← Back to Skills Marketplace
Zyka AI
by
Harshit Varshney
· GitHub ↗
· v0.4.12
· MIT-0
76
Downloads
2
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install zyka-ai
Description
Generate AI videos, images, voice, and use AI apps using the Zyka CLI. Use when users want to create AI-generated media — videos (Sora, Veo, Kling, WAN, Seed...
Usage Guidance
This skill is a documentation wrapper for the Zyka CLI and appears coherent, but before installing or enabling it: 1) Inspect the npm package source and the linked GitHub repo (npm packages can execute arbitrary code during install). 2) Only provide a least-privilege Zyka API key and avoid uploading private/proprietary files (the CLI uploads files to Zyka and may proxy to third-party models). 3) Decide whether to allow autonomous agent invocation (it can spend credits). 4) Monitor Zyka dashboard usage and rotate/delete the key when no longer needed. If you're uncomfortable running a global npm package, consider running the CLI in an isolated environment/container.
Capability Analysis
Type: OpenClaw Skill
Name: zyka-ai
Version: 0.4.12
The zyka-ai skill bundle provides a legitimate interface for the Zyka AI platform, allowing an agent to generate images, videos, and audio using the 'zyka' CLI. While the skill requires high-privilege actions such as installing a global npm package and uploading local files to a remote API, these behaviors are clearly aligned with the stated purpose and are accompanied by transparent security and privacy disclosures in SKILL.md. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description match the declared requirements: the skill expects a local 'zyka' binary and a ZYKA_API_KEY and the SKILL.md documents installing the 'zyka' npm package. Declared binaries, env var, and npm install align with media-generation via Zyka.
Instruction Scope
SKILL.md instructs the agent to install and call the local 'zyka' CLI and to upload user-specified media files to Zyka's API. It explicitly warns about uploads and asks not to write JS scripts. The instructions do not request unrelated files, system secrets, or hidden endpoints.
Install Mechanism
Install spec uses the public npm package 'zyka' (creates 'zyka' binary) which is appropriate for a CLI. npm packages can contain arbitrary code, so inspecting the package source and the referenced GitHub repo before running a global install is recommended.
Credentials
Only ZYKA_API_KEY is required and it's declared as the primary credential. This is proportionate to a third‑party media-generation service; treat the key as a sensitive secret because the CLI uploads local files and invokes downstream model providers.
Persistence & Privilege
always:false and agent-autonomy (disable-model-invocation:false) are normal. Note: autonomous agent use can invoke the Zyka API and consume credits without per-call confirmation, so consider whether you want that behavior enabled.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install zyka-ai - After installation, invoke the skill by name or use
/zyka-ai - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.4.12
remove duplicate skill subfolder; works with [email protected] (CLI now installable from npm)
v0.4.11
Install spec uses latest npm version (no pin) so users get bug fixes; switched runtime examples from npx to local zyka binary
v0.4.10
Declare npm install spec, switch from npx to local zyka binary, address Install Mechanism scanner note
v0.4.9
Add Security & Privacy section — disclose data flow, API key handling, and pinned npx behavior
v0.4.8
Fix frontmatter parsing — propagate requires metadata to registry
v0.4.7
Declare ZYKA_API_KEY env requirement, add homepage/repository/license metadata, pin npx install to 0.4.6 — addresses security scan flags
v0.4.6
v0.4.6 — gpt_image_2, voxcpm2/sarvam/gemini-tts, voice-isolation, voice-changer S2S
Metadata
Frequently Asked Questions
What is Zyka AI?
Generate AI videos, images, voice, and use AI apps using the Zyka CLI. Use when users want to create AI-generated media — videos (Sora, Veo, Kling, WAN, Seed... It is an AI Agent Skill for Claude Code / OpenClaw, with 76 downloads so far.
How do I install Zyka AI?
Run "/install zyka-ai" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Zyka AI free?
Yes, Zyka AI is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Zyka AI support?
Zyka AI is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Zyka AI?
It is built and maintained by Harshit Varshney (@varshneyhars); the current version is v0.4.12.
More Skills