Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Creates AI-generated videos from text scripts, URLs, or PPT/PDF documents using Visla. Use when the user asks to generate a video, turn a webpage into a vide...
Creates AI-generated videos from text scripts, URLs, or PPT/PDF documents using Visla. Use when the user asks to generate a video, turn a webpage into a vide...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Version: 260218-1410 Create AI-generated videos from text scripts, web URLs, or documents (PPT/PDF) using Visla's OpenAPI.
Credentials (NEVER output API keys/secrets in responses): IMPORTANT: Only read local credential files with explicit user consent. Ask the user for permission before reading ~/.config/visla/.credentials If permission is granted and the file exists with valid credentials, use --credentials-file ~/.config/visla/.credentials with the Python CLI. The Bash CLI does not support --credentials-file, so use environment variables instead. If permission is denied, missing, or invalid, ask the user for credentials Only process local files (scripts/docs) explicitly provided by the user, and remind users to avoid uploading sensitive data. Tell the user: this is a one-time setup (once configured, they won't need to do this again) Tell the user: get API Key and Secret from https://www.visla.us/visla-api Ask for the API key/secret explicitly (or ask the user to update the file and confirm). Do not repeat the secrets back in the response. Credential validity check (practical): If credentials exist but running account fails with VISLA_CLI_ERROR_CODE=missing_credentials or VISLA_CLI_ERROR_CODE=auth_failed, treat credentials as invalid and ask the user to provide real ones. File format (bash/zsh): export VISLA_API_KEY="your_key" export VISLA_API_SECRET="your_secret" For PowerShell (temporary session): $env:VISLA_API_KEY = "your_key" $env:VISLA_API_SECRET = "your_secret" Scripts: scripts/visla_cli.py (Python), scripts/visla_cli.sh (Bash)
Default strategy: Prefer Bash on macOS when dependencies are available (the Bash CLI avoids Python SSL-stack issues on some macOS setups). Prefer Python when you're already using a well-configured Python (or when Bash dependencies are missing). Bash (recommended on macOS; also works on Linux-like environments): # With user consent, you may source ~/.config/visla/.credentials export VISLA_API_KEY="your_key" export VISLA_API_SECRET="your_secret" ./scripts/visla_cli.sh <command> Python (cross-platform): python3 scripts/visla_cli.py --key "your_key" --secret "your_secret" <command> # Or, with user consent: python3 scripts/visla_cli.py --credentials-file ~/.config/visla/.credentials <command> Windows native (PowerShell/CMD without Bash; Python): # PowerShell $env:VISLA_API_KEY = "your_key" $env:VISLA_API_SECRET = "your_secret" python scripts/visla_cli.py <command> Windows note: The agent should prefer running the Python CLI on Windows unless it has verified a Bash environment (WSL/Git Bash) is available. For simple scripts, pass directly: python scripts/visla_cli.py script "Scene 1: ..." For multi-line or complex scripts, use stdin with - (recommended, no temp files): @" Scene 1: ... Scene 2: ... "@ | python scripts/visla_cli.py script - If you have Python Launcher installed, py -3 scripts/visla_cli.py <command> may work better than python. Credentials: The Python CLI only reads a credentials file if --credentials-file is explicitly provided. On Windows the default path is typically: %USERPROFILE%\\.config\\visla\\.credentials. Note: do not print credentials. Prefer environment variables or --credentials-file with explicit user consent.
CommandDescription/visla script <script-or-@file>Create video from a script (text or a local file)/visla url <URL>Create video from web page URL/visla doc <file>Create video from document (PPT/PDF)/visla accountShow account info and credit balance Source of truth for the exact CLI surface: run scripts/visla_cli.sh --help or python3 scripts/visla_cli.py --help.
**Scene 1** (0-10 sec): **Visual:** A futuristic calendar flipping to 2025 with digital patterns. **Narrator:** "AI is evolving rapidly! Here are 3 game-changing AI trends." **Scene 2** (10-25 sec): **Visual:** Text: "Trend #1: Generative AI Everywhere." Show tools like ChatGPT. **Narrator:** "Generative AI is dominating industriesโcreating content and images."
The script, url, and doc commands execute the complete flow automatically: Create project Poll until generation completes (may take a few minutes) Auto-export and return download link Execution Instructions: Inform user that video generation takes some time Report progress status periodically during polling
This workflow typically takes 3-10 minutes, but can take up to ~30 minutes in the worst case. Set the task/command timeout to >= 30 minutes (Windows defaults are often ~10 minutes and need to be increased). If you cannot change the timeout, warn the user up front and, on timeout, ask whether to continue or switch to a step-by-step run. If timeout occurs, the CLI returns project_uuid in the output. Inform the user they can manually check project status and continue later using the Visla web interface or API.
/visla script @myscript.txt /visla script "Scene 1: ..." /visla url https://blog.example.com/article /visla doc presentation.pptx /visla account
PowerPoint: .pptx, .ppt PDF: .pdf
Start: Display "Visla Skill v260218-1410" when skill begins End: Display "Visla Skill v260218-1410 completed" when skill finishes
Writing, remixing, publishing, visual generation, and marketing content production.
Largest current source with strong distribution and engagement signals.