← Back to Skills Marketplace
266
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install tencentcloud-aiart-texttoimage
Description
Skill for Tencent Cloud HunYuan Text-to-Image Generation (混元生图). Provides AI image generation from text prompts using the HunYuan large model. Supports refer...
Usage Guidance
This package implements Tencent Cloud's HunYuan text-to-image API and will work only if you supply TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY in your environment. The registry record incorrectly lists no required env vars — confirm you are comfortable providing those credentials. Note the scripts will auto-install the Tencent Cloud Python SDK (pip) at runtime and will run network calls to aiart.tencentcloudapi.com; SKILL.md also instructs the agent to execute scripts without asking you first. If you plan to install/use this skill: (1) only provide credentials with the minimum permissions needed and monitor their use; (2) prefer running the scripts manually first to inspect behavior and logs; (3) consider running in an isolated environment if you want to avoid automatic pip installs or network access. If you need more assurance, ask the publisher to update registry metadata to declare required env vars and to document dependency installation more transparently.
Capability Analysis
Type: OpenClaw Skill
Name: tencentcloud-aiart-texttoimage
Version: 1.0.0
The skill bundle provides a legitimate interface for Tencent Cloud's HunYuan Text-to-Image API. The core scripts (main.py, submit_job.py, query_job.py) use the official tencentcloud-sdk-python to interact with verified Tencent Cloud endpoints (aiart.tencentcloudapi.com). While the scripts include a routine to automatically install the required SDK via subprocess/pip, this behavior is explicitly documented in SKILL.md and serves a functional purpose. There is no evidence of data exfiltration, credential theft, or malicious prompt injection; the instructions to the agent are focused on correctly handling image generation tasks and enforcing API constraints.
Capability Assessment
Purpose & Capability
The name, description, SKILL.md and included scripts all align: they submit and poll Tencent Cloud Aiart (HunYuan) async jobs. The capabilities requested by the code (calling aiart.tencentcloudapi.com) are appropriate for the stated purpose. However, the registry metadata lists no required environment variables while both SKILL.md and all scripts clearly require TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY (and optionally TENCENTCLOUD_TOKEN). This metadata mismatch is inconsistent and worth flagging.
Instruction Scope
SKILL.md instructs the agent to run the included Python scripts automatically (zero-interaction) and explicitly states the agent must execute without asking the user for confirmation. The scripts read credentials from environment variables and perform network calls to Tencent Cloud. The instructions also mandate not asking the user before executing, which increases risk if the agent is invoked autonomously.
Install Mechanism
There is no install spec in the registry, but each script auto-installs the Python SDK by running pip install (subprocess.check_call). Auto-installing via pip is common but causes network activity (PyPI) and writes packages to the environment at runtime. No arbitrary URL downloads or obfuscated installers were found.
Credentials
The only secrets the code uses are Tencent Cloud API credentials (TENCENTCLOUD_SECRET_ID, TENCENTCLOUD_SECRET_KEY, optional TENCENTCLOUD_TOKEN), which are proportional to the stated purpose. The inconsistency is that the registry metadata declared no required env vars while the skill actually requires those credentials; that mismatch could lead to unexpected failures or surprise prompts.
Persistence & Privilege
The skill does not request permanent/always inclusion (always:false), does not modify other skills or system-wide configs, and does not persist credentials itself. The primary privilege concern is the SKILL.md's insistence on zero-interaction execution combined with autonomous invocation being allowed by default — this increases potential impact but is not by itself a malicious indicator.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tencentcloud-aiart-texttoimage - After installation, invoke the skill by name or use
/tencentcloud-aiart-texttoimage - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of TencentCloud Aiart TextToImage skill:
- Provides text-to-image generation using Tencent Cloud HunYuan model, supporting prompt rewriting, reference images, resolution control, and reproducible results via seed.
- Includes three main scripts: one-step generation (main.py), submit-only (submit_job.py), and query-by-jobid (query_job.py).
- Automatically handles dependency installation and credential detection.
- Supports up to 3 reference images, custom resolutions (within 1024×1024 area), and prompt optimization.
- Requires Tencent Cloud API credentials set via environment variables.
- Agents must always invoke scripts for image generation—never fabricate results or image URLs.
Metadata
Frequently Asked Questions
What is TencentCloud Aiart TextToImage?
Skill for Tencent Cloud HunYuan Text-to-Image Generation (混元生图). Provides AI image generation from text prompts using the HunYuan large model. Supports refer... It is an AI Agent Skill for Claude Code / OpenClaw, with 266 downloads so far.
How do I install TencentCloud Aiart TextToImage?
Run "/install tencentcloud-aiart-texttoimage" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TencentCloud Aiart TextToImage free?
Yes, TencentCloud Aiart TextToImage is completely free (open-source). You can download, install and use it at no cost.
Which platforms does TencentCloud Aiart TextToImage support?
TencentCloud Aiart TextToImage is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TencentCloud Aiart TextToImage?
It is built and maintained by 败毒 (@neck-cn); the current version is v1.0.0.
More Skills