aliyun-qwen-coder

Name: aliyun-qwen-coder
Author: cinience

55installs34forks

How to install aliyun-qwen-coder?

cinience/alicloud-skills/aliyun-qwen-coder

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

Installs into the current project.

Summary

Use when code generation, repository understanding, or coding-agent tasks need Alibaba Cloud Model Studio Qwen Coder models (qwen3-coder-next, qwen3-coder-plus and related coder variants).

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen Coder
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-coder
9	python -m py_compile skills/ai/code/aliyun-qwen-coder/scripts/prepare_code_request.py && echo "py_compile_ok" > output/aliyun-qwen-coder/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-coder/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save prompts, repository context summaries, and normalized coding request payloads under `output/aliyun-qwen-coder/`.
17	- Record the exact model, endpoint mode, and target language/framework for reproducibility.
18
19	Use Qwen Coder for coding assistants, code review drafting, repository-level reasoning, patch planning, and tool-using software agents.
20
21	## Critical model names
22
23	Use one of these exact model strings as appropriate:
24	- `qwen3-coder-next`
25	- `qwen3-coder-plus`
26	- `qwen-coder-plus`
27	- `qwen2.5-coder-32b-instruct`
28
29	## Prerequisites
30
31	- Install SDK in a virtual environment:
32
33	```bash
34	python3 -m venv .venv
35	. .venv/bin/activate
36	python -m pip install dashscope
37	```
38
39	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
40	- Prefer the OpenAI-compatible endpoint when a client does not yet expose the latest coder models in dropdown UI.
41
42	## Normalized interface (code.generate)
43
44	### Request
45	- `messages` (array<object>, required)
46	- `model` (string, optional): default `qwen3-coder-next`
47	- `repository_summary` (string, optional)
48	- `files` (array<string>, optional)
49	- `language` (string, optional)
50	- `tools` (array<object>, optional)
51	- `stream` (bool, optional)
52
53	### Response
54	- `text` (string)
55	- `patch` (string, optional)
56	- `usage` (object, optional)
57
58	## Quick start
59
60	```bash
61	python skills/ai/code/aliyun-qwen-coder/scripts/prepare_code_request.py \
62	--task "Refactor request validation into a small helper and add one unit test." \
63	--language python
64	```
65
66	## Operational guidance
67
68	- Pass only the files relevant to the requested change to reduce noise.
69	- Use `qwen3-coder-next` for current-generation coding tasks and `qwen3-coder-plus` when you need a stronger but potentially costlier coder.
70	- For repo-scale changes, include architecture notes and expected test commands.
71	- Prefer deterministic prompts and pinned model IDs for benchmarking or regression comparison.
72
73	## Output location
74
75	- Default output: `output/aliyun-qwen-coder/requests/`
76	- Override base dir with `OUTPUT_DIR`.
77
78	## References
79
80	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-qwen-coder

55installs34forks

View on GitHub

How to install aliyun-qwen-coder?

cinience/alicloud-skills/aliyun-qwen-coder

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

Installs into the current project.

Summary

Use when code generation, repository understanding, or coding-agent tasks need Alibaba Cloud Model Studio Qwen Coder models (qwen3-coder-next, qwen3-coder-plus and related coder variants).

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen Coder
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-coder
9	python -m py_compile skills/ai/code/aliyun-qwen-coder/scripts/prepare_code_request.py && echo "py_compile_ok" > output/aliyun-qwen-coder/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-coder/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save prompts, repository context summaries, and normalized coding request payloads under `output/aliyun-qwen-coder/`.
17	- Record the exact model, endpoint mode, and target language/framework for reproducibility.
18
19	Use Qwen Coder for coding assistants, code review drafting, repository-level reasoning, patch planning, and tool-using software agents.
20
21	## Critical model names
22
23	Use one of these exact model strings as appropriate:
24	- `qwen3-coder-next`
25	- `qwen3-coder-plus`
26	- `qwen-coder-plus`
27	- `qwen2.5-coder-32b-instruct`
28
29	## Prerequisites
30
31	- Install SDK in a virtual environment:
32
33	```bash
34	python3 -m venv .venv
35	. .venv/bin/activate
36	python -m pip install dashscope
37	```
38
39	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
40	- Prefer the OpenAI-compatible endpoint when a client does not yet expose the latest coder models in dropdown UI.
41
42	## Normalized interface (code.generate)
43
44	### Request
45	- `messages` (array<object>, required)
46	- `model` (string, optional): default `qwen3-coder-next`
47	- `repository_summary` (string, optional)
48	- `files` (array<string>, optional)
49	- `language` (string, optional)
50	- `tools` (array<object>, optional)
51	- `stream` (bool, optional)
52
53	### Response
54	- `text` (string)
55	- `patch` (string, optional)
56	- `usage` (object, optional)
57
58	## Quick start
59
60	```bash
61	python skills/ai/code/aliyun-qwen-coder/scripts/prepare_code_request.py \
62	--task "Refactor request validation into a small helper and add one unit test." \
63	--language python
64	```
65
66	## Operational guidance
67
68	- Pass only the files relevant to the requested change to reduce noise.
69	- Use `qwen3-coder-next` for current-generation coding tasks and `qwen3-coder-plus` when you need a stronger but potentially costlier coder.
70	- For repo-scale changes, include architecture notes and expected test commands.
71	- Prefer deterministic prompts and pinned model IDs for benchmarking or regression comparison.
72
73	## Output location
74
75	- Default output: `output/aliyun-qwen-coder/requests/`
76	- Override base dir with `OUTPUT_DIR`.
77
78	## References
79
80	- `references/sources.md`

People who liked this also viewed

6 picks

Type