← Back to Skills Marketplace
dlazyai

Dlazy Video Scenes

by dlazy · GitHub ↗ · v1.0.5 · MIT-0
cross-platform ⚠ suspicious
608
Downloads
0
Stars
1
Active Installs
6
Versions
Install in OpenClaw
/install dlazy-video-scenes
Description
Detects and splits videos into scene clips using ffmpeg, providing URLs for each clip without analyzing video content.
README (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.

Usage Guidance
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.
Capability Analysis
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.
Capability Tags
requires-sensitive-credentials
Capability Assessment
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.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install dlazy-video-scenes
  3. After installation, invoke the skill by name or use /dlazy-video-scenes
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Slug dlazy-video-scenes
Version 1.0.5
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 6
Frequently Asked Questions

What is Dlazy Video Scenes?

Detects and splits videos into scene clips using ffmpeg, providing URLs for each clip without analyzing video content. It is an AI Agent Skill for Claude Code / OpenClaw, with 608 downloads so far.

How do I install Dlazy Video Scenes?

Run "/install dlazy-video-scenes" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Dlazy Video Scenes free?

Yes, Dlazy Video Scenes is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Dlazy Video Scenes support?

Dlazy Video Scenes is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Dlazy Video Scenes?

It is built and maintained by dlazy (@dlazyai); the current version is v1.0.5.

💬 Comments