skywork-search
installsforks
How to install skywork-search?
skyworkai/skywork-skills/skywork-search
$npx -y skills add SkyworkAI/Skywork-Skills --skill skywork-searchSearch the web for real-time information using the Skywork web search API. Use this skill whenever the user needs up-to-date information from the internet — for example, researching a topic, looking up recent events, finding facts or statistics, gathering material for a document
SKILL.md
| 1 | # Web Search Skill |
| 2 | |
| 3 | Search the web for real-time information via the Skywork search API. This skill lets you run up to 3 queries in a single invocation and returns structured results with source URLs and content snippets. |
| 4 | |
| 5 | ## When to use |
| 6 | |
| 7 | - The user asks you to research a topic or find current information |
| 8 | - You need up-to-date facts, statistics, or news to answer a question |
| 9 | - Another task (writing a report, creating a PPT, drafting a document) needs web research as a preliminary step |
| 10 | - The user explicitly asks to search or look something up |
| 11 | |
| 12 | ## Prerequisites |
| 13 | |
| 14 | ### API Key Configuration (Required First) |
| 15 | This skill requires a **SKYWORK_API_KEY** to be configured in OpenClaw. |
| 16 | |
| 17 | If you don't have an API key yet, please visit: |
| 18 | **https://skywork.ai** |
| 19 | |
| 20 | For detailed setup instructions, see: |
| 21 | [references/apikey-fetch.md](references/apikey-fetch.md) |
| 22 | |
| 23 | ## How to use |
| 24 | |
| 25 | Run the bundled script from this skill's `scripts/` directory: |
| 26 | |
| 27 | ```bash |
| 28 | python3 <skill-path>/scripts/web_search.py "query1" ["query2"] ["query3"] |
| 29 | ``` |
| 30 | |
| 31 | - Pass 1–3 search queries as positional arguments |
| 32 | - Results are saved to individual text files in a temporary directory |
| 33 | - The script prints the file paths to stdout so you can read them |
| 34 | |
| 35 | ## Crafting good queries |
| 36 | |
| 37 | Search quality depends heavily on query phrasing. A few tips: |
| 38 | |
| 39 | - **Be specific**: "Tesla Q4 2025 revenue" works better than "Tesla financials" |
| 40 | - **Use natural language**: The API handles full questions well — "What is the current population of Tokyo?" is fine |
| 41 | - **Split broad topics**: If the user wants a comprehensive overview, break it into 2–3 focused queries rather than one vague one |
| 42 | - **Include time context** when relevant: "best Python web frameworks 2026" rather than just "best Python web frameworks" |
| 43 | |
| 44 | ## Reading results |
| 45 | |
| 46 | After running the script, read the output files. Each file contains: |
| 47 | |
| 48 | ``` |
| 49 | query: <the original query> |
| 50 | |
| 51 | [result-1] <source URL> |
| 52 | <content snippet> |
| 53 | |
| 54 | [result-2] <source URL> |
| 55 | <content snippet> |
| 56 | ... |
| 57 | ``` |
| 58 | |
| 59 | Synthesize the results into a clear answer for the user. Always cite sources when presenting factual information — include the URLs from the results so the user can verify. |
| 60 | |
| 61 | ## Example workflow |
| 62 | |
| 63 | User asks: "What are the latest developments in quantum computing?" |
| 64 | |
| 65 | 1. Run the search with focused queries: |
| 66 | ```bash |
| 67 | python3 <skill-path>/scripts/web_search.py \ |
| 68 | "quantum computing breakthroughs 2026" \ |
| 69 | "quantum computing industry news latest" |
| 70 | ``` |
| 71 | 2. Read the result files |
| 72 | 3. Synthesize findings into a clear, sourced summary for the user |
| 73 | |
| 74 | ## Limitations |
| 75 | |
| 76 | - Maximum 3 queries per invocation (the script caps it) |
| 77 | - Each query has a 30-second timeout |
| 78 | - Results depend on the Skywork search API availability |
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
