← Back to Skills Marketplace
503
Downloads
0
Stars
2
Active Installs
3
Versions
Install in OpenClaw
/install material-report
Description
Analyze ad material videos and produce a markdown report with framework, material traits, and acquisition keywords, then propose new material production fram...
Usage Guidance
This skill appears coherent and matches its description. Before installing or running it, be aware that: it will need access to the video file you provide and may create a directory of extracted frame images in the current working directory (potentially many files). If you prefer not to have files written, provide an existing frame-folder path or run the skill from a controlled directory. The skill does not request credentials or network endpoints, but avoid supplying sensitive videos you do not want processed locally. If you want more assurance, you can ask for a dry-run that only reads metadata (no frame extraction) or run the skill in an isolated workspace.
Capability Analysis
Type: OpenClaw Skill
Name: material-report
Version: 1.0.2
The skill instructs the AI agent to execute the `ffmpeg` command for video frame extraction. While `ffmpeg` is necessary for the stated purpose of video analysis, the execution of external commands based on user-provided input (like video paths) without robust sanitization by the agent's runtime environment creates a significant shell injection vulnerability (potential Remote Code Execution). There is no clear evidence of intentional malicious behavior such as data exfiltration or backdoor installation within the provided instructions or templates.
Capability Assessment
Purpose & Capability
Name/description (analyze ad videos and produce a report) match the instructions: verifying a video, extracting frames, analyzing structure, and producing a markdown report. No unrelated credentials, binaries, or services are requested.
Instruction Scope
Instructions legitimately require filesystem access to the provided video and may write extracted frame images into a folder under the current working directory. This is expected for video analysis but worth noting: the skill will check paths, read metadata, and may save many image files. It does not instruct the agent to read unrelated files, access environment variables, or transmit data externally.
Install Mechanism
No install spec or remote downloads — the skill is instruction-only and relies on ffmpeg being present on the user's system. The skill explicitly prompts the user to install ffmpeg if missing (but does not provide installation commands). This is low-risk.
Credentials
No environment variables, credentials, or config paths are requested. All required inputs are user-supplied (video path, category/vertical, platform).
Persistence & Privilege
Skill is not marked always:true and does not request persistent or cross-skill configuration. Autonomous invocation is allowed by default but is not combined with other concerning privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install material-report - After installation, invoke the skill by name or use
/material-report - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
material-report 1.0.2
- Added explicit use of ffmpeg for frame extraction, with instructions to prompt the user if ffmpeg is missing.
- Included option for users to manually provide an existing frame image folder path if ffmpeg is unavailable.
- Clarified not to provide installation instructions within the skill itself.
- No changes to core analysis or report output flow.
v1.0.1
Add instructions for video frame segmentation.
v1.0.0
material-report v1.0.0
- Initial release with comprehensive ad video analysis and markdown reporting workflow.
- Analyzes video framework, material traits, and acquisition keywords.
- Proposes new creative frameworks and produces detailed storyboard tables.
- Ensures consistent duration with original video unless specified otherwise.
- Requests/infers category and platform info for tailored analysis and creative direction.
- Handles frame extraction efficiently, reusing existing frames if available and saving under a video-named folder.
Metadata
Frequently Asked Questions
What is Material Report?
Analyze ad material videos and produce a markdown report with framework, material traits, and acquisition keywords, then propose new material production fram... It is an AI Agent Skill for Claude Code / OpenClaw, with 503 downloads so far.
How do I install Material Report?
Run "/install material-report" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Material Report free?
Yes, Material Report is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Material Report support?
Material Report is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Material Report?
It is built and maintained by FuQ (@fevolq); the current version is v1.0.2.
More Skills