{
  "schemaVersion": "1.0",
  "item": {
    "slug": "virtual-reading-group",
    "name": "Virtual Reading Group",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/IsonaEi/virtual-reading-group",
    "canonicalUrl": "https://clawhub.ai/IsonaEi/virtual-reading-group",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/virtual-reading-group",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=virtual-reading-group",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "assets/synthesis-template.md",
      "references/default-personas.md",
      "references/paper-notes-template.md",
      "references/workflow.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/virtual-reading-group"
    },
    "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/virtual-reading-group",
    "agentPageUrl": "https://openagent3.xyz/skills/virtual-reading-group/agent",
    "manifestUrl": "https://openagent3.xyz/skills/virtual-reading-group/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/virtual-reading-group/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": "Virtual Reading Group",
        "body": "Orchestrate parallel expert agents to read papers, discuss findings, challenge each other's interpretations, and synthesize an integrated discussion document with traceable citations."
      },
      {
        "title": "Quick Start",
        "body": "Minimum inputs required:\n\nResearch question — the lens through which papers are analyzed\nPaper list — paths to PDFs/text files, or paper descriptions for web lookup\nOutput directory — where all outputs are written\n\nOptional inputs:\n\nCustom expert personas (default: see references/default-personas.md)\nCustom junior researcher persona\nLanguage preference (default: English)\nNumber of experts (default: auto-calculated from paper count)"
      },
      {
        "title": "Workflow Overview",
        "body": "The skill runs 4 sequential phases. Each phase must complete before the next begins.\n\nPhaseAgentsInputOutput1. Paper ReadingN experts (parallel)Papers + research question{AuthorYear}_notes.md, {Expert}_session_summary.md2. Junior Discussion1 junior researcherAll Phase 1 outputs{Junior}_discussion.md3. Expert ResponsesN experts (parallel)Phase 2 output + other experts' summaries{Expert}_response_to_{Junior}.md4. Synthesis1 synthesizerAll previous outputsIntegrated_Discussion_Summary.md\n\nFor detailed prompts and phase specifications: Read references/workflow.md."
      },
      {
        "title": "Orchestration Procedure",
        "body": "⚠️ Important: The prompts below are abbreviated summaries. For full prompt templates that produce quality output, use references/workflow.md. The pseudocode blocks show orchestration structure — adapt to your actual sub-agent spawning mechanism."
      },
      {
        "title": "1. Validate Inputs",
        "body": "- Confirm research question is specified\n- Confirm paper list is non-empty\n- Confirm output directory exists or create it\n- Load personas from user input or references/default-personas.md"
      },
      {
        "title": "2. Calculate Expert Assignment",
        "body": "Determine number of experts and paper batches:\n\nif paper_count <= 4:\n    num_experts = 1\nelif paper_count <= 10:\n    num_experts = 2\nelif paper_count <= 20:\n    num_experts = min(4, ceil(paper_count / 5))\nelse:\n    num_experts = min(8, ceil(paper_count / 5))\n\nDistribute papers evenly across experts (max 5 per expert).\n\n# ⚠️ Context contamination warning: assigning >5 papers per expert degrades\n# note quality — later papers in the batch get shallower treatment as context\n# fills up. Prefer 3-5 papers per agent for best results."
      },
      {
        "title": "3. Execute Phase 1 — Paper Reading (Parallel)",
        "body": "For each expert, spawn a sub-agent with:\n\nLabel: expert-reader-{expert_name}\nModel: opus (or sonnet for budget)\nCore instructions:\n\nRead assigned papers through research question lens\nWrite notes using references/paper-notes-template.md\nSave as {output_dir}/{AuthorYear}_notes.md\nWrite session summary with cross-cutting themes\nCritical: Quote specific passages with section labels — all claims must be traceable\n\n📄 Full prompt template: See references/workflow.md → Phase 1\n\nWait for all Phase 1 agents to complete before proceeding."
      },
      {
        "title": "4. Execute Phase 2 — Junior Discussion (Single Agent)",
        "body": "Spawn single agent with:\n\nLabel: junior-discussion\nModel: opus (required — needs strong reasoning)\nCore instructions:\n\nRead all Phase 1 outputs (notes + summaries)\nFor each paper: summarize claims, pose challenging questions to each expert\nGenerate Grand Questions: 3 unsolved problems, 2 testable hypotheses, 2 methodological gaps\nReference specific passages — be intellectually provocative\n\n📄 Full prompt template: See references/workflow.md → Phase 2\n\nWait for Phase 2 to complete before proceeding."
      },
      {
        "title": "5. Execute Phase 3 — Expert Responses (Parallel)",
        "body": "For each expert, spawn a sub-agent with:\n\nLabel: expert-response-{expert_name}\nModel: opus (recommended)\nCore instructions:\n\nRead junior's discussion + other experts' summaries + own notes\nRespond to each question directed at them (150-300 words per response)\nReference specific paper passages, engage with other expert's perspective\nRespond to Grand Questions from their domain expertise\nBe collegial but intellectually rigorous — disagree where warranted\n\n📄 Full prompt template: See references/workflow.md → Phase 3\n\nWait for all Phase 3 agents to complete before proceeding."
      },
      {
        "title": "6. Execute Phase 4 — Synthesis (Single Agent)",
        "body": "Spawn single agent with:\n\nLabel: synthesis\nModel: opus (required — complex reasoning)\nCore instructions:\n\nRead ALL files from Phases 1-3\nFollow assets/synthesis-template.md structure\nOrganize by THEME, not by paper or speaker\nEvery claim attributed: [Expert_A]/[Expert_B]/[Junior] + (PaperCode, §Section)\nInclude: Points of Consensus, Points of Disagreement, Open Questions\nSynthesize, don't summarize — find the intellectual threads\n\n📄 Full prompt template: See references/workflow.md → Phase 4"
      },
      {
        "title": "7. Report Completion",
        "body": "List all generated files and provide a brief summary of the discussion themes."
      },
      {
        "title": "Deeper Discussion",
        "body": "If user wants experts to expand on specific points:\n\nSpawn new expert response agent(s) with targeted follow-up questions\nRe-run Phase 4 synthesis including the additional responses"
      },
      {
        "title": "Second Round",
        "body": "For a full second round (new questions, new responses):\n\nRename Phase 2-4 outputs with round suffix (e.g., Chen_discussion_r1.md)\nRe-run Phase 2 with instruction to build on previous round\nContinue through Phases 3-4"
      },
      {
        "title": "Recovery from Partial Run",
        "body": "If a phase fails:\n\nCheck error handling in references/workflow.md\nRetry failed agent(s) individually\nContinue from last successful phase (outputs are saved incrementally)"
      },
      {
        "title": "File Naming Conventions",
        "body": "File TypePatternExamplePaper notes{FirstAuthorLastName}{Year}_notes.mdChen2024_notes.mdExpert summary{ExpertLastName}_session_summary.mdLin_session_summary.mdJunior discussion{JuniorLastName}_discussion.mdChen_discussion.mdExpert response{ExpertLastName}_response_to_{JuniorLastName}.mdLin_response_to_Chen.mdSynthesisIntegrated_Discussion_Summary.md—"
      },
      {
        "title": "Citation Requirements",
        "body": "Enforce in all agent prompts:\n\nEvery factual claim must reference a paper\nUse format: (AuthorYear, §Section) or (AuthorYear, p.X)\nDirect quotes must include section/page\nDiscussion claims must attribute speaker: [Expert_A], [Expert_B], [Junior]"
      },
      {
        "title": "⚠️ Anti-Fabrication Rule (Critical)",
        "body": "Never fabricate citations. If an agent cannot find the exact passage in the source text:\n\nLeave the field blank or write <!-- source not found -->\nDo NOT paraphrase and present it as a quote\nDo NOT infer what the paper \"probably says\"\n\nFabricated citations are worse than missing citations — they corrupt the knowledge base silently. Accuracy > Coverage."
      },
      {
        "title": "No Source = No Notes",
        "body": "If a paper has no PDF or markdown source available:\n\nWrite a placeholder note with status 📭 未讀\nLeave all content sections blank\nDo NOT attempt to write notes from memory or web search results\n\nOnly write substantive notes when the actual source document is accessible."
      },
      {
        "title": "Scaling Guidelines",
        "body": "PapersExpertsBatchesEstimated Time1-61115-20 min7-122220-30 min13-243-43-430-45 min25-504-85-845-90 min"
      },
      {
        "title": "Custom Personas",
        "body": "Replace default personas by providing:\n\nExpert A: Dr. [Name], [Role]. Background in [X]. \nEmphasizes [methodology/perspective]. Skeptical of [Y].\nTone: [collegial/rigorous/provocative].\n\nExpert B: Dr. [Name], [Role]. Background in [X].\n...\n\nSee references/default-personas.md for complete templates."
      },
      {
        "title": "Language",
        "body": "Pass the language parameter when invoking the orchestration:\n\nAll agent prompts include Language: {language} instruction\nAgents read papers and write outputs in the specified language\nDefault: English\n\nExample: \"Run the reading group in Japanese\" → adds Language: Japanese to all phase prompts."
      },
      {
        "title": "Model Selection",
        "body": "Model choice significantly impacts output quality and cost:\n\nConfigurationPhasesQualityCostUse WhenFull opusAll phases use opusHighest$$$Publication-quality analysis, complex papersMixedPhase 1: sonnet, Phases 2-4: opusHigh$$Good balance — reading is less reasoning-intensiveBudgetAll phases use sonnetMedium$Quick exploration, simpler papers\n\nRecommendations:\n\nPhase 2 (Junior Discussion) benefits most from opus — requires synthesizing multiple papers and generating non-obvious questions\nPhase 4 (Synthesis) also benefits from opus — thematic organization requires complex reasoning\nPhase 1 (Reading) can use sonnet if papers aren't highly technical\nPhase 3 (Responses) can use sonnet if questions are straightforward"
      },
      {
        "title": "Integration",
        "body": "This skill is standalone but works well with paper collection workflows:\n\nliterature-manager or similar skills: Use to gather and organize papers first, then pass the collection to virtual-reading-group\nPDF extraction tools: Pre-extract text from PDFs if agents have trouble reading them directly"
      },
      {
        "title": "References",
        "body": "references/workflow.md — Detailed phase specifications and full prompt templates\nreferences/default-personas.md — Ready-to-use expert and junior researcher personas\nreferences/paper-notes-template.md — Template for individual paper notes"
      },
      {
        "title": "Assets",
        "body": "assets/synthesis-template.md — Structure for the final integrated discussion summary"
      }
    ],
    "body": "Virtual Reading Group\n\nOrchestrate parallel expert agents to read papers, discuss findings, challenge each other's interpretations, and synthesize an integrated discussion document with traceable citations.\n\nQuick Start\n\nMinimum inputs required:\n\nResearch question — the lens through which papers are analyzed\nPaper list — paths to PDFs/text files, or paper descriptions for web lookup\nOutput directory — where all outputs are written\n\nOptional inputs:\n\nCustom expert personas (default: see references/default-personas.md)\nCustom junior researcher persona\nLanguage preference (default: English)\nNumber of experts (default: auto-calculated from paper count)\nWorkflow Overview\n\nThe skill runs 4 sequential phases. Each phase must complete before the next begins.\n\nPhase\tAgents\tInput\tOutput\n1. Paper Reading\tN experts (parallel)\tPapers + research question\t{AuthorYear}_notes.md, {Expert}_session_summary.md\n2. Junior Discussion\t1 junior researcher\tAll Phase 1 outputs\t{Junior}_discussion.md\n3. Expert Responses\tN experts (parallel)\tPhase 2 output + other experts' summaries\t{Expert}_response_to_{Junior}.md\n4. Synthesis\t1 synthesizer\tAll previous outputs\tIntegrated_Discussion_Summary.md\n\nFor detailed prompts and phase specifications: Read references/workflow.md.\n\nOrchestration Procedure\n\n⚠️ Important: The prompts below are abbreviated summaries. For full prompt templates that produce quality output, use references/workflow.md. The pseudocode blocks show orchestration structure — adapt to your actual sub-agent spawning mechanism.\n\n1. Validate Inputs\n- Confirm research question is specified\n- Confirm paper list is non-empty\n- Confirm output directory exists or create it\n- Load personas from user input or references/default-personas.md\n\n2. Calculate Expert Assignment\n\nDetermine number of experts and paper batches:\n\nif paper_count <= 4:\n    num_experts = 1\nelif paper_count <= 10:\n    num_experts = 2\nelif paper_count <= 20:\n    num_experts = min(4, ceil(paper_count / 5))\nelse:\n    num_experts = min(8, ceil(paper_count / 5))\n\nDistribute papers evenly across experts (max 5 per expert).\n\n# ⚠️ Context contamination warning: assigning >5 papers per expert degrades\n# note quality — later papers in the batch get shallower treatment as context\n# fills up. Prefer 3-5 papers per agent for best results.\n\n3. Execute Phase 1 — Paper Reading (Parallel)\n\nFor each expert, spawn a sub-agent with:\n\nLabel: expert-reader-{expert_name}\nModel: opus (or sonnet for budget)\nCore instructions:\nRead assigned papers through research question lens\nWrite notes using references/paper-notes-template.md\nSave as {output_dir}/{AuthorYear}_notes.md\nWrite session summary with cross-cutting themes\nCritical: Quote specific passages with section labels — all claims must be traceable\n\n📄 Full prompt template: See references/workflow.md → Phase 1\n\nWait for all Phase 1 agents to complete before proceeding.\n\n4. Execute Phase 2 — Junior Discussion (Single Agent)\n\nSpawn single agent with:\n\nLabel: junior-discussion\nModel: opus (required — needs strong reasoning)\nCore instructions:\nRead all Phase 1 outputs (notes + summaries)\nFor each paper: summarize claims, pose challenging questions to each expert\nGenerate Grand Questions: 3 unsolved problems, 2 testable hypotheses, 2 methodological gaps\nReference specific passages — be intellectually provocative\n\n📄 Full prompt template: See references/workflow.md → Phase 2\n\nWait for Phase 2 to complete before proceeding.\n\n5. Execute Phase 3 — Expert Responses (Parallel)\n\nFor each expert, spawn a sub-agent with:\n\nLabel: expert-response-{expert_name}\nModel: opus (recommended)\nCore instructions:\nRead junior's discussion + other experts' summaries + own notes\nRespond to each question directed at them (150-300 words per response)\nReference specific paper passages, engage with other expert's perspective\nRespond to Grand Questions from their domain expertise\nBe collegial but intellectually rigorous — disagree where warranted\n\n📄 Full prompt template: See references/workflow.md → Phase 3\n\nWait for all Phase 3 agents to complete before proceeding.\n\n6. Execute Phase 4 — Synthesis (Single Agent)\n\nSpawn single agent with:\n\nLabel: synthesis\nModel: opus (required — complex reasoning)\nCore instructions:\nRead ALL files from Phases 1-3\nFollow assets/synthesis-template.md structure\nOrganize by THEME, not by paper or speaker\nEvery claim attributed: [Expert_A]/[Expert_B]/[Junior] + (PaperCode, §Section)\nInclude: Points of Consensus, Points of Disagreement, Open Questions\nSynthesize, don't summarize — find the intellectual threads\n\n📄 Full prompt template: See references/workflow.md → Phase 4\n\n7. Report Completion\n\nList all generated files and provide a brief summary of the discussion themes.\n\nIteration and Follow-up\nDeeper Discussion\n\nIf user wants experts to expand on specific points:\n\nSpawn new expert response agent(s) with targeted follow-up questions\nRe-run Phase 4 synthesis including the additional responses\nSecond Round\n\nFor a full second round (new questions, new responses):\n\nRename Phase 2-4 outputs with round suffix (e.g., Chen_discussion_r1.md)\nRe-run Phase 2 with instruction to build on previous round\nContinue through Phases 3-4\nRecovery from Partial Run\n\nIf a phase fails:\n\nCheck error handling in references/workflow.md\nRetry failed agent(s) individually\nContinue from last successful phase (outputs are saved incrementally)\nFile Naming Conventions\nFile Type\tPattern\tExample\nPaper notes\t{FirstAuthorLastName}{Year}_notes.md\tChen2024_notes.md\nExpert summary\t{ExpertLastName}_session_summary.md\tLin_session_summary.md\nJunior discussion\t{JuniorLastName}_discussion.md\tChen_discussion.md\nExpert response\t{ExpertLastName}_response_to_{JuniorLastName}.md\tLin_response_to_Chen.md\nSynthesis\tIntegrated_Discussion_Summary.md\t—\nCitation Requirements\n\nEnforce in all agent prompts:\n\nEvery factual claim must reference a paper\nUse format: (AuthorYear, §Section) or (AuthorYear, p.X)\nDirect quotes must include section/page\nDiscussion claims must attribute speaker: [Expert_A], [Expert_B], [Junior]\n⚠️ Anti-Fabrication Rule (Critical)\n\nNever fabricate citations. If an agent cannot find the exact passage in the source text:\n\nLeave the field blank or write <!-- source not found -->\nDo NOT paraphrase and present it as a quote\nDo NOT infer what the paper \"probably says\"\n\nFabricated citations are worse than missing citations — they corrupt the knowledge base silently. Accuracy > Coverage.\n\nNo Source = No Notes\n\nIf a paper has no PDF or markdown source available:\n\nWrite a placeholder note with status 📭 未讀\nLeave all content sections blank\nDo NOT attempt to write notes from memory or web search results\n\nOnly write substantive notes when the actual source document is accessible.\n\nScaling Guidelines\nPapers\tExperts\tBatches\tEstimated Time\n1-6\t1\t1\t15-20 min\n7-12\t2\t2\t20-30 min\n13-24\t3-4\t3-4\t30-45 min\n25-50\t4-8\t5-8\t45-90 min\nCustomization\nCustom Personas\n\nReplace default personas by providing:\n\nExpert A: Dr. [Name], [Role]. Background in [X]. \nEmphasizes [methodology/perspective]. Skeptical of [Y].\nTone: [collegial/rigorous/provocative].\n\nExpert B: Dr. [Name], [Role]. Background in [X].\n...\n\n\nSee references/default-personas.md for complete templates.\n\nLanguage\n\nPass the language parameter when invoking the orchestration:\n\nAll agent prompts include Language: {language} instruction\nAgents read papers and write outputs in the specified language\nDefault: English\n\nExample: \"Run the reading group in Japanese\" → adds Language: Japanese to all phase prompts.\n\nModel Selection\n\nModel choice significantly impacts output quality and cost:\n\nConfiguration\tPhases\tQuality\tCost\tUse When\nFull opus\tAll phases use opus\tHighest\t$$$\tPublication-quality analysis, complex papers\nMixed\tPhase 1: sonnet, Phases 2-4: opus\tHigh\t$$\tGood balance — reading is less reasoning-intensive\nBudget\tAll phases use sonnet\tMedium\t$\tQuick exploration, simpler papers\n\nRecommendations:\n\nPhase 2 (Junior Discussion) benefits most from opus — requires synthesizing multiple papers and generating non-obvious questions\nPhase 4 (Synthesis) also benefits from opus — thematic organization requires complex reasoning\nPhase 1 (Reading) can use sonnet if papers aren't highly technical\nPhase 3 (Responses) can use sonnet if questions are straightforward\nIntegration\n\nThis skill is standalone but works well with paper collection workflows:\n\nliterature-manager or similar skills: Use to gather and organize papers first, then pass the collection to virtual-reading-group\nPDF extraction tools: Pre-extract text from PDFs if agents have trouble reading them directly\nReferences\nreferences/workflow.md — Detailed phase specifications and full prompt templates\nreferences/default-personas.md — Ready-to-use expert and junior researcher personas\nreferences/paper-notes-template.md — Template for individual paper notes\nAssets\nassets/synthesis-template.md — Structure for the final integrated discussion summary"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/IsonaEi/virtual-reading-group",
    "publisherUrl": "https://clawhub.ai/IsonaEi/virtual-reading-group",
    "owner": "IsonaEi",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/virtual-reading-group",
    "downloadUrl": "https://openagent3.xyz/downloads/virtual-reading-group",
    "agentUrl": "https://openagent3.xyz/skills/virtual-reading-group/agent",
    "manifestUrl": "https://openagent3.xyz/skills/virtual-reading-group/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/virtual-reading-group/agent.md"
  }
}