aliyun-qwen-generation

Name: aliyun-qwen-generation
Author: cinience

397stars34forks

How to install aliyun-qwen-generation?

cinience/alicloud-skills/aliyun-qwen-generation

$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-generation

Installs into the current project.

Summary

Use when generating or reasoning over text with Alibaba Cloud Model Studio Qwen flagship text models (qwen3-max, qwen3.5-plus, qwen3.5-flash, snapshots, and compatible open-source variants). Use when building chat, agent, tool-calling, or long-context text generation workfl

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen Text Generation
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-generation
9	python -m py_compile skills/ai/text/aliyun-qwen-generation/scripts/prepare_generation_request.py && echo "py_compile_ok" > output/aliyun-qwen-generation/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-generation/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save prompt templates, normalized request payloads, and response summaries under `output/aliyun-qwen-generation/`.
17	- Keep one reproducible request example with model name, region, and key parameters.
18
19	Use this skill for general text generation, reasoning, tool-calling, and long-context chat on Alibaba Cloud Model Studio.
20
21	## Critical model names
22
23	Prefer the current flagship families:
24	- `qwen3-max`
25	- `qwen3-max-2026-01-23`
26	- `qwen3.5-plus`
27	- `qwen3.5-plus-2026-02-15`
28	- `qwen3.5-flash`
29	- `qwen3.5-flash-2026-02-23`
30
31	Common related variants listed in the official model catalog:
32	- `qwen3.5-397b-a17b`
33	- `qwen3.5-122b-a10b`
34	- `qwen3.5-35b-a3b`
35	- `qwen3.5-27b`
36
37	## Prerequisites
38
39	- Install SDK in a virtual environment:
40
41	```bash
42	python3 -m venv .venv
43	. .venv/bin/activate
44	python -m pip install dashscope
45	```
46
47	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
48
49	## Normalized interface (text.generate)
50
51	### Request
52	- `messages` (array<object>, required): standard chat turns.
53	- `model` (string, optional): default `qwen3.5-plus`.
54	- `temperature` (number, optional)
55	- `top_p` (number, optional)
56	- `max_tokens` (int, optional)
57	- `enable_thinking` (bool, optional)
58	- `tools` (array<object>, optional)
59	- `response_format` (object, optional)
60	- `stream` (bool, optional)
61
62	### Response
63	- `text` (string): assistant output.
64	- `finish_reason` (string, optional)
65	- `usage` (object, optional)
66	- `raw` (object, optional)
67
68	## Quick start (OpenAI-compatible endpoint)
69
70	```bash
71	curl -sS https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
72	-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
73	-H "Content-Type: application/json" \
74	-d '{
75	"model": "qwen3.5-plus",
76	"messages": [
77	{"role": "system", "content": "You are a concise assistant."},
78	{"role": "user", "content": "Summarize why object storage helps media pipelines."}
79	],
80	"stream": false
81	}'
82	```
83
84	## Local helper script
85
86	```bash
87	python skills/ai/text/aliyun-qwen-generation/scripts/prepare_generation_request.py \
88	--prompt "Draft a concise architecture summary for a media ingestion pipeline." \
89	--model qwen3.5-plus
90	```
91
92	## Operational guidance
93
94	- Use snapshot IDs when reproducibility matters.
95	- Prefer `qwen3.5-flash` for lower-latency simple tasks and `qwen3-max` for harder multi-step tasks.
96	- Keep tool schemas minimal and explicit when enabling tool calls.
97	- For multimodal input, route to dedicated VL or Omni skills unless the task is primarily text-centric.
98
99	## Output location
100
101	- Default output: `output/aliyun-qwen-generation/requests/`
102	- Override base dir with `OUTPUT_DIR`.
103
104	## References
105
106	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-qwen-generation

397stars34forks

View on GitHub

How to install aliyun-qwen-generation?

cinience/alicloud-skills/aliyun-qwen-generation

$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-generation

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen Text Generation
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-generation
9	python -m py_compile skills/ai/text/aliyun-qwen-generation/scripts/prepare_generation_request.py && echo "py_compile_ok" > output/aliyun-qwen-generation/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-generation/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save prompt templates, normalized request payloads, and response summaries under `output/aliyun-qwen-generation/`.
17	- Keep one reproducible request example with model name, region, and key parameters.
18
19	Use this skill for general text generation, reasoning, tool-calling, and long-context chat on Alibaba Cloud Model Studio.
20
21	## Critical model names
22
23	Prefer the current flagship families:
24	- `qwen3-max`
25	- `qwen3-max-2026-01-23`
26	- `qwen3.5-plus`
27	- `qwen3.5-plus-2026-02-15`
28	- `qwen3.5-flash`
29	- `qwen3.5-flash-2026-02-23`
30
31	Common related variants listed in the official model catalog:
32	- `qwen3.5-397b-a17b`
33	- `qwen3.5-122b-a10b`
34	- `qwen3.5-35b-a3b`
35	- `qwen3.5-27b`
36
37	## Prerequisites
38
39	- Install SDK in a virtual environment:
40
41	```bash
42	python3 -m venv .venv
43	. .venv/bin/activate
44	python -m pip install dashscope
45	```
46
47	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
48
49	## Normalized interface (text.generate)
50
51	### Request
52	- `messages` (array<object>, required): standard chat turns.
53	- `model` (string, optional): default `qwen3.5-plus`.
54	- `temperature` (number, optional)
55	- `top_p` (number, optional)
56	- `max_tokens` (int, optional)
57	- `enable_thinking` (bool, optional)
58	- `tools` (array<object>, optional)
59	- `response_format` (object, optional)
60	- `stream` (bool, optional)
61
62	### Response
63	- `text` (string): assistant output.
64	- `finish_reason` (string, optional)
65	- `usage` (object, optional)
66	- `raw` (object, optional)
67
68	## Quick start (OpenAI-compatible endpoint)
69
70	```bash
71	curl -sS https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
72	-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
73	-H "Content-Type: application/json" \
74	-d '{
75	"model": "qwen3.5-plus",
76	"messages": [
77	{"role": "system", "content": "You are a concise assistant."},
78	{"role": "user", "content": "Summarize why object storage helps media pipelines."}
79	],
80	"stream": false
81	}'
82	```
83
84	## Local helper script
85
86	```bash
87	python skills/ai/text/aliyun-qwen-generation/scripts/prepare_generation_request.py \
88	--prompt "Draft a concise architecture summary for a media ingestion pipeline." \
89	--model qwen3.5-plus
90	```
91
92	## Operational guidance
93
94	- Use snapshot IDs when reproducibility matters.
95	- Prefer `qwen3.5-flash` for lower-latency simple tasks and `qwen3-max` for harder multi-step tasks.
96	- Keep tool schemas minimal and explicit when enabling tool calls.
97	- For multimodal input, route to dedicated VL or Omni skills unless the task is primarily text-centric.
98
99	## Output location
100
101	- Default output: `output/aliyun-qwen-generation/requests/`
102	- Override base dir with `OUTPUT_DIR`.
103
104	## References
105
106	- `references/sources.md`

People who liked this also viewed

6 picks

Type