Search the web using DashScope Qwen API via bash. Returns real-time information with source citations.
The search script is at scripts/web_search.py relative to this skill's directory.
python3 {{SKILL_DIR}}/scripts/web_search.py [OPTIONS] "query"
| Flag | Effect | Best For |
|---|---|---|
| ------ | -------- | ---------- |
| _(none)_ | Fast turbo search | Quick facts, weather, person lookup |
--deep | Multi-source verification (max strategy) | Research, reports, fact-checking |
--agent | Multi-round retrieval + synthesis | Complex questions needing iterative search |
--think | Deep reasoning before answering (streaming) | Analysis, comparisons, trend prediction |
--images | Image+text mixed output (uses qwen-plus-latest) | Visual references, product images, diagrams |
--fresh N | Only results from last N days (7/30/180/365) | Breaking news, recent events |
--sites "a.com,b.com" | Restrict to specific domains | Domain-specific research |
Options can be combined freely:
# Deep research with reasoning
python3 {{SKILL_DIR}}/scripts/web_search.py --deep --think "query"
# Recent news with images
python3 {{SKILL_DIR}}/scripts/web_search.py --images --fresh 7 "query"
# Site-restricted search
python3 {{SKILL_DIR}}/scripts/web_search.py --sites "github.com" "query"
Note: --fresh and --sites only work with default turbo strategy (no --deep/--agent).
--deep when turbo results are incomplete or conflicting--agent for questions that need multiple search angles (e.g., "compare X vs Y across dimensions")--think when the user needs analysis, not just raw facts--images when visual context matters (products, places, people, charts)--think mode prepends ... with reasoning chain--images mode may include !alt markdown images — render or describe them for the userIf the script fails:
curl -s https://dashscope.aliyuncs.com > /dev/null && echo OKpython3 -c "import openai; print(openai.__version__)"DASHSCOPE_API_KEY must be set in the process environment共 1 个版本