aliyun-modelstudio-entry-test

Name: aliyun-modelstudio-entry-test
Author: cinience

48installs34forks

How to install aliyun-modelstudio-entry-test?

cinience/alicloud-skills/aliyun-modelstudio-entry-test

$npx -y skills add cinience/alicloud-skills --skill aliyun-modelstudio-entry-test

Installs into the current project.

Summary

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 reasoning, embedding, rerank, and edit variants. Use to execute one small request per skill and record results.

Files · 1

View on GitHub

SKILL.md

1	Category: task
2
3	# Model Studio Skills Minimal Test
4
5	Run minimal validation for currently available Model Studio skills in this repo and record results.
6
7	## Prerequisites
8
9	- Install SDK (virtual environment recommended to avoid PEP 668 restrictions):
10
11	```bash
12	python3 -m venv .venv
13	. .venv/bin/activate
14	python -m pip install dashscope
15	```
16	- Configure `DASHSCOPE_API_KEY` (environment variable preferred; or `dashscope_api_key` in `~/.alibabacloud/credentials`).
17
18	## Test Matrix (currently supported)
19
20	1) Text-to-image → `skills/ai/image/aliyun-qwen-image/`
21	2) Image editing → `skills/ai/image/aliyun-qwen-image-edit/`
22	3) Text-to-video / Image-to-video (i2v) → `skills/ai/video/aliyun-wan-video/`
23	4) Reference-to-video (r2v) → `skills/ai/video/aliyun-wan-r2v/`
24	5) TTS → `skills/ai/audio/aliyun-qwen-tts/`
25	6) ASR transcription (non-realtime) → `skills/ai/audio/aliyun-qwen-asr/`
26	7) Realtime ASR → `skills/ai/audio/aliyun-qwen-asr-realtime/`
27	8) Realtime TTS → `skills/ai/audio/aliyun-qwen-tts-realtime/`
28	9) Live speech translation → `skills/ai/audio/aliyun-qwen-livetranslate/`
29	10) CosyVoice voice clone → `skills/ai/audio/aliyun-cosyvoice-voice-clone/`
30	11) CosyVoice voice design → `skills/ai/audio/aliyun-cosyvoice-voice-design/`
31	12) Voice clone → `skills/ai/audio/aliyun-qwen-tts-voice-clone/`
32	13) Voice design → `skills/ai/audio/aliyun-qwen-tts-voice-design/`
33	14) Omni multimodal → `skills/ai/multimodal/aliyun-qwen-omni/`
34	15) Visual reasoning → `skills/ai/multimodal/aliyun-qvq/`
35	16) Text embedding → `skills/ai/search/aliyun-qwen-text-embedding/`
36	17) Rerank → `skills/ai/search/aliyun-qwen-rerank/`
37	18) Video editing → `skills/ai/video/aliyun-wan-edit/`
38
39	If new capability tests are needed, create corresponding skill first (use `skills/ai/misc/aliyun-modelstudio-crawl-and-skill/` to refresh model list).
40
41	## Minimal Flow Per Capability
42
43	1. Open target sub-skill directory and read `SKILL.md`.
44	2. Choose one minimal input example and recommended model.
45	3. Run SDK call or script.
46	4. Record model, request summary, response summary, duration, and status.
47
48	## Result Template
49
50	Save as `output/aliyun-modelstudio-entry-test-results.md`:
51
52	```
53	# Model Studio Skill Test Results
54
55	- Date: YYYY-MM-DD
56	- Environment: region / API_BASE / auth method
57
58	\| Capability \| Sub-skill \| Model \| Request summary \| Result summary \| Status \| Notes \|
59	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
60	\| Text-to-image \| aliyun-qwen-image \| <model-id> \| ... \| ... \| pass/fail \| ... \|
61	\| Image editing \| aliyun-qwen-image-edit \| <model-id> \| ... \| ... \| pass/fail \| ... \|
62	\| Image-to-video (i2v) \| aliyun-wan-video \| <model-id> \| ... \| ... \| pass/fail \| ... \|
63	\| Reference-to-video (r2v) \| aliyun-wan-r2v \| <model-id> \| ... \| ... \| pass/fail \| ... \|
64	\| TTS \| aliyun-qwen-tts \| <model-id> \| ... \| ... \| pass/fail \| ... \|
65	\| ASR (non-realtime) \| aliyun-qwen-asr \| <model-id> \| ... \| ... \| pass/fail \| ... \|
66	\| Realtime ASR \| aliyun-qwen-asr-realtime \| <model-id> \| ... \| ... \| pass/fail \| ... \|
67	\| Realtime TTS \| aliyun-qwen-tts-realtime \| <model-id> \| ... \| ... \| pass/fail \| ... \|
68	\| Live speech translation \| aliyun-qwen-livetranslate \| <model-id> \| ... \| ... \| pass/fail \| ... \|
69	\| CosyVoice voice clone \| aliyun-cosyvoice-voice-clone \| <model-id> \| ... \| ... \| pass/fail \| ... \|
70	\| CosyVoice voice design \| aliyun-cosyvoice-voice-design \| <model-id> \| ... \| ... \| pass/fail \| ... \|
71	\| Voice clone \| aliyun-qwen-tts-voice-clone \| <model-id> \| ... \| ... \| pass/fail \| ... \|
72	\| Voice design \| aliyun-qwen-tts-voice-design \| <model-id> \| ... \| ... \| pass/fail \| ... \|
73	\| Omni multimodal \| aliyun-qwen-omni \| <model-id> \| ... \| ... \| pass/fail \| ... \|
74	\| Visual reasoning \| aliyun-qvq \| <model-id> \| ... \| ... \| pass/fail \| ... \|
75	\| Text embedding \| aliyun-qwen-text-embedding \| <model-id> \| ... \| ... \| pass/fail \| ... \|
76	\| Rerank \| aliyun-qwen-rerank \| <model-id> \| ... \| ... \| pass/fail \| ... \|
77	\| Video editing \| aliyun-wan-edit \| <model-id> \| ... \| ... \| pass/fail \| ... \|
78	```
79
80	## Failure Handling
81
82	- If parameters are unclear, check target sub-skill `SKILL.md` or `references/*.md`.
83	- If model is unavailable, refresh model list and retry.
84	- For auth issues, verify `DASHSCOPE_API_KEY` (env var or `~/.alibabacloud/credentials`).
85	## Validation
86
87	```bash
88	mkdir -p output/aliyun-modelstudio-entry-test
89	echo "validation_placeholder" > output/aliyun-modelstudio-entry-test/validate.txt
90	```
91
92	Pass criteria: command exits 0 and `output/aliyun-modelstudio-entry-test/validate.txt` is generated.
93
94	## Output And Evidence
95
96	- Save artifacts, command outputs, and API response summaries under `output/aliyun-modelstudio-entry-test/`.
97	- Include key parameters (region/resource id/time range) in evidence files for reprod

People who liked this also viewed

6 picks

Type

aliyun-modelstudio-entry-test

48installs34forks

View on GitHub

How to install aliyun-modelstudio-entry-test?

cinience/alicloud-skills/aliyun-modelstudio-entry-test

$npx -y skills add cinience/alicloud-skills --skill aliyun-modelstudio-entry-test

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: task
2
3	# Model Studio Skills Minimal Test
4
5	Run minimal validation for currently available Model Studio skills in this repo and record results.
6
7	## Prerequisites
8
9	- Install SDK (virtual environment recommended to avoid PEP 668 restrictions):
10
11	```bash
12	python3 -m venv .venv
13	. .venv/bin/activate
14	python -m pip install dashscope
15	```
16	- Configure `DASHSCOPE_API_KEY` (environment variable preferred; or `dashscope_api_key` in `~/.alibabacloud/credentials`).
17
18	## Test Matrix (currently supported)
19
20	1) Text-to-image → `skills/ai/image/aliyun-qwen-image/`
21	2) Image editing → `skills/ai/image/aliyun-qwen-image-edit/`
22	3) Text-to-video / Image-to-video (i2v) → `skills/ai/video/aliyun-wan-video/`
23	4) Reference-to-video (r2v) → `skills/ai/video/aliyun-wan-r2v/`
24	5) TTS → `skills/ai/audio/aliyun-qwen-tts/`
25	6) ASR transcription (non-realtime) → `skills/ai/audio/aliyun-qwen-asr/`
26	7) Realtime ASR → `skills/ai/audio/aliyun-qwen-asr-realtime/`
27	8) Realtime TTS → `skills/ai/audio/aliyun-qwen-tts-realtime/`
28	9) Live speech translation → `skills/ai/audio/aliyun-qwen-livetranslate/`
29	10) CosyVoice voice clone → `skills/ai/audio/aliyun-cosyvoice-voice-clone/`
30	11) CosyVoice voice design → `skills/ai/audio/aliyun-cosyvoice-voice-design/`
31	12) Voice clone → `skills/ai/audio/aliyun-qwen-tts-voice-clone/`
32	13) Voice design → `skills/ai/audio/aliyun-qwen-tts-voice-design/`
33	14) Omni multimodal → `skills/ai/multimodal/aliyun-qwen-omni/`
34	15) Visual reasoning → `skills/ai/multimodal/aliyun-qvq/`
35	16) Text embedding → `skills/ai/search/aliyun-qwen-text-embedding/`
36	17) Rerank → `skills/ai/search/aliyun-qwen-rerank/`
37	18) Video editing → `skills/ai/video/aliyun-wan-edit/`
38
39	If new capability tests are needed, create corresponding skill first (use `skills/ai/misc/aliyun-modelstudio-crawl-and-skill/` to refresh model list).
40
41	## Minimal Flow Per Capability
42
43	1. Open target sub-skill directory and read `SKILL.md`.
44	2. Choose one minimal input example and recommended model.
45	3. Run SDK call or script.
46	4. Record model, request summary, response summary, duration, and status.
47
48	## Result Template
49
50	Save as `output/aliyun-modelstudio-entry-test-results.md`:
51
52	```
53	# Model Studio Skill Test Results
54
55	- Date: YYYY-MM-DD
56	- Environment: region / API_BASE / auth method
57
58	\| Capability \| Sub-skill \| Model \| Request summary \| Result summary \| Status \| Notes \|
59	\| --- \| --- \| --- \| --- \| --- \| --- \| --- \|
60	\| Text-to-image \| aliyun-qwen-image \| <model-id> \| ... \| ... \| pass/fail \| ... \|
61	\| Image editing \| aliyun-qwen-image-edit \| <model-id> \| ... \| ... \| pass/fail \| ... \|
62	\| Image-to-video (i2v) \| aliyun-wan-video \| <model-id> \| ... \| ... \| pass/fail \| ... \|
63	\| Reference-to-video (r2v) \| aliyun-wan-r2v \| <model-id> \| ... \| ... \| pass/fail \| ... \|
64	\| TTS \| aliyun-qwen-tts \| <model-id> \| ... \| ... \| pass/fail \| ... \|
65	\| ASR (non-realtime) \| aliyun-qwen-asr \| <model-id> \| ... \| ... \| pass/fail \| ... \|
66	\| Realtime ASR \| aliyun-qwen-asr-realtime \| <model-id> \| ... \| ... \| pass/fail \| ... \|
67	\| Realtime TTS \| aliyun-qwen-tts-realtime \| <model-id> \| ... \| ... \| pass/fail \| ... \|
68	\| Live speech translation \| aliyun-qwen-livetranslate \| <model-id> \| ... \| ... \| pass/fail \| ... \|
69	\| CosyVoice voice clone \| aliyun-cosyvoice-voice-clone \| <model-id> \| ... \| ... \| pass/fail \| ... \|
70	\| CosyVoice voice design \| aliyun-cosyvoice-voice-design \| <model-id> \| ... \| ... \| pass/fail \| ... \|
71	\| Voice clone \| aliyun-qwen-tts-voice-clone \| <model-id> \| ... \| ... \| pass/fail \| ... \|
72	\| Voice design \| aliyun-qwen-tts-voice-design \| <model-id> \| ... \| ... \| pass/fail \| ... \|
73	\| Omni multimodal \| aliyun-qwen-omni \| <model-id> \| ... \| ... \| pass/fail \| ... \|
74	\| Visual reasoning \| aliyun-qvq \| <model-id> \| ... \| ... \| pass/fail \| ... \|
75	\| Text embedding \| aliyun-qwen-text-embedding \| <model-id> \| ... \| ... \| pass/fail \| ... \|
76	\| Rerank \| aliyun-qwen-rerank \| <model-id> \| ... \| ... \| pass/fail \| ... \|
77	\| Video editing \| aliyun-wan-edit \| <model-id> \| ... \| ... \| pass/fail \| ... \|
78	```
79
80	## Failure Handling
81
82	- If parameters are unclear, check target sub-skill `SKILL.md` or `references/*.md`.
83	- If model is unavailable, refresh model list and retry.
84	- For auth issues, verify `DASHSCOPE_API_KEY` (env var or `~/.alibabacloud/credentials`).
85	## Validation
86
87	```bash
88	mkdir -p output/aliyun-modelstudio-entry-test
89	echo "validation_placeholder" > output/aliyun-modelstudio-entry-test/validate.txt
90	```
91
92	Pass criteria: command exits 0 and `output/aliyun-modelstudio-entry-test/validate.txt` is generated.
93
94	## Output And Evidence
95
96	- Save artifacts, command outputs, and API response summaries under `output/aliyun-modelstudio-entry-test/`.
97	- Include key parameters (region/resource id/time range) in evidence files for reprod

People who liked this also viewed

6 picks

Type