Skip to content
TrustedSkillsbeta
Back to all skills

Canghe Image Gen

Listed
freestylefly·vlatest·ai-ml

Generate unique, stylized images from text prompts using freestylefly's advanced AI image generation capabilities.

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 freestylefly/canghe-skills --skill canghe-image-gen -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

freestylefly

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: api.canghe.ai, dashscope.aliyuncs.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

    api.canghe.aiundeclareddashscope.aliyuncs.comundeclaredgenerativelanguage.googleapis.commodel providerapi.openai.commodel provider

    What it found

    • skills/canghe-image-gen/scripts/main.ts:41contacts api.canghe.ai
      CANGHE_BASE_URL           Custom Canghe endpoint (default: https://api.canghe.ai/v1)
    • skills/canghe-image-gen/scripts/providers/canghe.ts:26contacts api.canghe.ai
      const base = process.env.CANGHE_BASE_URL || "https://api.canghe.ai/v1";
    • skills/canghe-image-gen/scripts/providers/dashscope.ts:12contacts dashscope.aliyuncs.com
      const base = process.env.DASHSCOPE_BASE_URL || "https://dashscope.aliyuncs.com";

  • No credential access: failed

    Touches credential material in 3 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

    • skills/canghe-image-gen/scripts/main.ts:43environment file outside the project
      Env file load order: CLI args > EXTEND.md > process.env > <cwd>/.canghe-skills/.env > ~/.canghe-skills/.env`);
    • skills/canghe-image-gen/scripts/main.ts:370environment file outside the project
      "Create ~/.canghe-skills/.env or <cwd>/.canghe-skills/.env with your keys."
    • skills/canghe-image-gen/SKILL.md:113instructs the agent to access environment file outside the project(in the instructions, not code)
      **Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.canghe-skills/.env` > `~/.canghe-skills/.env`

  • 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 freestylefly/canghe-skills at dd0bf35595.

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

Commit
dd0bf35595
Manifest
skills/canghe-image-gen/SKILL.md
Scanned
8 files, 1,466 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

This skill enables AI agents to generate images directly using the Canghe platform. It allows for creating visual assets based on text prompts or specific design requirements without manual intervention.

When to use it

  • Rapidly prototype visual concepts during early-stage product design.
  • Generate consistent character or asset variations for storytelling projects.
  • Create placeholder graphics for documentation, presentations, or marketing drafts.
  • Automate the creation of simple illustrations when human artists are unavailable.

Key capabilities

  • Direct image generation via text-to-image models hosted on Canghe.
  • Integration with AI agent workflows to trigger visual output automatically.
  • Support for various aspect ratios and resolution settings (implied by standard image gen).
  • Accessible through the TrustedSkills registry for easy installation.

Example prompts

  • "Generate a futuristic cityscape at sunset with flying vehicles."
  • "Create a minimalist logo design for a coffee brand using green and brown tones."
  • "Produce a 3D render of a modern living room interior with natural lighting."

Tips & gotchas

Ensure your AI agent has proper permissions to call external image generation APIs if the skill requires network access. Be specific in your prompts to avoid generic or low-quality outputs, as Canghe's models may vary in interpretation based on input clarity.