{ "schemaVersion": "1.0", "item": { "slug": "parallel-deep-research", "name": "Parallel Deep Research", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/NormallyGaussian/parallel-deep-research", "canonicalUrl": "https://clawhub.ai/NormallyGaussian/parallel-deep-research", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/parallel-deep-research", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=parallel-deep-research", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/parallel-deep-research" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/parallel-deep-research", "agentPageUrl": "https://openagent3.xyz/skills/parallel-deep-research/agent", "manifestUrl": "https://openagent3.xyz/skills/parallel-deep-research/agent.json", "briefUrl": "https://openagent3.xyz/skills/parallel-deep-research/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Parallel Deep Research", "body": "Deep, multi-source research for complex topics requiring synthesis from many sources. Returns comprehensive reports with citations." }, { "title": "When to Use", "body": "Trigger this skill when the user asks for:\n\n\"deep research on...\", \"thorough investigation of...\", \"comprehensive report about...\"\n\"research everything about...\", \"full analysis of...\"\nComplex topics requiring synthesis from 10+ sources\nCompetitive analysis, market research, due diligence\nQuestions where depth and accuracy matter more than speed\n\nNOT for:\n\nQuick lookups or simple questions (use parallel-search)\nCurrent news or recent events (use parallel-search with --after-date)\nReading specific URLs (use parallel-extract)" }, { "title": "Quick Start", "body": "parallel-cli research run \"your research question\" --processor pro-fast --json -o ./report" }, { "title": "Basic Usage", "body": "parallel-cli research run \"\" [options]" }, { "title": "Common Flags", "body": "FlagDescription-p, --processor Processor tier (see table below)--jsonOutput as JSON-o, --output Save results to file (creates .json and .md)-f, --input-file Read query from file (for long questions)--timeout NMax wait time in seconds (default: 3600)--no-waitReturn immediately, poll later with research status" }, { "title": "Processor Tiers", "body": "ProcessorTimeUse Caselite-fast10-20sQuick lookupsbase-fast15-50sSimple questionscore-fast15s-100sModerate researchpro-fast30s-5minExploratory research (default)ultra-fast1-10minMulti-source deep researchultra2x-fast1-20minDifficult deep researchultra4x-fast1-40minVery difficult researchultra8x-fast1min-1hrMost challenging research\n\nNon-fast variants (e.g., pro, ultra) take longer but use fresher data." }, { "title": "Examples", "body": "Basic research:\n\nparallel-cli research run \"What are the latest developments in quantum computing?\" \\\n --processor pro-fast \\\n --json -o ./quantum-report\n\nDeep competitive analysis:\n\nparallel-cli research run \"Compare Stripe, Square, and Adyen payment platforms: features, pricing, market position, and developer experience\" \\\n --processor ultra-fast \\\n --json -o ./payments-analysis\n\nLong research question from file:\n\n# Create question file\ncat > /tmp/research-question.txt << 'EOF'\nInvestigate the current state of AI regulation globally:\n1. What regulations exist in the US, EU, and China?\n2. What's pending or proposed?\n3. How do companies like OpenAI, Google, and Anthropic respond?\n4. What industry groups are lobbying for/against regulation?\nEOF\n\nparallel-cli research run -f /tmp/research-question.txt \\\n --processor ultra-fast \\\n --json -o ./ai-regulation-report\n\nNon-blocking research:\n\n# Start research without waiting\nparallel-cli research run \"research question\" --no-wait\n\n# Check status later\nparallel-cli research status \n\n# Poll until complete\nparallel-cli research poll --json -o ./report" }, { "title": "Research Question", "body": "Write 2-5 sentences describing:\n\nThe specific question or topic\nScope boundaries (time period, geography, industries)\nWhat aspects matter most (pricing? features? market share?)\nDesired output format (comparison table, timeline, pros/cons)\n\nGood:\n\nCompare the top 5 CRM platforms for B2B SaaS companies with 50-200 employees.\nFocus on: pricing per seat, integration ecosystem, reporting capabilities.\nInclude recent 2024-2026 changes and customer reviews from G2/Capterra.\n\nPoor:\n\nTell me about CRMs" }, { "title": "Response Format", "body": "Returns structured JSON with:\n\ntask_id — unique identifier for polling\nstatus — pending, running, completed, failed\nresult — when complete:\n\nsummary — executive summary\nfindings[] — detailed findings with sources\nsources[] — all referenced URLs with titles" }, { "title": "Output Handling", "body": "When presenting research results:\n\nLead with the executive summary verbatim\nPresent key findings without paraphrasing\nInclude source URLs for all facts\nNote any conflicting information between sources\nPreserve all facts, names, numbers, dates, quotes" }, { "title": "Running Out of Context?", "body": "For long conversations, save results and use sessions_spawn:\n\nparallel-cli research run \"\" --json -o /tmp/research-\n\nThen spawn a sub-agent:\n\n{\n \"tool\": \"sessions_spawn\",\n \"task\": \"Read /tmp/research-.json and present the executive summary and key findings with sources.\",\n \"label\": \"research-summary\"\n}" }, { "title": "Error Handling", "body": "Exit CodeMeaning0Success1Unexpected error (network, parse)2Invalid arguments3API error (non-2xx)" }, { "title": "Prerequisites", "body": "Get an API key at parallel.ai\nInstall the CLI:\n\ncurl -fsSL https://parallel.ai/install.sh | bash\nexport PARALLEL_API_KEY=your-key" }, { "title": "References", "body": "API Docs\nResearch API Reference" } ], "body": "Parallel Deep Research\n\nDeep, multi-source research for complex topics requiring synthesis from many sources. Returns comprehensive reports with citations.\n\nWhen to Use\n\nTrigger this skill when the user asks for:\n\n\"deep research on...\", \"thorough investigation of...\", \"comprehensive report about...\"\n\"research everything about...\", \"full analysis of...\"\nComplex topics requiring synthesis from 10+ sources\nCompetitive analysis, market research, due diligence\nQuestions where depth and accuracy matter more than speed\n\nNOT for:\n\nQuick lookups or simple questions (use parallel-search)\nCurrent news or recent events (use parallel-search with --after-date)\nReading specific URLs (use parallel-extract)\nQuick Start\nparallel-cli research run \"your research question\" --processor pro-fast --json -o ./report\n\nCLI Reference\nBasic Usage\nparallel-cli research run \"\" [options]\n\nCommon Flags\nFlag\tDescription\n-p, --processor \tProcessor tier (see table below)\n--json\tOutput as JSON\n-o, --output \tSave results to file (creates .json and .md)\n-f, --input-file \tRead query from file (for long questions)\n--timeout N\tMax wait time in seconds (default: 3600)\n--no-wait\tReturn immediately, poll later with research status\nProcessor Tiers\nProcessor\tTime\tUse Case\nlite-fast\t10-20s\tQuick lookups\nbase-fast\t15-50s\tSimple questions\ncore-fast\t15s-100s\tModerate research\npro-fast\t30s-5min\tExploratory research (default)\nultra-fast\t1-10min\tMulti-source deep research\nultra2x-fast\t1-20min\tDifficult deep research\nultra4x-fast\t1-40min\tVery difficult research\nultra8x-fast\t1min-1hr\tMost challenging research\n\nNon-fast variants (e.g., pro, ultra) take longer but use fresher data.\n\nExamples\n\nBasic research:\n\nparallel-cli research run \"What are the latest developments in quantum computing?\" \\\n --processor pro-fast \\\n --json -o ./quantum-report\n\n\nDeep competitive analysis:\n\nparallel-cli research run \"Compare Stripe, Square, and Adyen payment platforms: features, pricing, market position, and developer experience\" \\\n --processor ultra-fast \\\n --json -o ./payments-analysis\n\n\nLong research question from file:\n\n# Create question file\ncat > /tmp/research-question.txt << 'EOF'\nInvestigate the current state of AI regulation globally:\n1. What regulations exist in the US, EU, and China?\n2. What's pending or proposed?\n3. How do companies like OpenAI, Google, and Anthropic respond?\n4. What industry groups are lobbying for/against regulation?\nEOF\n\nparallel-cli research run -f /tmp/research-question.txt \\\n --processor ultra-fast \\\n --json -o ./ai-regulation-report\n\n\nNon-blocking research:\n\n# Start research without waiting\nparallel-cli research run \"research question\" --no-wait\n\n# Check status later\nparallel-cli research status \n\n# Poll until complete\nparallel-cli research poll --json -o ./report\n\nBest-Practice Prompting\nResearch Question\n\nWrite 2-5 sentences describing:\n\nThe specific question or topic\nScope boundaries (time period, geography, industries)\nWhat aspects matter most (pricing? features? market share?)\nDesired output format (comparison table, timeline, pros/cons)\n\nGood:\n\nCompare the top 5 CRM platforms for B2B SaaS companies with 50-200 employees.\nFocus on: pricing per seat, integration ecosystem, reporting capabilities.\nInclude recent 2024-2026 changes and customer reviews from G2/Capterra.\n\n\nPoor:\n\nTell me about CRMs\n\nResponse Format\n\nReturns structured JSON with:\n\ntask_id — unique identifier for polling\nstatus — pending, running, completed, failed\nresult — when complete:\nsummary — executive summary\nfindings[] — detailed findings with sources\nsources[] — all referenced URLs with titles\nOutput Handling\n\nWhen presenting research results:\n\nLead with the executive summary verbatim\nPresent key findings without paraphrasing\nInclude source URLs for all facts\nNote any conflicting information between sources\nPreserve all facts, names, numbers, dates, quotes\nRunning Out of Context?\n\nFor long conversations, save results and use sessions_spawn:\n\nparallel-cli research run \"\" --json -o /tmp/research-\n\n\nThen spawn a sub-agent:\n\n{\n \"tool\": \"sessions_spawn\",\n \"task\": \"Read /tmp/research-.json and present the executive summary and key findings with sources.\",\n \"label\": \"research-summary\"\n}\n\nError Handling\nExit Code\tMeaning\n0\tSuccess\n1\tUnexpected error (network, parse)\n2\tInvalid arguments\n3\tAPI error (non-2xx)\nPrerequisites\nGet an API key at parallel.ai\nInstall the CLI:\ncurl -fsSL https://parallel.ai/install.sh | bash\nexport PARALLEL_API_KEY=your-key\n\nReferences\nAPI Docs\nResearch API Reference" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/NormallyGaussian/parallel-deep-research", "publisherUrl": "https://clawhub.ai/NormallyGaussian/parallel-deep-research", "owner": "NormallyGaussian", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/parallel-deep-research", "downloadUrl": "https://openagent3.xyz/downloads/parallel-deep-research", "agentUrl": "https://openagent3.xyz/skills/parallel-deep-research/agent", "manifestUrl": "https://openagent3.xyz/skills/parallel-deep-research/agent.json", "briefUrl": "https://openagent3.xyz/skills/parallel-deep-research/agent.md" } }