← Back to Skills Marketplace
261
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install tensorslab-image
Description
Generate and edit images using TensorsLab's AI models. Supports text-to-image, image-to-image generation, plus advanced editing: avatar generation, watermark...
Usage Guidance
Before installing: 1) Expect this skill to upload any local images you pass (including multiple --source files) and the textual prompts to an external API — do not supply sensitive images (IDs, passports, private photos) unless you trust the service. 2) The skill requires TENSORSLAB_API_KEY (SKILL.md and script) but the registry metadata does not declare it — confirm where/how you obtain and store that key. 3) The script forces requests.Session proxies to empty strings (bypasses proxy for that session); if you are on a monitored/corporate network, confirm this behavior is acceptable. 4) Verify the API hostname in your environment (the SKILL.md references several similar domains while the script uses https://api.tensorslab.com) to avoid misconfigured endpoints. 5) If you need stronger assurance, review the full script locally, run it in an isolated environment, and test with non-sensitive images and a throwaway API key first.
Capability Analysis
Type: OpenClaw Skill
Name: tensorslab-image
Version: 1.0.1
The skill bundle provides a legitimate interface for interacting with the TensorsLab image generation and editing API. The Python script (scripts/tensorslab_image.py) is well-structured, focusing on API communication, task polling, and image downloading to a local directory. The documentation (SKILL.md and references/) provides clear instructions for the AI agent to perform image-related tasks without any evidence of malicious intent, data exfiltration, or unauthorized command execution.
Capability Assessment
Purpose & Capability
The code and SKILL.md match the described purpose (text→image, image→image, avatar, watermark removal, face replacement). However the registry metadata claims no required environment variables while both SKILL.md and the script require TENSORSLAB_API_KEY — an inconsistency that should be resolved before trusting the skill.
Instruction Scope
Runtime instructions and the Python script stay within the stated image-generation/editing scope: they read local image paths when provided, enhance prompts, call a remote API, poll for status, and save outputs to ./tensorslab_output. Note: the skill explicitly instructs uploading local files (including multiple --source images) to the external service, and supports sensitive operations such as watermark removal and face replacement — behaviour that is consistent with the description but can have privacy/ethical/legal implications.
Install Mechanism
No install spec; this is instruction + bundled script only. No external downloads or package installs are performed by an installer. The included script requires the 'requests' Python package; failure to have it exits with an error message.
Credentials
Only one credential is actually needed: TENSORSLAB_API_KEY, which is reasonable for an external API client. But registry metadata omits that requirement while SKILL.md and the script require it — a metadata mismatch. Also the script attempts to disable proxies for its session (session.proxies set to empty strings), which may be disproportionate in managed environments and could bypass corporate monitoring or routing.
Persistence & Privilege
The skill does not request global/always privileges, does not modify other skills, and writes only to a local output directory (./tensorslab_output) by default.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tensorslab-image - After installation, invoke the skill by name or use
/tensorslab-image - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Improved API key check instructions with a privacy-friendly command that reports presence instead of showing the key value.
- No other user-facing changes or feature updates in this version.
v1.0.0
TensorLab Skills are AI task definitions for Claude Code, focusing on multimedia generation and processing using TensorsLab's AI models. It provides comprehensive capabilities including text-to-image and image-to-image generation, advanced image editing (avatar generation, watermark removal, object erasure, face replacement), as well as text-to-video and image-to-video generation.
Metadata
Frequently Asked Questions
What is TensorLab Image?
Generate and edit images using TensorsLab's AI models. Supports text-to-image, image-to-image generation, plus advanced editing: avatar generation, watermark... It is an AI Agent Skill for Claude Code / OpenClaw, with 261 downloads so far.
How do I install TensorLab Image?
Run "/install tensorslab-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TensorLab Image free?
Yes, TensorLab Image is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TensorLab Image support?
TensorLab Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TensorLab Image?
It is built and maintained by bob (@bob5-tensorslab); the current version is v1.0.1.
More Skills