Skip to content
TrustedSkillsbeta
Back to all skills

Ai Multimodal

Listed
binhmuc·vlatest·ai-ml

Analyzes images, text, and audio to extract insights and generate creative content across diverse applications.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add binhmuc/autobot-review --skill ai-multimodal -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

binhmuc

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 2 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: aistudio.google.com, cloud.google.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    aistudio.google.comundeclaredcloud.google.comundeclared

    What it found (3 of 4)

    • .claude/skills/ai-multimodal/scripts/check_setup.py:222contacts aistudio.google.com
      print("   → Visit: https://aistudio.google.com/apikey")
    • .claude/skills/ai-multimodal/scripts/gemini_batch_process.py:328contacts aistudio.google.com
      1. Enable billing: https://aistudio.google.com/apikey
    • .claude/skills/ai-multimodal/scripts/gemini_batch_process.py:817contacts aistudio.google.com
      "https://aistudio.google.com/apikey or use Google Cloud credits."

  • No credential access: failed

    Touches credential material in 4 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found (3 of 4)

    • .claude/skills/ai-multimodal/scripts/check_setup.py:227environment file outside the project
      print(f"   $ echo 'GEMINI_API_KEY=your-api-key-here' >> ~/.claude/.env")
    • .claude/skills/ai-multimodal/scripts/gemini_batch_process.py:85environment file outside the project
      5. ~/.claude/skills/ai-multimodal/.env (user skill-specific)
    • .claude/skills/ai-multimodal/scripts/gemini_batch_process.py:86environment file outside the project
      6. ~/.claude/skills/.env (user shared)

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned binhmuc/autobot-review at a2b4913a35.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
a2b4913a35
Manifest
.claude/skills/ai-multimodal/SKILL.md
Scanned
16 files, 6,159 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The binhmuc-ai-multimodal skill enables AI agents to process and understand both text and image inputs. It allows users to provide images alongside textual prompts, enabling more complex and nuanced interactions. This skill is designed for use with the binhmuc/autobot-review agent.

When to use it

  • Image analysis requests: When you need an AI to describe or analyze content within an image (e.g., "What objects are in this picture?").
  • Visual question answering: To ask questions about the contents of an image (e.g., “How many people are in this photo?”).
  • Combined text and visual context: When providing both textual instructions and a relevant image to guide the AI's response.
  • Reviewing multimodal content: For analyzing documents or presentations that include images alongside text.

Key capabilities

  • Image input processing
  • Text input processing
  • Multimodal understanding (combining text and image data)
  • Integration with binhmuc/autobot-review agent

Example prompts

  • "Describe the scene in this image." [followed by an image upload]
  • “What is the main topic of this document, considering both the text and the included diagram?” [followed by a document upload and an accompanying image]
  • "Analyze this photo and tell me what emotions are being conveyed." [followed by an image upload]

Tips & gotchas

The skill requires the binhmuc/autobot-review agent to be installed and active. Ensure that image uploads are supported within your AI agent's interface for optimal functionality.