vision-botDescribe images, detect objects, extract text, and analyze webpages. Pass any image URL directly in your task. Responds in your language.
Install via ClawdBot CLI:
clawdbot install unixlamadev-spec/vision-botGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://aiprox.dev/api/orchestrateCalls external URL not in known-safe list
https://aiprox.devAI Analysis
The skill sends image URLs and tasks to a documented external API (aiprox.dev) for processing, which is consistent with its stated vision analysis purpose. While the endpoint is not on a pre-approved safe list, there is no evidence of credential harvesting, hidden instructions, or data exfiltration beyond the declared functionality. The required token appears to be for payment authentication.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Automatically generate alt-text descriptions for images on websites and apps to improve accessibility for visually impaired users. This ensures compliance with WCAG guidelines and enhances user experience across digital platforms.
Count and identify products on store shelves from surveillance or inventory photos to automate stock monitoring. This reduces manual labor and provides real-time data for supply chain optimization.
Extract text from scanned documents, forms, or handwritten notes using OCR to convert physical records into editable digital formats. This streamlines data entry and archival processes for businesses.
Analyze user-uploaded images on social platforms to detect inappropriate objects or text, ensuring community safety. This automates moderation workflows and reduces reliance on human reviewers.
Describe diagrams, charts, or scientific images in multiple languages to aid students and educators in learning materials. This supports multilingual classrooms and remote education initiatives.
Charge per API call based on image analysis volume, with tiered pricing for different usage levels (e.g., free tier for low volume, paid plans for enterprises). This model scales with customer demand and ensures predictable revenue.
License the skill to software companies for embedding into their products (e.g., CMS platforms, mobile apps) under their brand. This generates recurring licensing fees and expands market reach through partnerships.
Offer tailored solutions for specific industries, such as healthcare or finance, with custom training or integration support. This addresses niche needs and commands higher margins through specialized services.
💬 Integration Tip
Include image URLs directly in task strings for simplicity, and ensure the AIPROX_SPEND_TOKEN environment variable is set for authentication.
Scored Apr 19, 2026
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions