← 返回 Skills 市场
dlazyai

Dlazy Video Scenes

作者 dlazy · GitHub ↗ · v1.0.5 · MIT-0
cross-platform ⚠ suspicious
608
总下载
0
收藏
1
当前安装
6
版本数
在 OpenClaw 中安装
/install dlazy-video-scenes
功能描述
Detects and splits videos into scene clips using ffmpeg, providing URLs for each clip without analyzing video content.
使用说明 (SKILL.md)

dlazy-video-scenes

English · 中文

Scene split tool: uses ffmpeg to detect and split a video into scene clips, returning only the clip URLs without video content understanding.

Trigger Keywords

  • video-scenes

Authentication

All requests require a dLazy API key, configured through the CLI:

dlazy auth set YOUR_API_KEY

The CLI saves the key in your user config directory (~/.dlazy/config.json on macOS/Linux, %USERPROFILE%\.dlazy\config.json on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the DLAZY_API_KEY environment variable.

Getting Your API Key

  1. Sign in or create an account at dlazy.com
  2. Go to dlazy.com/dashboard/organization/api-key
  3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be rotated or revoked at any time from the same dashboard.

About & Provenance

You can install on demand without persisting a global binary by running:

npx @dlazy/[email protected] \x3Ccommand>

Or, if you prefer a global install, the skill's metadata.clawdbot.install field declares the exact pinned version (npm install -g @dlazy/[email protected]). Review the GitHub source before installing.

How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

  • Prompts and parameters you provide are sent to the dLazy API endpoint (api.dlazy.com) for inference.
  • Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (oss.dlazy.com) so the model can read them — the same flow as any cloud-based generation API.
  • Generated output URLs returned by the API are hosted on oss.dlazy.com.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See dlazy.com for the full service terms.

Usage

CRITICAL INSTRUCTION FOR AGENT: Execute dlazy video-scenes to get the result.

dlazy video-scenes -h

Options:
  --video \x3Cvideo>                      Video (URL) [video: url or local path]
  --durationSeconds \x3CdurationSeconds>  Duration (s)
  --input \x3Cspec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout \x3Cseconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command

Output Format

{
  "ok": true,
  "kind": "text",
  "data": {
    "text": "..."
  }
}

Examples

dlazy video-scenes --prompt 'prompt content'

Error Handling

Code Error Type Example Message
401 Unauthorized (No API Key) ok: false, code: "unauthorized", message: "API key is missing or invalid"
501 Missing required parameter error: required option '--prompt \x3Cprompt>' not specified
502 Local file read error Error: Image file/Video file not found: C:\path o\your\file
503 API request failed (no balance) ok: false, code: "insufficient_balance"
503 API request failed (server error) HTTP status code error (500 server crash)
504 Asynchronous task execution failed === Generation Failed === / {Specific error reason returned by backend, for example "Prompt violates safety policy"}

AGENT CRITICAL INSTRUCTION:

  1. If the execution result returns code: "insufficient_balance", you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: https://dlazy.com/dashboard/organization/settings?tab=credits
  2. If the execution result returns code: "unauthorized" or indicates missing API key, you MUST inform the user to get their API key from https://dlazy.com/dashboard/organization/api-key and save it using dlazy auth set \x3Ckey> and resume the task.

Tips

Visit https://dlazy.com for more information.

安全使用建议
Before installing or using this skill: (1) Verify the dLazy CLI source on the referenced GitHub repo and confirm the npm package version; (2) Understand that invoking the skill runs the dLazy CLI which will upload any local video files to dLazy's media storage (oss.dlazy.com) — do not upload sensitive videos unless you trust the service and its retention policy; (3) The registry metadata omits required items (it doesn’t declare the API key or the install requirement), so ask the publisher or check the upstream repo for clarity about whether ffmpeg is required locally and exactly how uploads are performed; (4) If you will install the CLI, prefer using npx for one-off runs until you vet the package; (5) If you need higher assurance, request the publisher to correct registry metadata (declare DLAZY_API_KEY, required binaries like ffmpeg/npm) or provide signed releases and a clear privacy/retention policy.
功能分析
Type: OpenClaw Skill Name: dlazy-video-scenes Version: 1.0.5 The skill is a wrapper for the dLazy video analysis service, utilizing the `@dlazy/cli` npm package (pinned to version 1.0.8). It functions by uploading local video files to `oss.dlazy.com` and sending requests to `api.dlazy.com` for processing. The instructions in `SKILL.md` are standard for CLI tool operation and error handling, with no indicators of malicious intent, data exfiltration beyond the stated purpose, or prompt injection attacks.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The skill claims to split videos into scene clips using ffmpeg and to be a thin client for the dLazy API. However, the registry metadata lists no required binaries or env vars while SKILL.md metadata declares the CLI (npm/npx) and references ffmpeg and a DLAZY_API_KEY. The absence of declared requirements in the registry is inconsistent with the instructions and the described workflow (uploading local files to oss.dlazy.com and requiring an API key).
Instruction Scope
SKILL.md instructs the agent to execute the dLazy CLI (dlazy video-scenes) and states local video file paths will be uploaded to oss.dlazy.com. That is coherent with a cloud SaaS flow, but the document also contains slightly conflicting language about whether scene-level understanding is performed. The agent will be instructed to cause network uploads of any local files passed to the CLI, so users should expect file upload and retention by the service. The instructions also push explicit user-facing guidance for insufficient-balance and unauthorized errors (benign but prescriptive).
Install Mechanism
The registry lists no install spec, yet SKILL.md metadata includes an explicit npm install -g @dlazy/[email protected] and an npx alternative. This mismatch is important: although the skill is instruction-only in the registry, it expects a third-party CLI (npm package) to be available or installed. The install method is an npm package (traceable), not a direct arbitrary download, but the registry should have declared it.
Credentials
SKILL.md requires a dLazy API key (config file or DLAZY_API_KEY env var) and explains the CLI will save the key under ~/.dlazy/config.json. The registry metadata however lists no required env vars or primary credential. Requesting an API key for a cloud service is proportionate to the stated purpose, but the missing declaration in registry metadata is an inconsistency and reduces transparency. Also, if you pass local files, they will be uploaded to the vendor's OSS endpoint (oss.dlazy.com) — sensitive data implications.
Persistence & Privilege
The skill is not always-enabled and does not request any special platform privileges. It does not declare writing to other skills' configs. The CLI (if installed) stores a key in the user's home config directory, which is a normal behavior for a CLI tool and not inherently a privilege escalation.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install dlazy-video-scenes
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /dlazy-video-scenes 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.5
bump @dlazy/cli to 1.0.8
v1.0.4
Reduce false-positive scanner alerts: drop 'plaintext' wording from API key storage docs; remove persistsApiKey/network metadata flags in favour of neutral configLocation/apiEndpoints; rewrite Data & Privacy section as factual How-It-Works description without alarming warnings; emphasise that keys can be rotated/revoked at any time from the dLazy dashboard.
v1.0.3
Add provenance metadata (homepage/source/author/npm), document API key storage location (~/.dlazy/config.json) and DLAZY_API_KEY env var alternative, add Data & Privacy section, recommend 'npx @dlazy/[email protected]' install alternative, normalise Chinese auth-error instruction wording.
v1.0.2
- Updated AGENT CRITICAL INSTRUCTION: Agents now only need to save the API key themselves when provided and resume the task, without needing to ask the user to send it again. - Clarified instructions in the error handling section for API key and credit issues. - Minor improvements to language consistency across authentication and error guidance sections.
v1.0.1
- Added a dedicated Authentication section with step-by-step instructions for obtaining and configuring the API key. - Updated dlazy CLI dependency to version 1.0.6. - Clarified API key requirements in the documentation.
v1.0.0
Initial release of dlazy-video-scenes. - Scene split tool to detect and split videos into scene clips using ffmpeg. - Returns scene clip URLs; does not perform video content understanding. - Command-line interface with multiple input and output options. - Structured JSON output for integration. - Comprehensive error handling and user guidance for authentication and balance issues.
元数据
Slug dlazy-video-scenes
版本 1.0.5
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 6
常见问题

Dlazy Video Scenes 是什么?

Detects and splits videos into scene clips using ffmpeg, providing URLs for each clip without analyzing video content. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 608 次。

如何安装 Dlazy Video Scenes?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install dlazy-video-scenes」即可一键安装,无需额外配置。

Dlazy Video Scenes 是免费的吗?

是的,Dlazy Video Scenes 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Dlazy Video Scenes 支持哪些平台?

Dlazy Video Scenes 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Dlazy Video Scenes?

由 dlazy(@dlazyai)开发并维护,当前版本 v1.0.5。

💬 留言讨论