aliyun-qwen-deep-research
installsforks
How to install aliyun-qwen-deep-research?
cinience/alicloud-skills/aliyun-qwen-deep-research
$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-deep-researchUse when a task needs Alibaba Cloud Model Studio Qwen Deep Research models to plan multi-step investigation, run iterative web research, and produce structured reports with citations or evidence summaries.
SKILL.md
| 1 | Category: provider |
| 2 | |
| 3 | # Model Studio Qwen Deep Research |
| 4 | |
| 5 | ## Validation |
| 6 | |
| 7 | ```bash |
| 8 | mkdir -p output/aliyun-qwen-deep-research |
| 9 | 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 |
| 10 | ``` |
| 11 | |
| 12 | Pass criteria: command exits 0 and `output/aliyun-qwen-deep-research/validate.txt` is generated. |
| 13 | |
| 14 | ## Output And Evidence |
| 15 | |
| 16 | - Save research goals, confirmation answers, normalized request payloads, and final report snapshots under `output/aliyun-qwen-deep-research/`. |
| 17 | - Keep the exact model, region, and `enable_feedback` setting with each saved run. |
| 18 | |
| 19 | Use this skill when the user wants a deep, multi-stage research workflow rather than a single chat completion. |
| 20 | |
| 21 | ## Critical model names |
| 22 | |
| 23 | Use one of these exact model strings: |
| 24 | - `qwen-deep-research` |
| 25 | - `qwen-deep-research-2025-12-15` |
| 26 | |
| 27 | Selection guidance: |
| 28 | - Use `qwen-deep-research` for the current mainline model. |
| 29 | - Use `qwen-deep-research-2025-12-15` when you need the snapshot with MCP tool-calling support and stronger reproducibility. |
| 30 | |
| 31 | ## Prerequisites |
| 32 | |
| 33 | - Install SDK in a virtual environment: |
| 34 | |
| 35 | ```bash |
| 36 | python3 -m venv .venv |
| 37 | . .venv/bin/activate |
| 38 | python -m pip install dashscope |
| 39 | ``` |
| 40 | |
| 41 | - Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`. |
| 42 | - This model currently applies to the China mainland (Beijing) region and uses its own API shape rather than OpenAI-compatible mode. |
| 43 | |
| 44 | ## Normalized interface (research.run) |
| 45 | |
| 46 | ### Request |
| 47 | - `topic` (string, required) |
| 48 | - `model` (string, optional): default `qwen-deep-research` |
| 49 | - `messages` (array<object>, optional) |
| 50 | - `enable_feedback` (bool, optional): default `true` |
| 51 | - `stream` (bool, optional): must be `true` |
| 52 | - `attachments` (array<object>, optional): image URLs and related context |
| 53 | |
| 54 | ### Response |
| 55 | - `status` (string): stage status such as `thinking`, `researching`, or `finished` |
| 56 | - `text` (string, optional): streamed content chunk |
| 57 | - `report` (string, optional): final structured research report |
| 58 | - `raw` (object, optional) |
| 59 | |
| 60 | ## Quick start |
| 61 | |
| 62 | ```bash |
| 63 | python skills/ai/research/aliyun-qwen-deep-research/scripts/prepare_deep_research_request.py \ |
| 64 | --topic "Compare cloud video generation model trade-offs for marketing automation." \ |
| 65 | --disable-feedback |
| 66 | ``` |
| 67 | |
| 68 | ## Operational guidance |
| 69 | |
| 70 | - Expect streaming output only. |
| 71 | - Keep the initial topic concrete and bounded; broad topics can trigger long iterative search plans. |
| 72 | - If the model asks follow-up questions and you already know the constraints, answer them explicitly to avoid wasted rounds. |
| 73 | - Use the snapshot model when you need stable evaluation runs or MCP tool-calling support. |
| 74 | |
| 75 | ## Output location |
| 76 | |
| 77 | - Default output: `output/aliyun-qwen-deep-research/requests/` |
| 78 | - Override base dir with `OUTPUT_DIR`. |
| 79 | |
| 80 | ## References |
| 81 | |
| 82 | - `references/sources.md` |
People who liked this also viewed
6 picksType
- azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026
- just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026
- firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 2026
- firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 2026
- firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 2026
- firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 2026
