[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ0E6VCYKAVZCKHTR5EYX2":3,"skill-same:01M6CZ0E6VCYKAVZCKHTR5EYX2":121},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":34,"publishedAt":55,"linkOnly":56,"markdownContent":57,"markdownBody":58,"frontMatter":59,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":70,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":73,"updatedAt":74,"install":75,"resources":88},"01M6CZ0E6VCYKAVZCKHTR5EYX2","parallel-web",null,"Search 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.","eric861129\u002FSKILLS_All-in-one","eric861129","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74950944?v=4","01M6CXHDYEYRPFGGV4EFXCSYCF","ChiYu-Huang","01M6CXHE2J5CN1EBTY0FKV3ZKW",52,"MIT","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002FSKILL.md",[18,23,26,29],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"web","parallel web","parallel","write","research","deep","chat","queries","general","use","extract","edit","search","read","run","Bash","api","Citations","deep research","content","2026-11-10 10:12:30",false,"---\nname: parallel-web\ndescription: Search 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.\nallowed-tools: Read Write Edit Bash\nlicense: MIT license\ncompatibility: PARALLEL_API_KEY required\nmetadata:\n    skill-author: K-Dense Inc.\n---\n\n# Parallel Web Systems API\n\n## Overview\n\nThis 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.\n\n**Primary interface:** Parallel Chat API (OpenAI-compatible) for search and research.\n**Secondary interface:** Extract API for URL verification and special cases only.\n\n**API Documentation:** https:\u002F\u002Fdocs.parallel.ai\n**API Key:** https:\u002F\u002Fplatform.parallel.ai\n**Environment Variable:** `PARALLEL_API_KEY`\n\n## When to Use This Skill\n\nUse this skill for **ALL** of the following:\n\n- **Web Search**: Any query that requires searching the internet for information\n- **Deep Research**: Comprehensive research reports on any topic\n- **Market Research**: Industry analysis, competitive intelligence, market data\n- **Current Events**: News, recent developments, announcements\n- **Technical Information**: Documentation, specifications, product details\n- **Statistical Data**: Market sizes, growth rates, industry figures\n- **General Information**: Company profiles, facts, comparisons\n\n**Use Extract API only for:**\n- Citation verification (confirming a specific URL's content)\n- Special cases where you need raw content from a known URL\n\n**Do NOT use this skill for:**\n- Academic-specific paper searches (use `research-lookup` which routes to Perplexity for purely academic queries)\n- Google Scholar \u002F PubMed database searches (use `citation-management` skill)\n\n---\n\n## Two Capabilities\n\n### 1. Web Search (`search` command)\n\nSearch the web via the Parallel Chat API (`base` model) and get a **synthesized summary** with cited sources.\n\n**Best for:** General web searches, current events, fact-finding, technical lookups, news, market data.\n\n```bash\n# Basic search\npython scripts\u002Fparallel_web.py search \"latest advances in quantum computing 2025\"\n\n# Use core model for more complex queries\npython scripts\u002Fparallel_web.py search \"compare EV battery chemistries NMC vs LFP\" --model core\n\n# Save results to file\npython scripts\u002Fparallel_web.py search \"renewable energy policy updates\" -o results.txt\n\n# JSON output for programmatic use\npython scripts\u002Fparallel_web.py search \"AI regulation landscape\" --json -o results.json\n```\n\n**Key Parameters:**\n- `objective`: Natural language description of what you want to find\n- `--model`: Chat model to use (`base` default, or `core` for deeper research)\n- `-o`: Output file path\n- `--json`: Output as JSON\n\n**Response includes:** Synthesized summary organized by themes, with inline citations and a sources list.\n\n### 2. Deep Research (`research` command)\n\nRun comprehensive multi-source research via the Parallel Chat API (`core` model) that produces detailed intelligence reports with citations.\n\n**Best for:** Market research, comprehensive analysis, competitive intelligence, technology surveys, industry reports, any research question requiring synthesis of multiple sources.\n\n```bash\n# Default deep research (core model)\npython scripts\u002Fparallel_web.py research \"comprehensive analysis of the global EV battery market\"\n\n# Save research report to file\npython scripts\u002Fparallel_web.py research \"AI adoption in healthcare 2025\" -o report.md\n\n# Use base model for faster, lighter research\npython scripts\u002Fparallel_web.py research \"latest funding rounds in AI startups\" --model base\n\n# JSON output\npython scripts\u002Fparallel_web.py research \"renewable energy storage market in Europe\" --json -o data.json\n```\n\n**Key Parameters:**\n- `query`: Research question or topic\n- `--model`: Chat model to use (`core` default for deep research, or `base` for faster results)\n- `-o`: Output file path\n- `--json`: Output as JSON\n\n### 3. URL Extraction (`extract` command) — Verification Only\n\nExtract content from specific URLs. **Use only for citation verification and special cases.**\n\nFor general research, use `search` or `research` instead.\n\n```bash\n# Verify a citation's content\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fexample.com\u002Farticle\" --objective \"key findings\"\n\n# Get full page content for verification\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fdocs.example.com\u002Fapi\" --full-content\n\n# Save extraction to file\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fpaper-url.com\" --objective \"methodology\" -o extracted.md\n```\n\n---\n\n## Model Selection Guide\n\nThe Chat API supports two research models. Use `base` for most searches and `core` for deep research.\n\n| Model  | Latency    | Strengths                        | Use When                    |\n|--------|------------|----------------------------------|-----------------------------|\n| `base` | 15s-100s   | Standard research, factual queries | Web searches, quick lookups |\n| `core` | 60s-5min   | Complex research, multi-source synthesis | Deep research, comprehensive reports |\n\n**Recommendations:**\n- `search` command defaults to `base` — fast, good for most queries\n- `research` command defaults to `core` — thorough, good for comprehensive reports\n- Override with `--model` when you need different depth\u002Fspeed tradeoffs\n\n---\n\n## Python API Usage\n\n### Search\n\n```python\nfrom parallel_web import ParallelSearch\n\nsearcher = ParallelSearch()\nresult = searcher.search(\n    objective=\"Find latest information about transformer architectures in NLP\",\n    model=\"base\",\n)\n\nif result[\"success\"]:\n    print(result[\"response\"])  # Synthesized summary\n    for src in result[\"sources\"]:\n        print(f\"  {src['title']}: {src['url']}\")\n```\n\n### Deep Research\n\n```python\nfrom parallel_web import ParallelDeepResearch\n\nresearcher = ParallelDeepResearch()\nresult = researcher.research(\n    query=\"Comprehensive analysis of AI regulation in the EU and US\",\n    model=\"core\",\n)\n\nif result[\"success\"]:\n    print(result[\"response\"])  # Full research report\n    print(f\"Citations: {result['citation_count']}\")\n```\n\n### Extract (Verification Only)\n\n```python\nfrom parallel_web import ParallelExtract\n\nextractor = ParallelExtract()\nresult = extractor.extract(\n    urls=[\"https:\u002F\u002Fdocs.example.com\u002Fapi-reference\"],\n    objective=\"API authentication methods and rate limits\",\n)\n\nif result[\"success\"]:\n    for r in result[\"results\"]:\n        print(r[\"excerpts\"])\n```\n\n---\n\n## MANDATORY: Save All Results to Sources Folder\n\n**Every web search and deep research result MUST be saved to the project's `sources\u002F` folder.**\n\nThis ensures all research is preserved for reproducibility, auditability, and context window recovery.\n\n### Saving Rules\n\n| Operation | `-o` Flag Target | Filename Pattern |\n|-----------|-----------------|------------------|\n| Web Search | `sources\u002Fsearch_\u003Ctopic>.md` | `search_YYYYMMDD_HHMMSS_\u003Cbrief_topic>.md` |\n| Deep Research | `sources\u002Fresearch_\u003Ctopic>.md` | `research_YYYYMMDD_HHMMSS_\u003Cbrief_topic>.md` |\n| URL Extract | `sources\u002Fextract_\u003Csource>.md` | `extract_YYYYMMDD_HHMMSS_\u003Cbrief_source>.md` |\n\n### How to Save (Always Use `-o` Flag)\n\n**CRITICAL: Every call to `parallel_web.py` MUST include the `-o` flag pointing to the `sources\u002F` folder.**\n\n```bash\n# Web search — ALWAYS save to sources\u002F\npython scripts\u002Fparallel_web.py search \"latest advances in quantum computing 2025\" \\\n  -o sources\u002Fsearch_20250217_143000_quantum_computing.md\n\n# Deep research — ALWAYS save to sources\u002F\npython scripts\u002Fparallel_web.py research \"comprehensive analysis of the global EV battery market\" \\\n  -o sources\u002Fresearch_20250217_144000_ev_battery_market.md\n\n# URL extraction (verification only) — save to sources\u002F\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fexample.com\u002Farticle\" --objective \"key findings\" \\\n  -o sources\u002Fextract_20250217_143500_example_article.md\n```\n\n### Why Save Everything\n\n1. **Reproducibility**: Every claim in the final document can be traced back to its raw source material\n2. **Context Window Recovery**: If context is compacted mid-task, saved results can be re-read from `sources\u002F`\n3. **Audit Trail**: The `sources\u002F` folder provides complete transparency into how information was gathered\n4. **Reuse Across Sections**: Saved research can be referenced by multiple sections without duplicate API calls\n5. **Cost Efficiency**: Avoid redundant API calls by checking `sources\u002F` for existing results\n6. **Peer Review Support**: Reviewers can verify the research backing every claim\n\n### Logging\n\nWhen saving research results, always log:\n\n```\n[HH:MM:SS] SAVED: Search results to sources\u002Fsearch_20250217_143000_quantum_computing.md\n[HH:MM:SS] SAVED: Deep research report to sources\u002Fresearch_20250217_144000_ev_battery_market.md\n```\n\n### Before Making a New Query, Check Sources First\n\nBefore calling `parallel_web.py`, check if a relevant result already exists in `sources\u002F`:\n\n```bash\nls sources\u002F  # Check existing saved results\n```\n\n---\n\n## Integration with Scientific Writer\n\n### Routing Table\n\n| Task | Tool | Command |\n|------|------|---------|\n| Web search (any) | `parallel_web.py search` | `python scripts\u002Fparallel_web.py search \"query\" -o sources\u002Fsearch_\u003Ctopic>.md` |\n| Deep research | `parallel_web.py research` | `python scripts\u002Fparallel_web.py research \"query\" -o sources\u002Fresearch_\u003Ctopic>.md` |\n| Citation verification | `parallel_web.py extract` | `python scripts\u002Fparallel_web.py extract \"url\" -o sources\u002Fextract_\u003Csource>.md` |\n| Academic paper search | `research_lookup.py` | Routes to Perplexity sonar-pro-search |\n| DOI\u002Fmetadata lookup | `parallel_web.py extract` | Extract from DOI URLs (verification) |\n\n### When Writing Scientific Documents\n\n1. **Before writing any section**, use `search` or `research` to gather background information — **save results to `sources\u002F`**\n2. **For academic citations**, use `research-lookup` (which routes academic queries to Perplexity) — **save results to `sources\u002F`**\n3. **For citation verification** (confirming a specific URL), use `parallel_web.py extract` — **save results to `sources\u002F`**\n4. **For current market\u002Findustry data**, use `parallel_web.py research --model core` — **save results to `sources\u002F`**\n5. **Before any new query**, check `sources\u002F` for existing results to avoid duplicate API calls\n\n---\n\n## Environment Setup\n\n```bash\n# Required: Set your Parallel API key\nexport PARALLEL_API_KEY=\"your_api_key_here\"\n\n# Required Python packages\npip install openai        # For Chat API (search\u002Fresearch)\npip install parallel-web  # For Extract API (verification only)\n```\n\nGet your API key at https:\u002F\u002Fplatform.parallel.ai\n\n---\n\n## Error Handling\n\nThe script handles errors gracefully and returns structured error responses:\n\n```json\n{\n  \"success\": false,\n  \"error\": \"Error description\",\n  \"timestamp\": \"2025-02-14 12:00:00\"\n}\n```\n\n**Common issues:**\n- `PARALLEL_API_KEY not set`: Set the environment variable\n- `openai not installed`: Run `pip install openai`\n- `parallel-web not installed`: Run `pip install parallel-web` (only needed for extract)\n- `Rate limit exceeded`: Wait and retry (default: 300 req\u002Fmin for Chat API)\n\n---\n\n## Complementary Skills\n\n| Skill | Use For |\n|-------|---------|\n| `research-lookup` | Academic paper searches (routes to Perplexity for scholarly queries) |\n| `citation-management` | Google Scholar, PubMed, CrossRef database searches |\n| `literature-review` | Systematic literature reviews across academic databases |\n| `scientific-schematics` | Generate diagrams from research findings |\n","# Parallel Web Systems API\n\n## Overview\n\nThis 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.\n\n**Primary interface:** Parallel Chat API (OpenAI-compatible) for search and research.\n**Secondary interface:** Extract API for URL verification and special cases only.\n\n**API Documentation:** https:\u002F\u002Fdocs.parallel.ai\n**API Key:** https:\u002F\u002Fplatform.parallel.ai\n**Environment Variable:** `PARALLEL_API_KEY`\n\n## When to Use This Skill\n\nUse this skill for **ALL** of the following:\n\n- **Web Search**: Any query that requires searching the internet for information\n- **Deep Research**: Comprehensive research reports on any topic\n- **Market Research**: Industry analysis, competitive intelligence, market data\n- **Current Events**: News, recent developments, announcements\n- **Technical Information**: Documentation, specifications, product details\n- **Statistical Data**: Market sizes, growth rates, industry figures\n- **General Information**: Company profiles, facts, comparisons\n\n**Use Extract API only for:**\n- Citation verification (confirming a specific URL's content)\n- Special cases where you need raw content from a known URL\n\n**Do NOT use this skill for:**\n- Academic-specific paper searches (use `research-lookup` which routes to Perplexity for purely academic queries)\n- Google Scholar \u002F PubMed database searches (use `citation-management` skill)\n\n---\n\n## Two Capabilities\n\n### 1. Web Search (`search` command)\n\nSearch the web via the Parallel Chat API (`base` model) and get a **synthesized summary** with cited sources.\n\n**Best for:** General web searches, current events, fact-finding, technical lookups, news, market data.\n\n```bash\n# Basic search\npython scripts\u002Fparallel_web.py search \"latest advances in quantum computing 2025\"\n\n# Use core model for more complex queries\npython scripts\u002Fparallel_web.py search \"compare EV battery chemistries NMC vs LFP\" --model core\n\n# Save results to file\npython scripts\u002Fparallel_web.py search \"renewable energy policy updates\" -o results.txt\n\n# JSON output for programmatic use\npython scripts\u002Fparallel_web.py search \"AI regulation landscape\" --json -o results.json\n```\n\n**Key Parameters:**\n- `objective`: Natural language description of what you want to find\n- `--model`: Chat model to use (`base` default, or `core` for deeper research)\n- `-o`: Output file path\n- `--json`: Output as JSON\n\n**Response includes:** Synthesized summary organized by themes, with inline citations and a sources list.\n\n### 2. Deep Research (`research` command)\n\nRun comprehensive multi-source research via the Parallel Chat API (`core` model) that produces detailed intelligence reports with citations.\n\n**Best for:** Market research, comprehensive analysis, competitive intelligence, technology surveys, industry reports, any research question requiring synthesis of multiple sources.\n\n```bash\n# Default deep research (core model)\npython scripts\u002Fparallel_web.py research \"comprehensive analysis of the global EV battery market\"\n\n# Save research report to file\npython scripts\u002Fparallel_web.py research \"AI adoption in healthcare 2025\" -o report.md\n\n# Use base model for faster, lighter research\npython scripts\u002Fparallel_web.py research \"latest funding rounds in AI startups\" --model base\n\n# JSON output\npython scripts\u002Fparallel_web.py research \"renewable energy storage market in Europe\" --json -o data.json\n```\n\n**Key Parameters:**\n- `query`: Research question or topic\n- `--model`: Chat model to use (`core` default for deep research, or `base` for faster results)\n- `-o`: Output file path\n- `--json`: Output as JSON\n\n### 3. URL Extraction (`extract` command) — Verification Only\n\nExtract content from specific URLs. **Use only for citation verification and special cases.**\n\nFor general research, use `search` or `research` instead.\n\n```bash\n# Verify a citation's content\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fexample.com\u002Farticle\" --objective \"key findings\"\n\n# Get full page content for verification\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fdocs.example.com\u002Fapi\" --full-content\n\n# Save extraction to file\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fpaper-url.com\" --objective \"methodology\" -o extracted.md\n```\n\n---\n\n## Model Selection Guide\n\nThe Chat API supports two research models. Use `base` for most searches and `core` for deep research.\n\n| Model  | Latency    | Strengths                        | Use When                    |\n|--------|------------|----------------------------------|-----------------------------|\n| `base` | 15s-100s   | Standard research, factual queries | Web searches, quick lookups |\n| `core` | 60s-5min   | Complex research, multi-source synthesis | Deep research, comprehensive reports |\n\n**Recommendations:**\n- `search` command defaults to `base` — fast, good for most queries\n- `research` command defaults to `core` — thorough, good for comprehensive reports\n- Override with `--model` when you need different depth\u002Fspeed tradeoffs\n\n---\n\n## Python API Usage\n\n### Search\n\n```python\nfrom parallel_web import ParallelSearch\n\nsearcher = ParallelSearch()\nresult = searcher.search(\n    objective=\"Find latest information about transformer architectures in NLP\",\n    model=\"base\",\n)\n\nif result[\"success\"]:\n    print(result[\"response\"])  # Synthesized summary\n    for src in result[\"sources\"]:\n        print(f\"  {src['title']}: {src['url']}\")\n```\n\n### Deep Research\n\n```python\nfrom parallel_web import ParallelDeepResearch\n\nresearcher = ParallelDeepResearch()\nresult = researcher.research(\n    query=\"Comprehensive analysis of AI regulation in the EU and US\",\n    model=\"core\",\n)\n\nif result[\"success\"]:\n    print(result[\"response\"])  # Full research report\n    print(f\"Citations: {result['citation_count']}\")\n```\n\n### Extract (Verification Only)\n\n```python\nfrom parallel_web import ParallelExtract\n\nextractor = ParallelExtract()\nresult = extractor.extract(\n    urls=[\"https:\u002F\u002Fdocs.example.com\u002Fapi-reference\"],\n    objective=\"API authentication methods and rate limits\",\n)\n\nif result[\"success\"]:\n    for r in result[\"results\"]:\n        print(r[\"excerpts\"])\n```\n\n---\n\n## MANDATORY: Save All Results to Sources Folder\n\n**Every web search and deep research result MUST be saved to the project's `sources\u002F` folder.**\n\nThis ensures all research is preserved for reproducibility, auditability, and context window recovery.\n\n### Saving Rules\n\n| Operation | `-o` Flag Target | Filename Pattern |\n|-----------|-----------------|------------------|\n| Web Search | `sources\u002Fsearch_\u003Ctopic>.md` | `search_YYYYMMDD_HHMMSS_\u003Cbrief_topic>.md` |\n| Deep Research | `sources\u002Fresearch_\u003Ctopic>.md` | `research_YYYYMMDD_HHMMSS_\u003Cbrief_topic>.md` |\n| URL Extract | `sources\u002Fextract_\u003Csource>.md` | `extract_YYYYMMDD_HHMMSS_\u003Cbrief_source>.md` |\n\n### How to Save (Always Use `-o` Flag)\n\n**CRITICAL: Every call to `parallel_web.py` MUST include the `-o` flag pointing to the `sources\u002F` folder.**\n\n```bash\n# Web search — ALWAYS save to sources\u002F\npython scripts\u002Fparallel_web.py search \"latest advances in quantum computing 2025\" \\\n  -o sources\u002Fsearch_20250217_143000_quantum_computing.md\n\n# Deep research — ALWAYS save to sources\u002F\npython scripts\u002Fparallel_web.py research \"comprehensive analysis of the global EV battery market\" \\\n  -o sources\u002Fresearch_20250217_144000_ev_battery_market.md\n\n# URL extraction (verification only) — save to sources\u002F\npython scripts\u002Fparallel_web.py extract \"https:\u002F\u002Fexample.com\u002Farticle\" --objective \"key findings\" \\\n  -o sources\u002Fextract_20250217_143500_example_article.md\n```\n\n### Why Save Everything\n\n1. **Reproducibility**: Every claim in the final document can be traced back to its raw source material\n2. **Context Window Recovery**: If context is compacted mid-task, saved results can be re-read from `sources\u002F`\n3. **Audit Trail**: The `sources\u002F` folder provides complete transparency into how information was gathered\n4. **Reuse Across Sections**: Saved research can be referenced by multiple sections without duplicate API calls\n5. **Cost Efficiency**: Avoid redundant API calls by checking `sources\u002F` for existing results\n6. **Peer Review Support**: Reviewers can verify the research backing every claim\n\n### Logging\n\nWhen saving research results, always log:\n\n```\n[HH:MM:SS] SAVED: Search results to sources\u002Fsearch_20250217_143000_quantum_computing.md\n[HH:MM:SS] SAVED: Deep research report to sources\u002Fresearch_20250217_144000_ev_battery_market.md\n```\n\n### Before Making a New Query, Check Sources First\n\nBefore calling `parallel_web.py`, check if a relevant result already exists in `sources\u002F`:\n\n```bash\nls sources\u002F  # Check existing saved results\n```\n\n---\n\n## Integration with Scientific Writer\n\n### Routing Table\n\n| Task | Tool | Command |\n|------|------|---------|\n| Web search (any) | `parallel_web.py search` | `python scripts\u002Fparallel_web.py search \"query\" -o sources\u002Fsearch_\u003Ctopic>.md` |\n| Deep research | `parallel_web.py research` | `python scripts\u002Fparallel_web.py research \"query\" -o sources\u002Fresearch_\u003Ctopic>.md` |\n| Citation verification | `parallel_web.py extract` | `python scripts\u002Fparallel_web.py extract \"url\" -o sources\u002Fextract_\u003Csource>.md` |\n| Academic paper search | `research_lookup.py` | Routes to Perplexity sonar-pro-search |\n| DOI\u002Fmetadata lookup | `parallel_web.py extract` | Extract from DOI URLs (verification) |\n\n### When Writing Scientific Documents\n\n1. **Before writing any section**, use `search` or `research` to gather background information — **save results to `sources\u002F`**\n2. **For academic citations**, use `research-lookup` (which routes academic queries to Perplexity) — **save results to `sources\u002F`**\n3. **For citation verification** (confirming a specific URL), use `parallel_web.py extract` — **save results to `sources\u002F`**\n4. **For current market\u002Findustry data**, use `parallel_web.py research --model core` — **save results to `sources\u002F`**\n5. **Before any new query**, check `sources\u002F` for existing results to avoid duplicate API calls\n\n---\n\n## Environment Setup\n\n```bash\n# Required: Set your Parallel API key\nexport PARALLEL_API_KEY=\"your_api_key_here\"\n\n# Required Python packages\npip install openai        # For Chat API (search\u002Fresearch)\npip install parallel-web  # For Extract API (verification only)\n```\n\nGet your API key at https:\u002F\u002Fplatform.parallel.ai\n\n---\n\n## Error Handling\n\nThe script handles errors gracefully and returns structured error responses:\n\n```json\n{\n  \"success\": false,\n  \"error\": \"Error description\",\n  \"timestamp\": \"2025-02-14 12:00:00\"\n}\n```\n\n**Common issues:**\n- `PARALLEL_API_KEY not set`: Set the environment variable\n- `openai not installed`: Run `pip install openai`\n- `parallel-web not installed`: Run `pip install parallel-web` (only needed for extract)\n- `Rate limit exceeded`: Wait and retry (default: 300 req\u002Fmin for Chat API)\n\n---\n\n## Complementary Skills\n\n| Skill | Use For |\n|-------|---------|\n| `research-lookup` | Academic paper searches (routes to Perplexity for scholarly queries) |\n| `citation-management` | Google Scholar, PubMed, CrossRef database searches |\n| `literature-review` | Systematic literature reviews across academic databases |\n| `scientific-schematics` | Generate diagrams from research findings |\n",{"name":5,"license":60,"metadata":61,"description":7,"allowed-tools":63,"compatibility":64},"MIT license",{"skill-author":62},"K-Dense Inc.","Read Write Edit Bash","PARALLEL_API_KEY required","main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FWriting & Research\u002Fparallel-web",13,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one","http:\u002F\u002Fhuangchiyu.com\u002FSKILLS_All-in-one\u002F","https:\u002F\u002Fgithub.com\u002Feric861129","https:\u002F\u002Fhuangchiyu.com\u002FChiYu-Blog\u002F","開發工程師，專注於 C#／.NET 系統現代化、AI-assisted engineering、開源工具與技術寫作。","2026-04-16 14:28:14",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill parallel-web",{"tool":81,"command":82},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill parallel-web",{"tool":84,"command":85},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill parallel-web","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002FSKILL.md",true,[89,95,99,103,107,111,115],{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fapi_reference.md","REFERENCE","参考文档",5161,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002Freferences\u002Fapi_reference.md",{"path":96,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fdeep_research_guide.md",12898,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002Freferences\u002Fdeep_research_guide.md",{"path":100,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fextraction_patterns.md",9564,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002Freferences\u002Fextraction_patterns.md",{"path":104,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fsearch_best_practices.md",9310,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002Freferences\u002Fsearch_best_practices.md",{"path":108,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Fworkflow_recipes.md",16360,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002Freferences\u002Fworkflow_recipes.md",{"path":112,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":113,"sourceHtmlUrl":114},"resources\u002Fimplementation-playbook.md",12717,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcopilot\u002Fprotocol-reverse-engineering\u002Fresources\u002Fimplementation-playbook.md",{"path":116,"resourceType":117,"resourceTypeDesc":118,"sizeBytes":119,"sourceHtmlUrl":120},"scripts\u002Fparallel_web.py","SCRIPT","脚本",19801,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fparallel-web\u002Fscripts\u002Fparallel_web.py",[122,147,173,199,220,240],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":55},"01M6CZ1WR3KNVTKSWH4GNWT646","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fwhat-if-oracle\u002FSKILL.md",[128],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[130,131,132,49,133,134,135,136,137,138,139,140,141,48,38,142,143,144,145,146],"oracle","what if oracle","go","planning","ux","futures","risk","analysis","explore","decision","branch","question","idea","exploration","options","stress-test","strategies",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":161,"publishedAt":55},"01M6CZ1QHGJE91A95MSN5EK5Q9","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fvenue-templates\u002FSKILL.md",[153,156,157,158],{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":159,"categoryName":160,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000036","内容创作者",[162,163,39,164,165,166,167,168,50,169,48,38,46,170,171,172],"templates","venue templates","guidelines","NeurIPS","ICML","LaTeX","science","access","proposals","Academic","requirements",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":181,"publishedAt":55},"01M6CZ1KBQD2E5RTFB3BGVX7CD","the-fool","Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fthe-fool\u002FSKILL.md",[179,180],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},[182,183,132,184,185,49,186,187,188,189,190,191,192,193,170,194,195,196,197,198],"the fool","review","workflow","architecture","code","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","expert","poke","ideas",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":208,"publishedAt":55},"01M6CZ1ES826S7P1X3333E40TA","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-writing\u002FSKILL.md",[205,206,207],{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":159,"categoryName":160,"taxonomyType":32,"taxonomyTypeDesc":33},[209,210,164,211,212,53,52,213,50,214,48,38,46,44,215,216,40,217,218,219],"writing","scientific writing","core","reporting","Outlines","tool","never","structure","full","stage","prisma",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":227,"publishedAt":55},"01M6CZ1B2JGJTB9FRD0TW4RXXE","scientific-brainstorming","Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-brainstorming\u002FSKILL.md",[226],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[228,229,39,230,133,231,232,233,44,234,235,236,143,237,238,218,239],"brainstorming","scientific brainstorming","sessions","data","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"skillNo":241,"name":242,"nameZh":6,"description":243,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":244,"categories":245,"keywords":250,"publishedAt":55},"01M6CZ16JG8N7A2ZX04BGE8J2Y","research-lookup","Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fresearch-lookup\u002FSKILL.md",[246,247,248,249],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},[39,251,252,47,231,253,51,50,37,254,48,38,46,44,255,256,257,42,41,171],"lookup","research lookup","perplexity","openrouter","backend","up","look"]