Media Tools

What it does

When your agent uses it

• Claude needs to generate images
• Run vision analysis with a specific provider rather than relying on Claudes built-in image understanding

Example prompts

• “/media-tools”

Requirements

• Python 3
• A credential in OPENROUTER_API_KEY
• A credential in GEMINI_API_KEY
• Pre-approved tools (allowed-tools): Bash, Read

What it can do on your machine

Read from SKILL.md and the folder at commit dd902b1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 13 files in scripts/ (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • openrouter.ai
  • api.openai.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENROUTER_API_KEY
  • GEMINI_API_KEY
  • OPENAI_API_KEY
  • MINIMAX_API_KEY
  • DASHSCOPE_API_KEY
  • BYTEPLUS_API_KEY
  • ANTHROPIC_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Media Tools loads about 1.5k tokens when it runs. Until then it costs about 221 tokens; SKILL.md has 264 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~221

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:3

  /multi-line prompts, auto UTF-8 stdout, `.env` auto-load, and `--list-providers` diagnostic. Use when Claude needs to ge

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from therichardngai-code/gpt-image-2-pro-max at commit dd902b1, republished under its MIT licence (© therichardngai-code). 264 words, ~1,506 tokens.

name

media-tools

description

Two CLI tools for image generation + vision analysis using goclaw's provider-chain pattern. `create_image` generates images via 7-provider chain (ChatGPT-OAuth/Codex, OpenRouter, Gemini, OpenAI, MiniMax, DashScope, BytePlus) — first available credential wins (OAuth session OR API key), embeds prompt into PNG tEXt metadata, saves to date-folder workspace. The ChatGPT-OAuth provider reads from `~/.codex/auth.json` so a ChatGPT Plus / Codex login works without any API key. `read_image` analyzes images via 4-provider vision chain (OpenRouter, Gemini, Anthropic, DashScope) — accepts file path. Supports `--prompt-file` for long/multi-line prompts, auto UTF-8 stdout, `.env` auto-load, and `--list-providers` diagnostic. Use when Claude needs to generate images or run vision analysis with a specific provider rather than relying on Claude's built-in image understanding.

allowed-tools

Bash, Read

license

MIT

.claude/skills/.venv/Scripts/python.exe -m pip install -r .claude/skills/media-tools/requirements.txt

# Image generation
$env:OPENROUTER_API_KEY = "..."   # OpenRouter (aggregator, OpenAI-compat)
$env:GEMINI_API_KEY     = "..."   # Google AI Studio
$env:OPENAI_API_KEY     = "..."   # OpenAI gpt-image
$env:MINIMAX_API_KEY    = "..."   # MiniMax image-01
$env:DASHSCOPE_API_KEY  = "..."   # Alibaba Qwen / Wan2.6
$env:BYTEPLUS_API_KEY   = "..."   # ByteDance Seedream

# Vision (some keys overlap with image gen)
$env:ANTHROPIC_API_KEY  = "..."   # Anthropic Claude vision

# Optional API base overrides (for proxies / regional endpoints)
$env:OPENROUTER_API_BASE = "https://openrouter.ai/api/v1"
$env:OPENAI_API_BASE     = "https://api.openai.com/v1"
# etc — see lib/env_keys.py for full list

.claude/skills/.venv/Scripts/python.exe .claude/skills/media-tools/scripts/create_image.py \
  --prompt "a cyberpunk cat in neon rain, ukiyo-e style" \
  --aspect-ratio 16:9 \
  --filename-hint "neon-cat"

.claude/skills/.venv/Scripts/python.exe .claude/skills/media-tools/scripts/create_image.py \
  --prompt "Same character, now wearing a red trench coat, neon Tokyo street at night" \
  --reference-image ./character.png \
  --aspect-ratio 9:16

.claude/skills/.venv/Scripts/python.exe .claude/skills/media-tools/scripts/read_image.py \
  --path "C:/path/to/image.png" \
  --prompt "Describe this image in detail. What text appears?"

© therichardngai-code, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 26 other files (scripts) in .claude/skills/media-tools of therichardngai-code/gpt-image-2-pro-max.

• SKILL.md
• .env.example
• .gitignore
• README.md
• requirements.txt
• scripts/chatgpt_oauth_login.py
• scripts/create_image.py
• scripts/lib/__init__.py
• scripts/lib/chain.py
• scripts/lib/chatgpt_oauth_token.py
• scripts/lib/dotenv_loader.py
• scripts/lib/env_keys.py
• scripts/lib/filename.py
• scripts/lib/png_metadata.py
• scripts/lib/providers/__init__.py
• scripts/lib/providers/anthropic_vision.py
• scripts/lib/providers/byteplus_image.py
• scripts/lib/providers/chatgpt_oauth_image.py
• … and 9 more

Open the folder on GitHubat commit dd902b1