← Back to Skills Marketplace
lolieatapple

QuiverAI Skill

by lolieatapple · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
106
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install quiver-ai-skill
Description
Generate SVGs from text prompts and convert raster images (PNG/JPG/WebP) to SVG using QuiverAI's AI models. Use when user asks to create icons, illustrations...
Usage Guidance
This skill looks coherent for creating and vectorizing SVGs, but check a few things before trusting it: 1) The SKILL.md asks you to install 'quiver-ai-cli' from npm — verify the package name, author, and reviews on the npm registry before running a global install (or prefer a non-global/sandboxed install). 2) The CLI expects an API key that will be stored in the quiver CLI config on disk; be aware where that config is stored and what API/account the key grants. 3) When vectorizing, the agent will operate on local files or URLs you supply — avoid pointing it at sensitive local files. 4) If you need least privilege, create a dedicated API key with limited scope for this tool. If you want additional assurance, ask the maintainer/source of this skill for a verified homepage or a link to the quiver CLI repository before installing.
Capability Analysis
Type: OpenClaw Skill Name: quiver-ai-skill Version: 1.0.0 The skill bundle provides a standard interface for the 'quiver-ai-cli' tool to generate and vectorize SVGs. It uses restricted bash permissions (Bash(quiver:*)) and follows a logical workflow for file generation and verification without any evidence of data exfiltration, obfuscation, or malicious prompt injection.
Capability Assessment
Purpose & Capability
The skill claims to generate/vectorize SVGs and the SKILL.md exclusively documents using a 'quiver' CLI to do exactly that. Required tools (quiver, filesystem read/write) are consistent with creating and returning SVG files; there are no unrelated service credentials or unrelated binaries requested.
Instruction Scope
Instructions are narrowly scoped to running the quiver CLI, saving outputs (-o), and reading the produced SVGs. One behavioral note: the skill advises passthrough of arbitrary user arguments (quiver $ARGUMENTS) and allows reading files provided by the user (for vectorize), which is expected for this use but gives the agent the ability to operate on arbitrary local files the user points to.
Install Mechanism
No registry install spec is included; the SKILL.md recommends installing a global npm package (npm install -g quiver-ai-cli). That is an expected way to obtain a CLI, but the package name/source is not validated here. Global npm installs can require elevated permissions on some systems and introduce external code from the public registry — reasonable for a CLI but worth verifying the package's trustworthiness.
Credentials
The skill metadata declares no required env vars, but SKILL.md instructs users to set an API key via 'quiver config set api_key <key>' (the CLI's own config). This is proportionate to the stated purpose, but the skill does not declare where the key will be stored or any primaryEnv; users should be aware the key will reside in the CLI config (on disk) rather than in the registry metadata.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent platform privileges. It uses Read/Write to create and inspect output SVG files in the working directory, which matches its purpose. Autonomous invocation is allowed by default but is not combined with unusual credential or persistence demands here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install quiver-ai-skill
  3. After installation, invoke the skill by name or use /quiver-ai-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the QuiverAI SVG Generation Skill. - Generate SVGs from text prompts or vectorize raster images (PNG/JPG/WebP) using the `quiver` CLI. - Supports commands for text-to-SVG (`generate`), image-to-SVG (`vectorize`), and listing available AI models. - Always saves SVG output to a file for user access and provides file details upon completion. - Includes configuration guidance for installing and authenticating the `quiver` CLI. - Offers workflow tips for optimal SVG generation and troubleshooting common issues.
Metadata
Slug quiver-ai-skill
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is QuiverAI Skill?

Generate SVGs from text prompts and convert raster images (PNG/JPG/WebP) to SVG using QuiverAI's AI models. Use when user asks to create icons, illustrations... It is an AI Agent Skill for Claude Code / OpenClaw, with 106 downloads so far.

How do I install QuiverAI Skill?

Run "/install quiver-ai-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is QuiverAI Skill free?

Yes, QuiverAI Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does QuiverAI Skill support?

QuiverAI Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created QuiverAI Skill?

It is built and maintained by lolieatapple (@lolieatapple); the current version is v1.0.0.

💬 Comments