Aliyun Qwen Deep Research

Use when a task needs Alibaba Cloud Model Studio Qwen Deep Research models to plan multi-step investigation, run iterative web research, and produce structur...

Security Scan

The skill appears to implement what it claims (prepare and run Qwen Deep Research requests), but the SKILL.md expects an Alibaba/DASHSCOPE API key and instructs installing a third‑party pip package while the registry metadata declares no required credentials — this mismatch and the external install are worth caution.

Purpose & Capability

The skill's name, description, script, and docs all align with running Alibaba Cloud Qwen Deep Research workflows. However, the registry metadata lists no required environment variables or primary credential while the SKILL.md explicitly requires DASHSCOPE_API_KEY (or adding dashscope_api_key to ~/.alibabacloud/credentials) — an omission in the declared requirements.

Instruction Scope

The SKILL.md and included script are narrowly scoped: they prepare a JSON request payload, save outputs under the skill's output directory, and document expected model strings and streaming behavior. There are no instructions to read unrelated system files, exfiltrate data, or contact endpoints outside of the expected Alibaba SDK usage. The only notable runtime actions are installing/using the dashscope SDK and requiring an API key.

Install Mechanism

There is no formal install spec in the registry (skill is instruction-only). The README instructs creating a venv and running pip install dashscope. Installing a package from PyPI (or another pip source) is a moderate-risk operation because it pulls remote code — confirm the dashscope package's provenance and trustworthiness before running.

Credentials

The skill needs an Alibaba/DASHSCOPE API key (DASHSCOPE_API_KEY or dashscope_api_key in ~/.alibabacloud/credentials) according to SKILL.md, but the published metadata lists no required env vars or primary credential. This mismatch is concerning: a credential is necessary for the skill to do its work, but it was not declared. Ensure you only provide a least-privilege API key and understand where credentials will be read/stored.

Persistence & Privilege

The skill does not request persistent, always-on privileges (always:false) and does not attempt to modify other skills or system-wide agent settings. It writes outputs under its own output directory, which is expected behavior.

What to consider before installing

Before installing or running this skill: - Be aware the SKILL.md requires an Alibaba/DASHSCOPE API key, but the registry metadata did not declare any required credentials — treat that as an omission and do not supply broad credentials blindly. - Review and verify the dashscope Python package (source, maintainers, download URL) before pip installing; if possible, install it in an isolated virtualenv and inspect its code or use a vetted mirror. - Provide a least-privilege API key (scoped to only the model access needed), and prefer adding it to a dedicated credentials file rather than exposing it system-wide. - Test the skill in a sandboxed environment first and inspect the generated request.json in output/aliyun-qwen-deep-research/requests/ to confirm it contains only expected data. - If you need higher assurance, ask the publisher for the authoritative homepage/source, or request that required env vars be declared in the registry metadata so the credential requirement is explicit.

Category: provider

Model Studio Qwen Deep Research

Validation

mkdir -p output/aliyun-qwen-deep-research
python -m py_compile skills/ai/research/aliyun-qwen-deep-research/scripts/prepare_deep_research_request.py && echo "py_compile_ok" > output/aliyun-qwen-deep-research/validate.txt

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

Output And Evidence

• Save research goals, confirmation answers, normalized request payloads, and final report snapshots under output/aliyun-qwen-deep-research/.
• Keep the exact model, region, and enable_feedback setting with each saved run.

Use this skill when the user wants a deep, multi-stage research workflow rather than a single chat completion.

Critical model names

Use one of these exact model strings:

• qwen-deep-research
• qwen-deep-research-2025-12-15

Selection guidance:

• Use qwen-deep-research for the current mainline model.
• Use qwen-deep-research-2025-12-15 when you need the snapshot with MCP tool-calling support and stronger reproducibility.

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.
• This model currently applies to the China mainland (Beijing) region and uses its own API shape rather than OpenAI-compatible mode.

Normalized interface (research.run)

Request

• topic (string, required)
• model (string, optional): default qwen-deep-research
• messages (array<object>, optional)
• enable_feedback (bool, optional): default true
• stream (bool, optional): must be true
• attachments (array<object>, optional): image URLs and related context

Response

• status (string): stage status such as thinking, researching, or finished
• text (string, optional): streamed content chunk
• report (string, optional): final structured research report
• raw (object, optional)

Quick start

python skills/ai/research/aliyun-qwen-deep-research/scripts/prepare_deep_research_request.py \
  --topic "Compare cloud video generation model trade-offs for marketing automation." \
  --disable-feedback

Operational guidance

• Expect streaming output only.
• Keep the initial topic concrete and bounded; broad topics can trigger long iterative search plans.
• If the model asks follow-up questions and you already know the constraints, answer them explicitly to avoid wasted rounds.
• Use the snapshot model when you need stable evaluation runs or MCP tool-calling support.

Output location

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

References

• references/sources.md