← Back to Skills Marketplace
cuixiaoyang123

qwencloud-text

by Cuixiaoyang123 · GitHub ↗ · v0.1.1 · MIT-0
cross-platform ⚠ suspicious
127
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install qwencloud-text
Description
[QwenCloud] Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate t...
Usage Guidance
This is code for a Qwen/OpenAI-compatible chat client and is plausibly legitimate — but there are important mismatches and behaviors to review before installing: (1) the metadata does not list required env vars but the code needs DASHSCOPE_API_KEY (and may use QWEN_BASE_URL/QWEN_REGION). Do not provide your API key until you confirm how it will be stored/used. (2) The scripts automatically load .env files from the current directory and repository root into the process environment; inspect those .env files first (or run the skill in a sandbox) to avoid exposing unrelated secrets. (3) The skill may execute local scripts (update-check logic uses subprocess.run on repo files); only run it in repositories you trust. (4) Ask the publisher to update the registry metadata to explicitly list required env variables and to document any automatic repo-file modification behaviors. If you lack confidence, run the scripts manually in a controlled environment and audit the code (look at require_api_key, load_dotenv, run_update_signal) before granting it access to your real API keys or allowing automatic file changes.
Capability Analysis
Type: OpenClaw Skill Name: qwencloud-text Version: 0.1.1 The qwencloud-text skill bundle is a well-structured tool for interacting with Qwen AI models via OpenAI-compatible APIs. It includes robust features such as streaming, function calling, and file uploads to Alibaba Cloud OSS (via qwencloud_lib.py). The bundle contains a self-update mechanism (gossamer.py) that detects missing dependencies and instructs the agent to prompt the user for installation of a companion update-check skill. While it includes telemetry (sending skill and agent names in headers) and proactive update prompts, these behaviors are transparently documented in SKILL.md and require user interaction, aligning with the stated purpose of providing a managed AI service integration.
Capability Tags
cryptocan-make-purchasesrequires-sensitive-credentials
Capability Assessment
Purpose & Capability
The skill's name/description match the included code and docs (a Qwen/OpenAI-compatible chat client). However the registry metadata declares no required environment variables or primary credential while the SKILL.md and bundled code clearly expect and use DASHSCOPE_API_KEY (and aliases QWEN_API_KEY) plus optional QWEN_BASE_URL/QWEN_REGION. Omitting required env declarations is an coherence problem: a Qwen client legitimately needs an API key, so the metadata should list it.
Instruction Scope
SKILL.md and the scripts instruct the agent to load .env files, locate repository roots, examine and (with user confirmation) append to agent config files, and rely on local fallback code. The code also calls a run_update_signal helper which attempts to execute other repo scripts (via subprocess). Reading .env and repo files and running local scripts is beyond a simple 'generate text' scope and increases the surface for accidental exposure of secrets or execution of untrusted local code.
Install Mechanism
No install spec is provided (instruction-only with bundled scripts). That is low-risk from an install download perspective — nothing is fetched from external URLs at install time.
Credentials
The skill requests no env vars in its metadata but the implementation uses/relies on DASHSCOPE_API_KEY (primary API key), QWEN_API_KEY alias, and optional QWEN_BASE_URL/QWEN_REGION. The scripts load .env files into os.environ (repo and current dir) which may expose any secrets stored there to the agent process. Requiring an API key is expected, but failing to declare it in metadata and auto-loading .env is disproportionate without explicit user consent and clear listing of required credentials.
Persistence & Privilege
always:false and normal model invocation make the skill user-invocable and not force-installed. The skill offers guidance to append entries to agent project config files (CLAUDE.md/AGENTS.md) but states 'ask the user before modifying any file.' The run_update_signal behavior can execute local repository scripts to check for updates, which gives the skill the ability to run local code when the script is executed — acceptable for a CLI tool but worth user awareness.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install qwencloud-text
  3. After installation, invoke the skill by name or use /qwencloud-text
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
- Updated model list: added `qwen3.6-plus` as the new recommended default model. - Detailed `qwen3.6-plus`: latest flagship model with multimodal (text+image+video) support, thinking mode by default, and 1M context. - Marked `qwen3.5-plus` as previous default; clarified model features and defaults in the table. - Added direct model detail URL guidance for every model listed. - No code or script changes; documentation and selection logic only.
v0.1.0
- Initial release of qwencloud-text skill. - Enables text generation, conversation, code writing, and tool invocation using Qwen models via an OpenAI-compatible API. - Provides detailed guidance on security, key setup, and model selection, including compatibility checks for Coding Plan keys. - Includes instructions for execution with Python 3.9+ (no extra dependencies) and environment setup. - Lists supported Qwen models for text, code, translation, and role-playing tasks. - Emphasizes never outputting API keys, with clear steps for obtaining and configuring credentials.
Metadata
Slug qwencloud-text
Version 0.1.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is qwencloud-text?

[QwenCloud] Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate t... It is an AI Agent Skill for Claude Code / OpenClaw, with 127 downloads so far.

How do I install qwencloud-text?

Run "/install qwencloud-text" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is qwencloud-text free?

Yes, qwencloud-text is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does qwencloud-text support?

qwencloud-text is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created qwencloud-text?

It is built and maintained by Cuixiaoyang123 (@cuixiaoyang123); the current version is v0.1.1.

💬 Comments