parallel-web
starsforks
How to install parallel-web?
leonchaox/qinyan-academic-skills/parallel-web
$npx -y skills add LeonChaoX/qinyan-academic-skills --skill parallel-webSearch the web, extract URL content, and run deep research using the Parallel Chat API and Extract API. Use for ALL web searches, research queries, and general information gathering. Provides synthesized summaries with citations.
SKILL.md
| 1 | # Parallel Web Systems API |
| 2 | |
| 3 | ## Overview |
| 4 | |
| 5 | This skill provides access to **Parallel Web Systems** APIs for web search, deep research, and content extraction. It is the **primary tool for all web-related operations** in the scientific writer workflow. |
| 6 | |
| 7 | **Primary interface:** Parallel Chat API (OpenAI-compatible) for search and research. |
| 8 | **Secondary interface:** Extract API for URL verification and special cases only. |
| 9 | |
| 10 | **API Documentation:** https://docs.parallel.ai |
| 11 | **API Key:** https://platform.parallel.ai |
| 12 | **Environment Variable:** `PARALLEL_API_KEY` |
| 13 | |
| 14 | ## When to Use This Skill |
| 15 | |
| 16 | Use this skill for **ALL** of the following: |
| 17 | |
| 18 | - **Web Search**: Any query that requires searching the internet for information |
| 19 | - **Deep Research**: Comprehensive research reports on any topic |
| 20 | - **Market Research**: Industry analysis, competitive intelligence, market data |
| 21 | - **Current Events**: News, recent developments, announcements |
| 22 | - **Technical Information**: Documentation, specifications, product details |
| 23 | - **Statistical Data**: Market sizes, growth rates, industry figures |
| 24 | - **General Information**: Company profiles, facts, comparisons |
| 25 | |
| 26 | **Use Extract API only for:** |
| 27 | - Citation verification (confirming a specific URL's content) |
| 28 | - Special cases where you need raw content from a known URL |
| 29 | |
| 30 | **Do NOT use this skill for:** |
| 31 | - Academic-specific paper searches (use `research-lookup` which routes to Perplexity for purely academic queries) |
| 32 | - Google Scholar / PubMed database searches (use `citation-management` skill) |
| 33 | |
| 34 | --- |
| 35 | |
| 36 | ## Two Capabilities |
| 37 | |
| 38 | ### 1. Web Search (`search` command) |
| 39 | |
| 40 | Search the web via the Parallel Chat API (`base` model) and get a **synthesized summary** with cited sources. |
| 41 | |
| 42 | **Best for:** General web searches, current events, fact-finding, technical lookups, news, market data. |
| 43 | |
| 44 | ```bash |
| 45 | # Basic search |
| 46 | python scripts/parallel_web.py search "latest advances in quantum computing 2025" |
| 47 | |
| 48 | # Use core model for more complex queries |
| 49 | python scripts/parallel_web.py search "compare EV battery chemistries NMC vs LFP" --model core |
| 50 | |
| 51 | # Save results to file |
| 52 | python scripts/parallel_web.py search "renewable energy policy updates" -o results.txt |
| 53 | |
| 54 | # JSON output for programmatic use |
| 55 | python scripts/parallel_web.py search "AI regulation landscape" --json -o results.json |
| 56 | ``` |
| 57 | |
| 58 | **Key Parameters:** |
| 59 | - `objective`: Natural language description of what you want to find |
| 60 | - `--model`: Chat model to use (`base` default, or `core` for deeper research) |
| 61 | - `-o`: Output file path |
| 62 | - `--json`: Output as JSON |
| 63 | |
| 64 | **Response includes:** Synthesized summary organized by themes, with inline citations and a sources list. |
| 65 | |
| 66 | ### 2. Deep Research (`research` command) |
| 67 | |
| 68 | Run comprehensive multi-source research via the Parallel Chat API (`core` model) that produces detailed intelligence reports with citations. |
| 69 | |
| 70 | **Best for:** Market research, comprehensive analysis, competitive intelligence, technology surveys, industry reports, any research question requiring synthesis of multiple sources. |
| 71 | |
| 72 | ```bash |
| 73 | # Default deep research (core model) |
| 74 | python scripts/parallel_web.py research "comprehensive analysis of the global EV battery market" |
| 75 | |
| 76 | # Save research report to file |
| 77 | python scripts/parallel_web.py research "AI adoption in healthcare 2025" -o report.md |
| 78 | |
| 79 | # Use base model for faster, lighter research |
| 80 | python scripts/parallel_web.py research "latest funding rounds in AI startups" --model base |
| 81 | |
| 82 | # JSON output |
| 83 | python scripts/parallel_web.py research "renewable energy storage market in Europe" --json -o data.json |
| 84 | ``` |
| 85 | |
| 86 | **Key Parameters:** |
| 87 | - `query`: Research question or topic |
| 88 | - `--model`: Chat model to use (`core` default for deep research, or `base` for faster results) |
| 89 | - `-o`: Output file path |
| 90 | - `--json`: Output as JSON |
| 91 | |
| 92 | ### 3. URL Extraction (`extract` command) — Verification Only |
| 93 | |
| 94 | Extract content from specific URLs. **Use only for citation verification and special cases.** |
| 95 | |
| 96 | For general research, use `search` or `research` instead. |
| 97 | |
| 98 | ```bash |
| 99 | # Verify a citation's content |
| 100 | python scripts/parallel_web.py extract "https://example.com/article" --objective "key findings" |
| 101 | |
| 102 | # Get full page content for verification |
| 103 | python scripts/parallel_web.py extract "https://docs.example.com/api" --full-content |
| 104 | |
| 105 | # Save extraction to file |
| 106 | python scripts/parallel_web.py extract "https://paper-url.com" --objective "methodology" -o extracted.md |
| 107 | ``` |
| 108 | |
| 109 | --- |
| 110 | |
| 111 | ## Model Selection Guide |
| 112 | |
| 113 | The Chat API supports two research models. Use `base` for most searches and `core` for deep research. |
| 114 | |
| 115 | | Model | Latency | Strengths | Use When | |
| 116 | |--------|------------|----------------------------------|-- |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
