Aliyun Qwen Coder

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

Security Scan

The skill's behavior generally matches a Qwen Coder adapter, but the runtime instructions reference credentials and installation steps that are not declared in the skill metadata and may require networked SDK calls — this mismatch warrants caution before installing.

Purpose & Capability

Name/description (Alibaba Cloud Qwen Coder adapter) align with the provided script and instructions: the included prepare_code_request.py builds code.generate request payloads and the SKILL.md documents using Qwen Coder models. The requested pip package (dashscope) and the DASHSCOPE_API_KEY mentioned in SKILL.md are consistent with a vendor SDK for Alibaba Cloud, so the capability is plausible.

Instruction Scope

SKILL.md instructs the agent to install a Python SDK, set DASHSCOPE_API_KEY (or add credentials to ~/.alibabacloud/credentials), and to write prompts/payloads under output/aliyun-qwen-coder/. The instructions reference an environment variable and a credential file path that are not declared in the registry metadata; they also imply making network calls to Alibaba endpoints (via the SDK), but the skill does not declare or document network usage in the registry. The script itself only writes JSON payloads and does not access credentials, but the overall runtime guidance expects access to secrets and remote APIs.

Install Mechanism

There is no formal install spec in the registry (instruction-only), but SKILL.md advises creating a Python venv and pip-installing 'dashscope'. Installing a third-party package via pip is expected for an SDK adapter; this is moderate risk but typical. No downloads from untrusted URLs or archive extraction are present.

Credentials

The SKILL.md requires DASHSCOPE_API_KEY or credentials under ~/.alibabacloud/credentials to call Alibaba Cloud model endpoints, but the registry metadata lists no required environment variables or primary credential. That mismatch is a red flag: the skill will need an API key in practice, yet it does not declare it as a requirement, which could lead to unexpected credential prompting or misconfiguration. The quantity of env/credential access is small and relevant to the stated purpose, but it should be declared explicitly.

Persistence & Privilege

The skill is not marked always:true, is instruction-only aside from a small helper script, does not request persistent agent-wide privileges, and does not modify other skills' configuration. Its filesystem writes are limited to an output directory under the skill's namespace.

What to consider before installing

This skill appears to be a legitimate adapter for Alibaba's Qwen Coder models, but it has a small mismatch: SKILL.md instructs you to provide DASHSCOPE_API_KEY (or ~/.alibabacloud/credentials) and install a pip package, yet the skill metadata does not declare that credential requirement. Before installing or using it: 1) Verify the source/owner (no homepage provided) and prefer an official or audited package for 'dashscope'. 2) Only provide a least-privilege API key scoped to Model Studio, not broad Alibaba Cloud credentials. 3) Run the helper in an isolated environment (venv/container) and inspect network activity or package origin (pip index, package homepage). 4) Ask the publisher to update the registry metadata to explicitly declare the required environment variable and any network endpoints. If you need higher assurance, request the upstream package source and confirm that 'dashscope' is the official SDK for the intended endpoint.

Category: provider

Model Studio Qwen Coder

Validation

mkdir -p output/aliyun-qwen-coder
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

Pass criteria: command exits 0 and output/aliyun-qwen-coder/validate.txt is generated.

Output And Evidence

• Save prompts, repository context summaries, and normalized coding request payloads under output/aliyun-qwen-coder/.
• Record the exact model, endpoint mode, and target language/framework for reproducibility.

Use Qwen Coder for coding assistants, code review drafting, repository-level reasoning, patch planning, and tool-using software agents.

Critical model names

Use one of these exact model strings as appropriate:

• qwen3-coder-next
• qwen3-coder-plus
• qwen-coder-plus
• qwen2.5-coder-32b-instruct

Prerequisites

• Install SDK in a virtual environment:

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

• Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials.
• Prefer the OpenAI-compatible endpoint when a client does not yet expose the latest coder models in dropdown UI.

Normalized interface (code.generate)

Request

• messages (array<object>, required)
• model (string, optional): default qwen3-coder-next
• repository_summary (string, optional)
• files (array<string>, optional)
• language (string, optional)
• tools (array<object>, optional)
• stream (bool, optional)

Response

• text (string)
• patch (string, optional)
• usage (object, optional)

Quick start

python skills/ai/code/aliyun-qwen-coder/scripts/prepare_code_request.py \
  --task "Refactor request validation into a small helper and add one unit test." \
  --language python

Operational guidance

• Pass only the files relevant to the requested change to reduce noise.
• Use qwen3-coder-next for current-generation coding tasks and qwen3-coder-plus when you need a stronger but potentially costlier coder.
• For repo-scale changes, include architecture notes and expected test commands.
• Prefer deterministic prompts and pinned model IDs for benchmarking or regression comparison.

Output location

• Default output: output/aliyun-qwen-coder/requests/
• Override base dir with OUTPUT_DIR.

References

• references/sources.md