{
  "schemaVersion": "1.0",
  "item": {
    "slug": "empirical-paper-analysis-skill",
    "name": "Empirical paper analysis",
    "source": "tencent",
    "type": "skill",
    "category": "数据分析",
    "sourceUrl": "https://clawhub.ai/zhouziyue233/empirical-paper-analysis-skill",
    "canonicalUrl": "https://clawhub.ai/zhouziyue233/empirical-paper-analysis-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/empirical-paper-analysis-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=empirical-paper-analysis-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "examples.md",
      "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/empirical-paper-analysis-skill"
    },
    "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/empirical-paper-analysis-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/empirical-paper-analysis-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/empirical-paper-analysis-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/empirical-paper-analysis-skill/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": "Skill Description",
        "body": "This skill enables Claude Code to deeply analyze empirical research papers, following a structured framework: Problem Statement → Core Empirical Challenges → Identification Strategy → Key Findings → Academic Contribution."
      },
      {
        "title": "Target User",
        "body": "Researchers in law and economics who regularly read and analyze empirical papers in law and economics, especially with quantitative methods (econometrics, machine learning, NLP, etc.)."
      },
      {
        "title": "Input Requirements",
        "body": "PDF file of an empirical research paper\nPublication information (Authors, Journal, Date, etc)"
      },
      {
        "title": "1. 问题的提出 (Problem Statement)",
        "body": "Objective: Identify the core research question and its motivation.\n\nAnalysis Points:\n\nWhat is the primary research question? / What problem or phenomenon is being studied?\nWhy is this question important (policy relevance, theoretical gap, methodological innovation, practical value)?\nWhat is the economic/legal intuition behind the research design?"
      },
      {
        "title": "2. 实证研究的核心难题 (Core Empirical Challenges)",
        "body": "Objective: Identify the key methodological obstacles that make causal inference difficult.\n\nCommon Challenges to Look For:\n\nSelection bias: Observed vs unobserved outcomes (e.g., selective labels problem)\nOmitted variable bias: Unobserved confounders (e.g., judges' private information)\nEndogeneity: Reverse causality or simultaneity\nMeasurement error: How to quantify abstract concepts (e.g., legal ideas, judicial attitudes)\nExternal validity: Generalizability concerns\nData limitations: Missing counterfactuals, truncated samples, etc.\n\nOutput Format:\nFor each challenge:\n\nClearly state the problem\nExplain why it matters for causal inference\nUse examples/tables to illustrate if helpful"
      },
      {
        "title": "3. 识别策略与方法设计 (Identification Strategy & Research Design)",
        "body": "Objective: Explain how the paper solves the empirical challenges.\n\nKey Elements:\n\nIdentification strategy: Natural experiment, IV, RD, DID, matching, ML+causal inference hybrid\nData source: Dataset description, sample selection, time period\nEmpirical specification: Main regression model, key variables\nRobustness checks: Alternative specifications, placebo tests, sensitivity analysis\nNovel methodological contributions: Any innovative techniques?\n\nCritical Analysis:\n\nAre the identification assumptions plausible?\nAre there remaining threats to validity?\nHow convincing is the causal interpretation?"
      },
      {
        "title": "4. 重要发现与结论 (Key Findings & Conclusions)",
        "body": "Objective: Summarize the main empirical results and their interpretation.\n\nStructure:\n\nMain findings (with magnitude/significance)\nRobustness of results\nHeterogeneous effects (if any)\nEconomic/legal interpretation\nPolicy implications\n\nFormat:\n\nUse bullet points for clarity\nInclude key numbers (effect sizes, significance levels)\nReference important tables/figures"
      },
      {
        "title": "5. 学术价值 (Academic Contribution)",
        "body": "Objective: Evaluate the paper's broader significance.\n\nDimensions:\n\nMethodological innovation: New identification strategies, measurement techniques\nTheoretical contribution: New insights about legal/judicial behavior, institutional design\nPolicy relevance: Implications for legal reform, judicial training, algorithm adoption\nInterdisciplinary impact: Bridges law, economics, computer science\nFuture research: Opens new questions or directions"
      },
      {
        "title": "Output Format",
        "body": "Generate a structured markdown document following this template:\n\n# [Paper Title]\n\n**Authors:** [List]\n**Journal:** [Name, Year]\n**DOI/Link:** [If available]\n\n## 问题的提出\n\n[Analysis following framework above]\n\n## 实证研究的核心难题\n\n### 难题一：[Name]\n[Explanation]\n\n### 难题二：[Name]\n[Explanation]\n\n## 识别策略与方法设计\n\n### 数据来源\n[Description]\n\n### 识别策略\n[Core identification approach]\n\n### 方法设计\n[Technical details]\n\n## 重要发现与结论\n\n- **发现一：** [Finding with magnitude]\n- **发现二：** [Finding with magnitude]\n- **政策含义：** [Implications]\n\n## 学术价值\n\n- **方法论贡献：** [Innovation]\n- **理论贡献：** [Insights]\n- **政策相关性：** [Relevance]"
      },
      {
        "title": "Special Instructions",
        "body": "Academic Tone: Use precise academic language appropriate for PhD-level analysis. Assume familiarity with econometric concepts (DID, IV, RDD, etc.) and ML methods (GBDT, NLP, embeddings).\n\n\nBilingual Output: Primary language is Chinese (as shown in the examples), but technical terms can be included in parentheses with English abbreviation when first introduced.\n\n\nMathematical Rigor: Don't shy away from mathematical notation when describing models or identification strategies. For example:\n\nRegression specifications: $Y_i = \\beta_0 + \\beta_1 Treatment_i + X_i'\\gamma + \\epsilon_i$\nDID: $Y_{ijt} = \\alpha + \\beta(Post_t \\times Treat_j) + \\delta_j + \\lambda_t + \\varepsilon_{ijt}$\n\n\n\nCritical Thinking: Don't just summarize—analyze. Question assumptions, evaluate identification strength, consider alternative explanations.\n\n\nTables/Figures: When referencing tables or figures from the paper:\n\nDescribe what they show conceptually\nHighlight the most important results\nDon't try to reproduce full tables in text\n\n\n\nScope: Focus on the five core sections. Don't add unnecessary sections."
      },
      {
        "title": "Example Workflow",
        "body": "Read the entire paper to understand the research question and context\nExtract the empirical strategy - pay special attention to identification sections\nIdentify the key challenges the authors face\nTrace how they solve each challenge methodologically\nSynthesize the findings with appropriate interpretation\nEvaluate the contribution in context of the literature"
      }
    ],
    "body": "Empirical Paper Analysis Skill\nSkill Description\n\nThis skill enables Claude Code to deeply analyze empirical research papers, following a structured framework: Problem Statement → Core Empirical Challenges → Identification Strategy → Key Findings → Academic Contribution.\n\nTarget User\n\nResearchers in law and economics who regularly read and analyze empirical papers in law and economics, especially with quantitative methods (econometrics, machine learning, NLP, etc.).\n\nInput Requirements\nPDF file of an empirical research paper\nPublication information (Authors, Journal, Date, etc)\nAnalysis Framework\n1. 问题的提出 (Problem Statement)\n\nObjective: Identify the core research question and its motivation.\n\nAnalysis Points:\n\nWhat is the primary research question? / What problem or phenomenon is being studied?\nWhy is this question important (policy relevance, theoretical gap, methodological innovation, practical value)?\nWhat is the economic/legal intuition behind the research design?\n2. 实证研究的核心难题 (Core Empirical Challenges)\n\nObjective: Identify the key methodological obstacles that make causal inference difficult.\n\nCommon Challenges to Look For:\n\nSelection bias: Observed vs unobserved outcomes (e.g., selective labels problem)\nOmitted variable bias: Unobserved confounders (e.g., judges' private information)\nEndogeneity: Reverse causality or simultaneity\nMeasurement error: How to quantify abstract concepts (e.g., legal ideas, judicial attitudes)\nExternal validity: Generalizability concerns\nData limitations: Missing counterfactuals, truncated samples, etc.\n\nOutput Format: For each challenge:\n\nClearly state the problem\nExplain why it matters for causal inference\nUse examples/tables to illustrate if helpful\n3. 识别策略与方法设计 (Identification Strategy & Research Design)\n\nObjective: Explain how the paper solves the empirical challenges.\n\nKey Elements:\n\nIdentification strategy: Natural experiment, IV, RD, DID, matching, ML+causal inference hybrid\nData source: Dataset description, sample selection, time period\nEmpirical specification: Main regression model, key variables\nRobustness checks: Alternative specifications, placebo tests, sensitivity analysis\nNovel methodological contributions: Any innovative techniques?\n\nCritical Analysis:\n\nAre the identification assumptions plausible?\nAre there remaining threats to validity?\nHow convincing is the causal interpretation?\n4. 重要发现与结论 (Key Findings & Conclusions)\n\nObjective: Summarize the main empirical results and their interpretation.\n\nStructure:\n\nMain findings (with magnitude/significance)\nRobustness of results\nHeterogeneous effects (if any)\nEconomic/legal interpretation\nPolicy implications\n\nFormat:\n\nUse bullet points for clarity\nInclude key numbers (effect sizes, significance levels)\nReference important tables/figures\n5. 学术价值 (Academic Contribution)\n\nObjective: Evaluate the paper's broader significance.\n\nDimensions:\n\nMethodological innovation: New identification strategies, measurement techniques\nTheoretical contribution: New insights about legal/judicial behavior, institutional design\nPolicy relevance: Implications for legal reform, judicial training, algorithm adoption\nInterdisciplinary impact: Bridges law, economics, computer science\nFuture research: Opens new questions or directions\nOutput Format\n\nGenerate a structured markdown document following this template:\n\n# [Paper Title]\n\n**Authors:** [List]\n**Journal:** [Name, Year]\n**DOI/Link:** [If available]\n\n## 问题的提出\n\n[Analysis following framework above]\n\n## 实证研究的核心难题\n\n### 难题一：[Name]\n[Explanation]\n\n### 难题二：[Name]\n[Explanation]\n\n## 识别策略与方法设计\n\n### 数据来源\n[Description]\n\n### 识别策略\n[Core identification approach]\n\n### 方法设计\n[Technical details]\n\n## 重要发现与结论\n\n- **发现一：** [Finding with magnitude]\n- **发现二：** [Finding with magnitude]\n- **政策含义：** [Implications]\n\n## 学术价值\n\n- **方法论贡献：** [Innovation]\n- **理论贡献：** [Insights]\n- **政策相关性：** [Relevance]\n\n\nSpecial Instructions\n\nAcademic Tone: Use precise academic language appropriate for PhD-level analysis. Assume familiarity with econometric concepts (DID, IV, RDD, etc.) and ML methods (GBDT, NLP, embeddings).\n\nBilingual Output: Primary language is Chinese (as shown in the examples), but technical terms can be included in parentheses with English abbreviation when first introduced.\n\nMathematical Rigor: Don't shy away from mathematical notation when describing models or identification strategies. For example:\n\nRegression specifications: $Y_i = \\beta_0 + \\beta_1 Treatment_i + X_i'\\gamma + \\epsilon_i$\nDID: $Y_{ijt} = \\alpha + \\beta(Post_t \\times Treat_j) + \\delta_j + \\lambda_t + \\varepsilon_{ijt}$\n\nCritical Thinking: Don't just summarize—analyze. Question assumptions, evaluate identification strength, consider alternative explanations.\n\nTables/Figures: When referencing tables or figures from the paper:\n\nDescribe what they show conceptually\nHighlight the most important results\nDon't try to reproduce full tables in text\n\nScope: Focus on the five core sections. Don't add unnecessary sections.\n\nExample Workflow\nRead the entire paper to understand the research question and context\nExtract the empirical strategy - pay special attention to identification sections\nIdentify the key challenges the authors face\nTrace how they solve each challenge methodologically\nSynthesize the findings with appropriate interpretation\nEvaluate the contribution in context of the literature"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/zhouziyue233/empirical-paper-analysis-skill",
    "publisherUrl": "https://clawhub.ai/zhouziyue233/empirical-paper-analysis-skill",
    "owner": "zhouziyue233",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/empirical-paper-analysis-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/empirical-paper-analysis-skill",
    "agentUrl": "https://openagent3.xyz/skills/empirical-paper-analysis-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/empirical-paper-analysis-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/empirical-paper-analysis-skill/agent.md"
  }
}