← Back to Skills Marketplace
55
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install revid-prompt-to-video
Description
Turn a one-line idea into a full short video — Revid writes the script, picks visuals, and assembles the cut. Use when the user has a topic but no script.
Usage Guidance
This skill appears to do exactly what it says: call Revid's public API to render videos and poll status. Before installing, 1) confirm you trust https://www.revid.ai and that the REVID_API_KEY you provide has the minimal needed permissions; 2) avoid sending sensitive/private prompts or PII to the service (the API call will transmit the prompt and other render metadata to Revid); 3) if you plan to use the example script, ensure curl and jq are available and inspect the script (it requires REVID_API_KEY in the environment); and 4) review Revid's privacy/retention policy if your inputs include customer data or proprietary content.
Capability Analysis
Type: OpenClaw Skill
Name: revid-prompt-to-video
Version: 1.2.0
The skill provides a standard interface for interacting with the Revid.ai API to generate videos from text prompts. The documentation (SKILL.md) and example script (examples/run.sh) correctly implement the API's render and status polling workflow using the provided REVID_API_KEY, with no evidence of malicious behavior, data exfiltration, or prompt injection.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description map directly to calling Revid's API to render videos. The declared config key REVID_API_KEY matches the API usage in SKILL.md and example code.
Instruction Scope
SKILL.md instructs POST /api/public/v3/render and polling /status on https://www.revid.ai and only references REVID_API_KEY. This stays within the expected scope. Note: the shipped example script uses curl and jq (network calls and local JSON manipulation); those binaries are not declared as required in registry metadata — the examples assume them but the skill itself is instruction-only.
Install Mechanism
No install spec — instruction-only. Nothing is downloaded or written to disk by the skill itself, which minimizes install-time risk.
Credentials
Only a single service credential (REVID_API_KEY) is required, which is proportional to the stated purpose. No unrelated secrets or broad system paths are requested.
Persistence & Privilege
always:false and default invocation settings are used. The skill does not request permanent system presence or privileges beyond calling the external API.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install revid-prompt-to-video - After installation, invoke the skill by name or use
/revid-prompt-to-video - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
- Improved documentation for easier use and troubleshooting
- Clarified when to use this skill versus other related video skills
- Detailed required and optional input fields
- Added practical examples and common failure modes with solutions
- Improved API call template and response flow overview
Metadata
Frequently Asked Questions
What is Prompt to Video?
Turn a one-line idea into a full short video — Revid writes the script, picks visuals, and assembles the cut. Use when the user has a topic but no script. It is an AI Agent Skill for Claude Code / OpenClaw, with 55 downloads so far.
How do I install Prompt to Video?
Run "/install revid-prompt-to-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Prompt to Video free?
Yes, Prompt to Video is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Prompt to Video support?
Prompt to Video is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Prompt to Video?
It is built and maintained by api00 (@api00); the current version is v1.2.0.
More Skills