← 返回 Skills 市场

Alicloud Ai Entry Modelstudio Test

Name: Alicloud Ai Entry Modelstudio Test
Author: cinience

作者 cinience · GitHub ↗ · v1.0.3 · MIT-0

cross-platform ⚠ suspicious

1204

总下载

当前安装

版本数

在 OpenClaw 中安装

/install alicloud-ai-entry-modelstudio-test

功能描述

Run a minimal test matrix for the Model Studio skills that exist in this repo, including image/video/audio, realtime speech, omni, visual reasoning, embeddin...

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

If new capability tests are needed, create corresponding skill first (use skills/ai/misc/alicloud-ai-misc-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/alicloud-ai-entry-modelstudio-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 | alicloud-ai-image-qwen-image | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Image editing | alicloud-ai-image-qwen-image-edit | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Image-to-video (i2v) | alicloud-ai-video-wan-video | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Reference-to-video (r2v) | alicloud-ai-video-wan-r2v | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| TTS | alicloud-ai-audio-tts | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| ASR (non-realtime) | alicloud-ai-audio-asr | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Realtime ASR | alicloud-ai-audio-asr-realtime | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Realtime TTS | alicloud-ai-audio-tts-realtime | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Live speech translation | alicloud-ai-audio-livetranslate | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| CosyVoice voice clone | alicloud-ai-audio-cosyvoice-voice-clone | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| CosyVoice voice design | alicloud-ai-audio-cosyvoice-voice-design | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Voice clone | alicloud-ai-audio-tts-voice-clone | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Voice design | alicloud-ai-audio-tts-voice-design | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Omni multimodal | alicloud-ai-multimodal-qwen-omni | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Visual reasoning | alicloud-ai-multimodal-qvq | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Text embedding | alicloud-ai-search-text-embedding | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Rerank | alicloud-ai-search-rerank | \x3Cmodel-id> | ... | ... | pass/fail | ... |
| Video editing | alicloud-ai-video-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/alicloud-ai-entry-modelstudio-test
echo "validation_placeholder" > output/alicloud-ai-entry-modelstudio-test/validate.txt

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

Output And Evidence

Save artifacts, command outputs, and API response summaries under output/alicloud-ai-entry-modelstudio-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 running: (1) Expect to provide an Alibaba Cloud API key (DASHSCOPE_API_KEY) or credentials file—the registry metadata does not declare this, so add or verify it. (2) Run tests in an isolated environment (fresh venv, dedicated or limited-scope API key) so any accidental mutating calls or credentials are confined. (3) Inspect each referenced sub-skill's SKILL.md to confirm the exact API calls and whether they are read-only; some capabilities (video/editing/voice cloning) may create resources or be billable. (4) Verify the 'dashscope' PyPI package/project identity before pip install (ensure it's from the official source). (5) Avoid committing output files that include region/resource IDs, API keys, or other sensitive identifiers; sanitize or store evidence securely. (6) Consider updating the skill metadata to declare DASHSCOPE_API_KEY and the ~/.alibabacloud/credentials config path so automated reviewers and users are aware of the credential requirement.

功能分析

Type: OpenClaw Skill Name: alicloud-ai-entry-modelstudio-test Version: 1.0.3 The skill is a test runner designed to validate various Alibaba Cloud Model Studio AI capabilities (image, video, audio, etc.) by executing minimal SDK calls. It requires the official 'dashscope' library and standard Alibaba Cloud credentials. The instructions in SKILL.md are transparent and aligned with the stated purpose of testing and recording results, with no evidence of malicious intent, data exfiltration, or unauthorized execution.

能力评估

ℹ Purpose & Capability

The skill's stated purpose—run a minimal test matrix across many Model Studio sub-skills—matches the SKILL.md steps (open sub-skill SKILL.md, run one request per sub-skill). However the manifest metadata does not declare the credential/config needs that the instructions require (see environment_proportionality).

⚠ Instruction Scope

Runtime instructions tell the operator to install the 'dashscope' SDK, set DASHSCOPE_API_KEY or use ~/.alibabacloud/credentials, read many sub-skill SKILL.md files, run SDK/API calls, and save evidence including region/resource IDs/time ranges. That is expected for testing, but it also means tests may access real cloud resources, be mutating (some operations may create or modify content), and will record potentially sensitive identifiers into repository files—there is no built-in safeguard to enforce read-only testing.

ℹ Install Mechanism

This is instruction-only (no install spec). SKILL.md requires creating a venv and pip-installing 'dashscope'. That is a common pattern, but the package name is not validated in the metadata (no lockfile or vetted source). Installing arbitrary PyPI packages carries moderate risk—verify the package provenance before pip install.

⚠ Credentials

The SKILL.md explicitly requires DASHSCOPE_API_KEY (or ~/.alibabacloud/credentials) but the registry metadata lists no required env vars or config paths. This mismatch is material: the skill needs cloud credentials to function but does not declare them, which can mislead reviewers and automated gates.

✓ Persistence & Privilege

always is false and the skill is instruction-only with no install spec that persists code or modifies other skills/config. It does instruct saving test outputs under an output/ path in the repo, which is normal for test artifacts.

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 alicloud-ai-entry-modelstudio-test
安装完成后，直接呼叫该 Skill 的名称或使用 /alicloud-ai-entry-modelstudio-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

v1.0.3

batch publish from alicloud-skills on 2026-03-11

v1.0.2

batch publish from alicloud-skills on 2026-02-13

v1.0.1

Initial ClawHub publish for Alibaba Cloud skills with agents metadata.

v1.0.0

Initial ClawHub publish for Alibaba Cloud skills with agents metadata.

元数据

Slug alicloud-ai-entry-modelstudio-test

版本 1.0.3

许可证 MIT-0

累计安装 3

当前安装数 3

历史版本数 4

常见问题