← 返回 Skills 市场

Aliyun Modelstudio Entry Test

Name: Aliyun Modelstudio Entry Test
Author: cinience

作者 cinience · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

111

总下载

当前安装

版本数

在 OpenClaw 中安装

/install aliyun-modelstudio-entry-test

功能描述

Use when running a minimal test matrix for the Model Studio skills that exist in this repo, including image/video/audio, realtime speech, omni, visual reason...

使用说明 (SKILL.md)

Category: task

Model Studio Skills Minimal Test

Run minimal validation for currently available Model Studio skills in this repo and record results.

Prerequisites

Install SDK (virtual environment recommended to avoid PEP 668 restrictions):

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

Configure DASHSCOPE_API_KEY (environment variable preferred; or dashscope_api_key in ~/.alibabacloud/credentials).

Test Matrix (currently supported)

Text-to-image → skills/ai/image/aliyun-qwen-image/
Image editing → skills/ai/image/aliyun-qwen-image-edit/
Text-to-video / Image-to-video (i2v) → skills/ai/video/aliyun-wan-video/
Reference-to-video (r2v) → skills/ai/video/aliyun-wan-r2v/
TTS → skills/ai/audio/aliyun-qwen-tts/
ASR transcription (non-realtime) → skills/ai/audio/aliyun-qwen-asr/
Realtime ASR → skills/ai/audio/aliyun-qwen-asr-realtime/
Realtime TTS → skills/ai/audio/aliyun-qwen-tts-realtime/
Live speech translation → skills/ai/audio/aliyun-qwen-livetranslate/
CosyVoice voice clone → skills/ai/audio/aliyun-cosyvoice-voice-clone/
CosyVoice voice design → skills/ai/audio/aliyun-cosyvoice-voice-design/
Voice clone → skills/ai/audio/aliyun-qwen-tts-voice-clone/
Voice design → skills/ai/audio/aliyun-qwen-tts-voice-design/
Omni multimodal → skills/ai/multimodal/aliyun-qwen-omni/
Visual reasoning → skills/ai/multimodal/aliyun-qvq/
Text embedding → skills/ai/search/aliyun-qwen-text-embedding/
Rerank → skills/ai/search/aliyun-qwen-rerank/
Video editing → skills/ai/video/aliyun-wan-edit/

If new capability tests are needed, create corresponding skill first (use skills/ai/misc/aliyun-modelstudio-crawl-and-skill/ to refresh model list).

Minimal Flow Per Capability

Open target sub-skill directory and read SKILL.md.
Choose one minimal input example and recommended model.
Run SDK call or script.
Record model, request summary, response summary, duration, and status.

Result Template

Save as output/aliyun-modelstudio-entry-test-results.md:

# Model Studio Skill Test Results

- Date: YYYY-MM-DD
- Environment: region / API_BASE / auth method

| Capability | Sub-skill | Model | Request summary | Result summary | Status | Notes |
| --- | --- | --- | --- | --- | --- | --- |
| Text-to-image | aliyun-qwen-image | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Image editing | aliyun-qwen-image-edit | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Image-to-video (i2v) | aliyun-wan-video | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Reference-to-video (r2v) | aliyun-wan-r2v | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| TTS | aliyun-qwen-tts | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| ASR (non-realtime) | aliyun-qwen-asr | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Realtime ASR | aliyun-qwen-asr-realtime | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Realtime TTS | aliyun-qwen-tts-realtime | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Live speech translation | aliyun-qwen-livetranslate | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| CosyVoice voice clone | aliyun-cosyvoice-voice-clone | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| CosyVoice voice design | aliyun-cosyvoice-voice-design | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Voice clone | aliyun-qwen-tts-voice-clone | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Voice design | aliyun-qwen-tts-voice-design | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Omni multimodal | aliyun-qwen-omni | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Visual reasoning | aliyun-qvq | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Text embedding | aliyun-qwen-text-embedding | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Rerank | aliyun-qwen-rerank | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Video editing | aliyun-wan-edit | \x3Cmodel-id> | ... | ... | pass/fail | ... |

Failure Handling

If parameters are unclear, check target sub-skill SKILL.md or references/*.md.
If model is unavailable, refresh model list and retry.
For auth issues, verify DASHSCOPE_API_KEY (env var or ~/.alibabacloud/credentials).

Validation

mkdir -p output/aliyun-modelstudio-entry-test
echo "validation_placeholder" > output/aliyun-modelstudio-entry-test/validate.txt

Pass criteria: command exits 0 and output/aliyun-modelstudio-entry-test/validate.txt is generated.

Output And Evidence

Save artifacts, command outputs, and API response summaries under output/aliyun-modelstudio-entry-test/.
Include key parameters (region/resource id/time range) in evidence files for reproducibility.

Workflow

Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
Run one minimal read-only query first to verify connectivity and permissions.
Execute the target operation with explicit parameters and bounded scope.
Verify results and save output/evidence files.

References

Source list: references/sources.md

安全使用建议

Before installing or running this skill: 1) Treat the SKILL.md as authoritative — it requires installing a third-party Python package ('dashscope') and providing an Alibaba API key (DASHSCOPE_API_KEY or ~/.alibabacloud/credentials), but the registry metadata does not declare those env vars. 2) Use an isolated virtual environment as instructed, and consider reviewing the 'dashscope' package source or pinning a trusted release/version before pip installing. 3) Avoid putting long-lived or high-privilege credentials in the environment or in ~/.alibabacloud/credentials for testing; create a scoped test API key with minimal permissions and rotate/delete it after use. 4) Inspect each referenced sub-skill's SKILL.md (the test will open and execute those) so you understand additional auth needs or network endpoints. 5) When saving evidence/output, ensure you do not accidentally write secrets or full API responses containing sensitive data. If you want me to proceed with a deeper review, provide the contents of the referenced sub-skill SKILL.md files and/or the dashscope package origin/version.

功能分析

Type: OpenClaw Skill Name: aliyun-modelstudio-entry-test Version: 1.0.0 The skill 'aliyun-modelstudio-entry-test' (SKILL.md) functions as a test orchestrator for various Alibaba Cloud AI capabilities. It instructs the AI agent to perform high-risk actions including installing packages via shell (pip install dashscope), accessing sensitive credential files (~/.alibabacloud/credentials), and dynamically executing logic from multiple sub-skill directories. While these behaviors are aligned with the stated purpose of running a validation matrix, the broad shell and file system access requirements are classified as suspicious under the security framework due to the inherent risks of credential exposure and arbitrary execution.

能力评估

✓ Purpose & Capability

The name/description (minimal test matrix for Alibaba Model Studio skills) align with the runtime instructions: open sub-skill SKILL.md files, run one small request per capability, and save results. The required actions (SDK calls to Alibaba services) are expected for this purpose.

ℹ Instruction Scope

Instructions explicitly tell the operator/agent to read sub-skill SKILL.md files in the repo, run SDK calls, and write output/evidence under output/. They also instruct checking user intent/region and to include certain parameters in evidence files. Reading repo files and writing results is within scope; however the SKILL.md also references reading ~/.alibabacloud/credentials as an alternative auth source — that touches a user credential file outside the skill directory and should be handled carefully.

ℹ Install Mechanism

There is no install spec in registry metadata, but SKILL.md instructs creating a venv and running 'pip install dashscope'. Installing a third-party pip package at runtime is common for SDKs but carries moderate risk: the package origin/version is not pinned or proven here. Using an isolated venv is recommended (and the instructions suggest one).

⚠ Credentials

SKILL.md requires DASHSCOPE_API_KEY (or credentials stored in ~/.alibabacloud/credentials) to run, but the skill metadata lists no required env vars and no primary credential. This mismatch means the registry entry underreports credential needs. Requiring an Alibaba API key is proportionate to the stated goal, but the missing declaration is an important coherence/visibility issue.

✓ Persistence & Privilege

The skill does not request always:true and is not requesting to modify other skills or system-wide settings. It is user-invocable and allows autonomous invocation by default (platform normal). No additional persistence or elevated privileges are requested by the manifest.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install aliyun-modelstudio-entry-test
安装完成后，直接呼叫该 Skill 的名称或使用 /aliyun-modelstudio-entry-test 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of aliyun-modelstudio-entry-test. - Provides a minimal test matrix for all Model Studio skills in the repo, including image, video, audio, speech, multimodal, embedding, rerank, and editing. - Defines a standard output template for test results. - Includes prerequisites, failure handling guidance, and workflow for running validation and saving evidence.

元数据

Slug aliyun-modelstudio-entry-test

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题