aliyun-modelstudio-entry

Name: aliyun-modelstudio-entry
Author: cinience

50installs34forks

How to install aliyun-modelstudio-entry?

cinience/alicloud-skills/aliyun-modelstudio-entry

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

Installs into the current project.

Summary

Use when routing Alibaba Cloud Model Studio requests to the right local skill (Qwen text, coder, deep research, image, video, audio, search and multimodal skills). Use when the user asks for Model Studio without specifying a capability.

Files · 1

View on GitHub

SKILL.md

1	Category: task
2
3	# Alibaba Cloud Model Studio Entry (Routing)
4
5	Route requests to existing local skills to avoid duplicating model/parameter details.
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	## Routing Table (currently supported in this repo)
19
20	\| Need \| Target skill \|
21	\| --- \| --- \|
22	\| Text generation / reasoning / tool-calling \| `skills/ai/text/aliyun-qwen-generation/` \|
23	\| Coding / repository reasoning \| `skills/ai/code/aliyun-qwen-coder/` \|
24	\| Deep multi-step research \| `skills/ai/research/aliyun-qwen-deep-research/` \|
25	\| Text-to-image / image generation \| `skills/ai/image/aliyun-qwen-image/` \|
26	\| Image editing \| `skills/ai/image/aliyun-qwen-image-edit/` \|
27	\| Text-to-video / image-to-video (t2v/i2v) \| `skills/ai/video/aliyun-wan-video/` \|
28	\| Non-Wan PixVerse video generation \| `skills/ai/video/aliyun-pixverse-generation/` \|
29	\| Reference-to-video (r2v) \| `skills/ai/video/aliyun-wan-r2v/` \|
30	\| Digital human talking / singing avatar \| `skills/ai/video/aliyun-wan-digital-human/` \|
31	\| Expressive portrait video (EMO) \| `skills/ai/video/aliyun-emo/` \|
32	\| Lightweight portrait animation (LivePortrait) \| `skills/ai/video/aliyun-liveportrait/` \|
33	\| Motion transfer / dancing avatar (AnimateAnyone) \| `skills/ai/video/aliyun-animate-anyone/` \|
34	\| Emoji / meme portrait video \| `skills/ai/video/aliyun-emoji/` \|
35	\| Text-to-speech (TTS) \| `skills/ai/audio/aliyun-qwen-tts/` \|
36	\| Speech recognition/transcription (ASR) \| `skills/ai/audio/aliyun-qwen-asr/` \|
37	\| Realtime speech recognition \| `skills/ai/audio/aliyun-qwen-asr-realtime/` \|
38	\| Realtime TTS \| `skills/ai/audio/aliyun-qwen-tts-realtime/` \|
39	\| Live speech translation \| `skills/ai/audio/aliyun-qwen-livetranslate/` \|
40	\| CosyVoice voice clone \| `skills/ai/audio/aliyun-cosyvoice-voice-clone/` \|
41	\| CosyVoice voice design \| `skills/ai/audio/aliyun-cosyvoice-voice-design/` \|
42	\| Voice clone \| `skills/ai/audio/aliyun-qwen-tts-voice-clone/` \|
43	\| Voice design \| `skills/ai/audio/aliyun-qwen-tts-voice-design/` \|
44	\| Omni multimodal interaction \| `skills/ai/multimodal/aliyun-qwen-omni/` \|
45	\| Visual reasoning \| `skills/ai/multimodal/aliyun-qvq/` \|
46	\| OCR / document parsing / table parsing \| `skills/ai/multimodal/aliyun-qwen-ocr/` \|
47	\| Text embeddings \| `skills/ai/search/aliyun-qwen-text-embedding/` \|
48	\| Multimodal embeddings \| `skills/ai/search/aliyun-qwen-multimodal-embedding/` \|
49	\| Rerank \| `skills/ai/search/aliyun-qwen-rerank/` \|
50	\| Vector retrieval \| `skills/ai/search/aliyun-dashvector-search/` or `skills/ai/search/aliyun-opensearch-search/` or `skills/ai/search/aliyun-milvus-search/` \|
51	\| Document understanding \| `skills/ai/text/aliyun-docmind-extract/` \|
52	\| Video editing \| `skills/ai/video/aliyun-wan-edit/` \|
53	\| Video lip-sync replacement / retalk \| `skills/ai/video/aliyun-videoretalk/` \|
54	\| Model list crawl/update \| `skills/ai/misc/aliyun-modelstudio-crawl-and-skill/` \|
55
56	## When Not Matched
57
58	- Clarify model capability and input/output type first.
59	- If capability is missing in repo, add a new skill first.
60
61	## Common Missing Capabilities In This Repo (remaining gaps)
62
63	- image translation
64	- virtual try-on / digital human / advanced video personas
65
66	- For multimodal/ASR download failures, prefer public URLs listed above.
67	- For ASR parameter errors, use data URI in `input_audio.data`.
68	- For multimodal embedding 400, ensure `input.contents` is an array.
69
70	## Async Task Polling Template (video/long-running tasks)
71
72	When `X-DashScope-Async: enable` returns `task_id`, poll as follows:
73
74	```
75	GET https://dashscope.aliyuncs.com/api/v1/tasks/<task_id>
76	Authorization: Bearer $DASHSCOPE_API_KEY
77	```
78
79	Example result fields (success):
80
81	```
82	{
83	"output": {
84	"task_status": "SUCCEEDED",
85	"video_url": "https://..."
86	}
87	}
88	```
89
90	Notes:
91	- Recommended polling interval: 15-20 seconds, max 10 attempts.
92	- After success, download `output.video_url`.
93
94	## Clarifying questions (ask when uncertain)
95
96	1. Are you working with text, image, audio, or video?
97	2. Is this generation, editing/understanding, or retrieval?
98	3. Do you need speech (TTS/ASR/live translate) or retrieval (embedding/rerank/vector DB)?
99	4. Do you want runnable SDK scripts or just API/parameter guidance?
100
101	## References
102
103	- Model list and links:`output/alicloud-model-studio-models-summary.md`
104	- API/parameters/examples: see target sub-skill `SKILL.md` and `references/*.md`
105
106	- Official source list:`references/sources.md`
107
108	## Validation
109
110	```bash
111	mkdir -p output/aliyun-modelstudio-entry
112	echo "validation_placeholder" > output/al

People who liked this also viewed

6 picks

Type

aliyun-modelstudio-entry

50installs34forks

View on GitHub

How to install aliyun-modelstudio-entry?

cinience/alicloud-skills/aliyun-modelstudio-entry

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: task
2
3	# Alibaba Cloud Model Studio Entry (Routing)
4
5	Route requests to existing local skills to avoid duplicating model/parameter details.
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	## Routing Table (currently supported in this repo)
19
20	\| Need \| Target skill \|
21	\| --- \| --- \|
22	\| Text generation / reasoning / tool-calling \| `skills/ai/text/aliyun-qwen-generation/` \|
23	\| Coding / repository reasoning \| `skills/ai/code/aliyun-qwen-coder/` \|
24	\| Deep multi-step research \| `skills/ai/research/aliyun-qwen-deep-research/` \|
25	\| Text-to-image / image generation \| `skills/ai/image/aliyun-qwen-image/` \|
26	\| Image editing \| `skills/ai/image/aliyun-qwen-image-edit/` \|
27	\| Text-to-video / image-to-video (t2v/i2v) \| `skills/ai/video/aliyun-wan-video/` \|
28	\| Non-Wan PixVerse video generation \| `skills/ai/video/aliyun-pixverse-generation/` \|
29	\| Reference-to-video (r2v) \| `skills/ai/video/aliyun-wan-r2v/` \|
30	\| Digital human talking / singing avatar \| `skills/ai/video/aliyun-wan-digital-human/` \|
31	\| Expressive portrait video (EMO) \| `skills/ai/video/aliyun-emo/` \|
32	\| Lightweight portrait animation (LivePortrait) \| `skills/ai/video/aliyun-liveportrait/` \|
33	\| Motion transfer / dancing avatar (AnimateAnyone) \| `skills/ai/video/aliyun-animate-anyone/` \|
34	\| Emoji / meme portrait video \| `skills/ai/video/aliyun-emoji/` \|
35	\| Text-to-speech (TTS) \| `skills/ai/audio/aliyun-qwen-tts/` \|
36	\| Speech recognition/transcription (ASR) \| `skills/ai/audio/aliyun-qwen-asr/` \|
37	\| Realtime speech recognition \| `skills/ai/audio/aliyun-qwen-asr-realtime/` \|
38	\| Realtime TTS \| `skills/ai/audio/aliyun-qwen-tts-realtime/` \|
39	\| Live speech translation \| `skills/ai/audio/aliyun-qwen-livetranslate/` \|
40	\| CosyVoice voice clone \| `skills/ai/audio/aliyun-cosyvoice-voice-clone/` \|
41	\| CosyVoice voice design \| `skills/ai/audio/aliyun-cosyvoice-voice-design/` \|
42	\| Voice clone \| `skills/ai/audio/aliyun-qwen-tts-voice-clone/` \|
43	\| Voice design \| `skills/ai/audio/aliyun-qwen-tts-voice-design/` \|
44	\| Omni multimodal interaction \| `skills/ai/multimodal/aliyun-qwen-omni/` \|
45	\| Visual reasoning \| `skills/ai/multimodal/aliyun-qvq/` \|
46	\| OCR / document parsing / table parsing \| `skills/ai/multimodal/aliyun-qwen-ocr/` \|
47	\| Text embeddings \| `skills/ai/search/aliyun-qwen-text-embedding/` \|
48	\| Multimodal embeddings \| `skills/ai/search/aliyun-qwen-multimodal-embedding/` \|
49	\| Rerank \| `skills/ai/search/aliyun-qwen-rerank/` \|
50	\| Vector retrieval \| `skills/ai/search/aliyun-dashvector-search/` or `skills/ai/search/aliyun-opensearch-search/` or `skills/ai/search/aliyun-milvus-search/` \|
51	\| Document understanding \| `skills/ai/text/aliyun-docmind-extract/` \|
52	\| Video editing \| `skills/ai/video/aliyun-wan-edit/` \|
53	\| Video lip-sync replacement / retalk \| `skills/ai/video/aliyun-videoretalk/` \|
54	\| Model list crawl/update \| `skills/ai/misc/aliyun-modelstudio-crawl-and-skill/` \|
55
56	## When Not Matched
57
58	- Clarify model capability and input/output type first.
59	- If capability is missing in repo, add a new skill first.
60
61	## Common Missing Capabilities In This Repo (remaining gaps)
62
63	- image translation
64	- virtual try-on / digital human / advanced video personas
65
66	- For multimodal/ASR download failures, prefer public URLs listed above.
67	- For ASR parameter errors, use data URI in `input_audio.data`.
68	- For multimodal embedding 400, ensure `input.contents` is an array.
69
70	## Async Task Polling Template (video/long-running tasks)
71
72	When `X-DashScope-Async: enable` returns `task_id`, poll as follows:
73
74	```
75	GET https://dashscope.aliyuncs.com/api/v1/tasks/<task_id>
76	Authorization: Bearer $DASHSCOPE_API_KEY
77	```
78
79	Example result fields (success):
80
81	```
82	{
83	"output": {
84	"task_status": "SUCCEEDED",
85	"video_url": "https://..."
86	}
87	}
88	```
89
90	Notes:
91	- Recommended polling interval: 15-20 seconds, max 10 attempts.
92	- After success, download `output.video_url`.
93
94	## Clarifying questions (ask when uncertain)
95
96	1. Are you working with text, image, audio, or video?
97	2. Is this generation, editing/understanding, or retrieval?
98	3. Do you need speech (TTS/ASR/live translate) or retrieval (embedding/rerank/vector DB)?
99	4. Do you want runnable SDK scripts or just API/parameter guidance?
100
101	## References
102
103	- Model list and links:`output/alicloud-model-studio-models-summary.md`
104	- API/parameters/examples: see target sub-skill `SKILL.md` and `references/*.md`
105
106	- Official source list:`references/sources.md`
107
108	## Validation
109
110	```bash
111	mkdir -p output/aliyun-modelstudio-entry
112	echo "validation_placeholder" > output/al

People who liked this also viewed

6 picks

Type