← Back to Skills Marketplace
Video Prompting Guide
by
Ömer Karışman
· GitHub ↗
· v0.1.5
1340
Downloads
2
Stars
3
Active Installs
2
Versions
Install in OpenClaw
/install video-prompting-guide
Description
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strate...
Usage Guidance
This is primarily a helpful, instruction-only guide for writing video-generation prompts and the examples are consistent with that purpose. Before following the install examples, do not run curl | sh blindly: inspect the installer script (or use the provided checksums) and prefer downloading verified releases or manual install steps. Be aware that running infsh login or the CLI will contact external services and may request credentials or tokens—only provide credentials you expect to give to that service. If you want to avoid executing remote code, you can still use the guide's prompt templates and examples without installing the CLI. If you need higher assurance, ask the publisher for the install script contents or use the manual checksum URL referenced in the doc to validate any downloaded binary.
Capability Analysis
Type: OpenClaw Skill
Name: video-prompting-guide
Version: 0.1.5
The skill is classified as suspicious due to the inclusion of a `curl -fsSL https://cli.inference.sh | sh` command in `SKILL.md`. While presented as a benign installation step for the `inference.sh` CLI and accompanied by a note explaining its function, this pattern constitutes a remote code execution (RCE) vector. If the `cli.inference.sh` domain or the script itself were compromised, it could lead to arbitrary code execution on the agent's host, posing a significant supply chain risk. Additionally, the `allowed-tools: Bash(infsh *)` permission grants broad shell access for `infsh` commands, which, combined with the `curl | sh` instruction, elevates the risk profile beyond benign, despite no clear evidence of intentional malicious behavior from the skill author.
Capability Assessment
Purpose & Capability
Name/description (video prompt best practices) match the content: shot types, camera movement, style keywords and many example prompts for video generation services. Requested capabilities (none) and examples of CLI usage are coherent with a guide.
Instruction Scope
SKILL.md stays within the domain of prompting guidance and example commands for inference.sh; it does not instruct reading arbitrary files or harvesting unrelated data. However it explicitly recommends running a remote install script (curl -fsSL https://cli.inference.sh | sh) and calling infsh login, which introduces runtime behavior (downloading/executing remote code, authenticating) not strictly necessary to the static textual guidance.
Install Mechanism
There is no packaged install spec in the registry (instruction-only), but the document encourages piping a script from cli.inference.sh. That pattern (curl | sh) is convenient but higher-risk than documented package installs; the guide claims checksum verification is available on dist.inference.sh, but the skill does not verify or bundle those artifacts itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. It does show an example 'infsh login' which implies credentials might be needed at runtime, but those are not requested by the skill and are appropriate for the external CLI usage shown.
Persistence & Privilege
No always:true, no install or code files, and no requests to modify other skills or system-wide configuration. The skill is user-invocable and can be used interactively; autonomous invocation is allowed by platform default but not excessive here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-prompting-guide - After installation, invoke the skill by name or use
/video-prompting-guide - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.5
- Adds a comprehensive guide to effective AI video prompt writing for multiple models (Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora)
- Introduces a clear prompt structure formula, with categorized examples for shot types, lighting, camera movement, and style
- Provides prompt templates and breakdowns for common use cases (product demos, documentaries, urban, food, tech)
- Shares model-specific tips to optimize prompt results per platform
- Includes detailed tables for cinematic language, common mistakes, and iterative prompting best practices
- Offers install instructions and links to related skills and documentation for easy reference
v0.1.0
- Initial release of the Video Prompting Guide skill.
- Provides best practices and prompt formulas for AI video generation across popular models (Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora).
- Includes curated lists of shot types, camera movements, lighting terms, and style keywords for improved video results.
- Features model-specific tips and prompt workflow examples.
- Offers common mistakes to avoid, and related skill recommendations for the inference.sh platform.
Metadata
Frequently Asked Questions
What is Video Prompting Guide?
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strate... It is an AI Agent Skill for Claude Code / OpenClaw, with 1340 downloads so far.
How do I install Video Prompting Guide?
Run "/install video-prompting-guide" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Prompting Guide free?
Yes, Video Prompting Guide is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Video Prompting Guide support?
Video Prompting Guide is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Prompting Guide?
It is built and maintained by Ömer Karışman (@okaris); the current version is v0.1.5.
More Skills