Use Ark (火山引擎豆包) for text-to-image (文生图) via an OpenAI-compatible API. Suitable for short captions and long, structured creative or poster-style briefs in agent workflows.
v1.0.5Use Ark (火山引擎豆包) for text-to-image (文生图) via an OpenAI-compatible API. Suitable for short captions and long, structured creative or poster-style briefs in ag...
⭐ 0· 18·0 current·0 all-time
by@hidebug
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, required env vars (ARK_API_KEY, ARK_IMAGE_MODEL), and the code all align: the script posts prompt+model+size to Ark's images/generations API. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to write the user's prompt to a fixed path (wdatas/xqx-img-prompt.txt in the OpenClaw workspace) and then run the included script with the workspace as cwd. The script only reads that file and environment variables; it does not access other files or external endpoints beyond the declared Ark API URL. Note: prompts and the printed output are written to stdout and to that fixed file, so user-provided content will be persisted in the workspace file.
Install Mechanism
No install spec; instruction-only plus a small Python script. No external downloads or package installs are required. requirements.txt is empty and the script relies only on the Python standard library.
Credentials
Only two env vars are required (ARK_API_KEY as primary, ARK_IMAGE_MODEL). Both are necessary and proportional for calling Ark's image generation endpoint; no unrelated secrets or config paths are requested.
Persistence & Privilege
always is false and the skill does not request permanent platform presence or modify other skills. It does require the agent to write a prompt file in the workspace (intended behavior for long prompts) but does not modify global agent settings.
Assessment
This skill appears to do what it says: send a prompt to Ark and return an image URL. Before installing, consider: 1) Keep ARK_API_KEY secret—inject it via your OS/CI/secret manager rather than putting it in shared TOOLS.md or a repo. 2) The agent will write the user prompt to workspace/wdatas/xqx-img-prompt.txt and print the prompt to stdout; avoid sending sensitive data in prompts or using a shared workspace. 3) Confirm the Ark API endpoint and ARK_IMAGE_MODEL you plan to use. 4) The script may error in unusual terminal environments (it assumes sys.stdout.encoding is non-null), so test with non-sensitive prompts first. If you need stronger guarantees (no disk writes or logging of prompts), request a variant that streams prompts directly to the API and avoids writing the prompt file and printing the full prompt.Like a lobster shell, security has layers — review code before you run it.
latestvk97cq9d40wyvr1xpp915g2vzs184fvhc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
EnvARK_API_KEY, ARK_IMAGE_MODEL
Primary envARK_API_KEY