← Back to Skills Marketplace
512
Downloads
1
Stars
1
Active Installs
7
Versions
Install in OpenClaw
/install seedream-image-generation
Description
Image generation via Volcengine Seedream API. Use this when you need to perform Text-to-Image (T2I), Image-to-Image (I2I), or general visual creative tasks.
Usage Guidance
This skill appears to implement a legit wrapper for Volcengine Seedream, but review and precaution are recommended before use: 1) Correct the metadata mismatch — SEEDREAM_BASE_URL is optional in code but listed as required in metadata. 2) Inspect the scripts locally (they will read any local image path you pass and upload its base64 to the remote API). Do not pass sensitive file paths. 3) Note a likely bug/partial truncation in the Python entrypoint (an undefined/truncated variable near the end) — test the script in a safe environment first. 4) Use a dedicated API key with limited scope, avoid placing a broad-seoped SEEDREAM_API_KEY in a shared environment, and rotate the key if you suspect misuse. 5) If you need higher assurance, run the scripts in an isolated/sandbox environment and confirm the base URL is the official Volcengine endpoint before sending data.
Capability Analysis
Type: OpenClaw Skill
Name: seedream-image-generation
Version: 1.0.6
The skill provides image generation via the Volcengine Seedream API but includes high-risk capabilities for arbitrary file read and write access. The scripts `seedream.py` and `seedream.js` can read any local file to convert it to base64 for API requests (intended for Image-to-Image tasks) and can write downloaded images to any local directory specified by the user or agent. While these features are aligned with the stated purpose, the lack of path sanitization or sandboxing creates a vector for data exfiltration or unauthorized file modification if the agent is misdirected. No evidence of intentional malice or hidden exfiltration was found.
Capability Assessment
Purpose & Capability
The declared requirements (SEEDREAM_API_KEY and SEEDREAM_BASE_URL) and the included Python/JS wrappers align with the stated purpose of calling Volcengine Seedream for T2I/I2I. Minor incoherence: the registry metadata and SKILL.md list SEEDREAM_BASE_URL as a required env var, but both code files treat SEEDREAM_BASE_URL as optional (they default to the Volcengine endpoint). This mismatch should be corrected.
Instruction Scope
Runtime instructions and scripts explicitly read user-supplied local image file paths, convert them to base64, and transmit them to the Seedream API; they also optionally download generated images to a local directory. That behavior is expected for I2I workflows, but it means any local file path you provide will be uploaded — a privacy/exfiltration risk if you pass sensitive files. The SKILL.md and scripts only reference the two declared env vars and the specified API endpoint.
Install Mechanism
There is no install spec or remote download; the skill is instruction-plus-local-scripts only. The code uses standard stdlib network/file APIs. No third‑party install or remote archive is fetched during install.
Credentials
The skill requests only SEEDREAM_API_KEY (primary) and SEEDREAM_BASE_URL. That is proportionate for a client of the Seedream API. Small inconsistency: registry metadata claims SEEDREAM_BASE_URL is required while code treats it as optional and uses a sensible default endpoint. JS also allows an override param 'api_key' at runtime which is acceptable but should be documented clearly.
Persistence & Privilege
The skill does not request always:true and does not attempt to modify other skills or system-wide config. It does write files only when you explicitly pass a download_dir. Autonomous invocation is enabled by default but is not combined with other red flags here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install seedream-image-generation - After installation, invoke the skill by name or use
/seedream-image-generation - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.6
- Updated environment variables: now requires SEEDREAM_API_KEY and SEEDREAM_BASE_URL (was ARK_API_KEY).
- Script files reorganized into the scripts/ directory; removed old and config files.
- Added explicit support and documentation for the size parameter, including 2K, 3K, and 4K options.
- Expanded troubleshooting section and updated guidance on environment setup.
- Usage examples updated for the new script locations and parameter behavior.
v1.0.5
- Added support for image-to-image (I2I) generation by introducing an image parameter (handles local path(s) as input).
- Updated documentation with new script parameter details and example usage for image-to-image workflows.
- Added .env file for environment variables.
v1.0.4
- Removed the requirement for the SEEDREAM_ENDPOINT_ID environment variable; only ARK_API_KEY is now required.
- No changes to usage, parameters, or core functionality.
v1.0.3
- Updated SKILL.md to reflect current supported model IDs, changing from generic names (e.g., doubao-seedream-5.0-lite) to specific deployment IDs (e.g., doubao-seedream-5-0-260128).
- Clarified that the default model is now doubao-seedream-5-0-260128.
- Added a reference link for the latest model ID list and instructions on updating supported model parameters.
- No functional changes to the skill code.
v1.0.2
- Added a sample environment file (.env.example) to help users configure required environment variables.
- No other changes to the skill functionality.
v1.0.1
- Added a new metadata section specifying required environment variables (ARK_API_KEY and SEEDREAM_ENDPOINT_ID).
- Designated ARK_API_KEY as the primary environment variable in metadata.
- No changes to skill code or functionality.
v1.0.0
Seedream Image Generation Skill 1.0.0 – Initial Release
- Provides image generation capabilities via Volcengine Seedream API (supports T2I, I2I, and creative visual tasks).
- Supports both Python and Node.js/JavaScript runtimes.
- Allows selection of model endpoint, prompt tuning, watermarking, output formatting, and advanced tool integration.
- Includes resolution/aspect-ratio recommendations and full parameter documentation.
- Usage examples provided for both Python and Node.js environments.
Metadata
Frequently Asked Questions
What is seedream(doubao)-image-generation?
Image generation via Volcengine Seedream API. Use this when you need to perform Text-to-Image (T2I), Image-to-Image (I2I), or general visual creative tasks. It is an AI Agent Skill for Claude Code / OpenClaw, with 512 downloads so far.
How do I install seedream(doubao)-image-generation?
Run "/install seedream-image-generation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is seedream(doubao)-image-generation free?
Yes, seedream(doubao)-image-generation is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does seedream(doubao)-image-generation support?
seedream(doubao)-image-generation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created seedream(doubao)-image-generation?
It is built and maintained by cp7553479 (@cp7553479); the current version is v1.0.6.
More Skills