  • api: github.com
  • api: v18.xhscdn.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
9/16/2026, 4:27:34 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:fd2b7060fa0d29253e9e3eafb183d91178ecb83d650b847496c22b99659f1a94
Show up to 17 recorded paths
  • package.json
  • README.md
  • scripts/api/video.js
  • scripts/config/constants.js
  • scripts/utils/args.js
  • scripts/utils/clean.js
  • scripts/utils/download.js
  • scripts/utils/helper.js
  • scripts/utils/name.js
  • scripts/utils/request.js
  • scripts/utils/token.js
  • scripts/utils/upload.js
  • scripts/utils/utils.js
  • scripts/utils/validator.js
  • scripts/video2text/index.js
  • SKILL.md
  • video2text-ai-1.0.1/SKILL.md

Source changelog

Initial release: Professional video-to-text processing for online/local videos, with AI-powered transcription and versatile content generation. - Supports extracting clean text transcripts from both public video links (e.g., Douyin, Xiaohongshu) and local video files. - Flexible content customization via prompts: summarize, rephrase, extract highlights, translate, and more—all with one command. - Clean output: automatically removes filler words, repetitions, and disfluencies for ready-to-use transcripts. - Command-line interface with simple options (--file, --id, --prompt); detailed usage examples and scene coverage included. - Not suitable for livestreams, login/DRM-protected videos, pure music content, or batch processing. - Requires GUAIKEI_API_TOKEN environment variable for authentication; error handling and user safeguards in place.