{
  "schemaVersion": "1.0",
  "item": {
    "slug": "lawclaw",
    "name": "Drop a contract, get answers. lawclaw rips through PDFs, spots risky clauses, diffs redlines, checks citations, and searches thousands of discovery docs—locally, so nothing leaves your machine. Built for attorneys and paralegals who bill by the hour and can't waste one",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/jagadeeshmurali-coder/lawclaw",
    "canonicalUrl": "https://clawhub.ai/jagadeeshmurali-coder/lawclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/lawclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lawclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "_meta.json",
      "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/lawclaw"
    },
    "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/lawclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/lawclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/lawclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/lawclaw/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": "lawclaw",
        "body": "Drop a contract, get answers.\n\nlawclaw tears through legal documents the way you wish your associates would—fast, thorough, and without missing the indemnification clause buried on page 47. It extracts text from PDFs, flags key clauses, generates redline comparisons, validates citations, and searches entire discovery sets for the one sentence that wins your case.\n\nEverything runs locally on your machine. No uploads, no third-party servers, no risk to attorney-client privilege. Just you, your terminal, and a very sharp claw.\n\nWho it's for: Attorneys, paralegals, and legal ops teams doing contract review, litigation support, due diligence, e-discovery, or brief-writing.\n\nWhat it replaces: Hours of Ctrl+F across dozens of PDFs."
      },
      {
        "title": "Core Capabilities",
        "body": "Document Analysis\n\nExtract text from legal PDFs: pdftotext <file.pdf> <output.txt>\nSearch for specific clauses: grep -i \"indemnification\\|liability\\|warranty\" contract.txt\nWord count for billing: wc -w document.txt\nExtract metadata: pdfinfo <file.pdf>\n\nContract Clause Extraction\nUse grep with regex to find common clauses:\n\nIndemnification: grep -i \"indemnif\\|hold harmless\" contract.txt\nTermination: grep -i \"terminat\\|cancellation\" contract.txt -A 3\nConfidentiality: grep -i \"confidential\\|proprietary\\|NDA\" contract.txt -A 3\nForce majeure: grep -i \"force majeure\\|act of god\" contract.txt -A 3\nJurisdiction: grep -i \"jurisdiction\\|venue\\|governing law\" contract.txt -A 2\nArbitration: grep -i \"arbitration\\|dispute resolution\" contract.txt -A 3\nNon-compete: grep -i \"non-compete\\|noncompete\\|restrictive covenant\" contract.txt -A 3\nAssignment: grep -i \"assign\\|transfer\\|delegate\" contract.txt -A 2\n\nRedline / Comparison\n\nCompare two versions: diff -u original.txt revised.txt > redline.diff\nSide-by-side view: diff -y original.txt revised.txt | less\nWord-level diff: wdiff original.txt revised.txt > changes.txt\nConvert Word to text first: pandoc contract.docx -t plain -o contract.txt\n\nCitation and Reference Checking\n\nFind case citations: grep -E \"[0-9]+ [A-Z]\\.[A-Za-z0-9.]+ [0-9]+\" brief.txt\nFind U.S. Code refs: grep -E \"[0-9]+ U\\.S\\.C\\. § [0-9]+\" document.txt\nFind CFR refs: grep -E \"[0-9]+ C\\.F\\.R\\. § [0-9]+\" document.txt\nExtract footnotes: grep -E \"\\[[0-9]+\\]\" brief.txt\nFind Bluebook short cites: grep -E \"[A-Z][a-z]+, [0-9]+ [A-Z]\\.\" brief.txt\n\nDocument Organization\n\nFind specific file types: find . -name \"*.pdf\" -type f\nSearch within discovery docs: grep -r \"key term\" ./discovery/\nList recent modifications: find . -name \"*.pdf\" -mtime -7 -ls\nBatch rename exhibits: for f in *.pdf; do mv \"$f\" \"Exhibit_${f}\"; done\n\nDiscovery Support\n\nCount pages in PDF: pdfinfo document.pdf | grep Pages\nBatch convert PDFs: for f in *.pdf; do pdftotext \"$f\" \"${f%.pdf}.txt\"; done\nCreate production log: ls -lh *.pdf > production_log.txt\nSearch Bates numbers: grep -r \"PROD[0-9]\\{6\\}\" ./documents/\n\nDue Diligence\n\nScan for key terms: grep -i \"material adverse\\|intellectual property\\|pending litigation\" diligence/*.txt\nExtract dates: grep -E \"[0-9]{1,2}/[0-9]{1,2}/[0-9]{4}\" contract.txt\nFind monetary amounts: grep -E \"\\$[0-9,]+(\\.[0-9]{2})?\" agreement.txt\nIdentify parties: grep -E \"WHEREAS|Party|Seller|Buyer|Lessor|Lessee\" contract.txt\n\nDeposition / Transcript Analysis\n\nSearch testimony: grep -i \"Q\\.\" deposition.txt | grep -i \"keyword\"\nExtract witness answers: grep \"A\\.\" deposition.txt -A 2\nCount pages/lines: wc -l transcript.txt\n\nPrivilege Log Support\n\nGenerate file list: find ./documents -type f -exec ls -lh {} \\; > privilege_log.csv\nSearch for privileged terms: grep -ri \"attorney-client\\|work product\" ./emails/\nTag privileged docs: grep -rli \"attorney-client\" ./emails/ > privileged_files.txt"
      },
      {
        "title": "Common Workflows",
        "body": "Contract Review Checklist\n\nExtract text: pdftotext contract.pdf contract.txt\nScan key clauses:\n\ngrep -i \"limitation of liability\" contract.txt\ngrep -i \"indemnification\" contract.txt\ngrep -i \"termination\" contract.txt\ngrep -i \"confidentiality\" contract.txt\ngrep -i \"governing law\" contract.txt\n\n\nExtract monetary terms: grep -E \"\\$[0-9,]+\" contract.txt\nFlag deadlines: grep -i \"within [0-9]+ days\\|business days\\|calendar days\" contract.txt\n\nRedline Workflow\n\nConvert both versions: pandoc original.docx -t plain -o original.txt && pandoc revised.docx -t plain -o revised.txt\nGenerate diff: diff -u original.txt revised.txt > changes.diff\nSide-by-side: diff -y original.txt revised.txt | less\n\nDiscovery Review\n\nExtract all PDFs: for pdf in discovery/*.pdf; do pdftotext \"$pdf\" \"${pdf%.pdf}.txt\"; done\nSearch across all docs: grep -ri \"responsive term\" discovery/*.txt\nGenerate document index: ls -lh discovery/*.pdf > document_index.txt\n\nDue Diligence Package Review\n\nExtract all docs: find diligence/ -name \"*.pdf\" -exec pdftotext {} \\;\nSearch for red flags: grep -ri \"litigation\\|breach\\|default\\|bankruptcy\" diligence/*.txt\nExtract unique dates: grep -Eroh \"[0-9]{1,2}/[0-9]{1,2}/[0-9]{4}\" diligence/*.txt | sort -u\n\nBrief / Motion Citation Check\n\nExtract citations: grep -E \"[0-9]+ [A-Z]\\.[A-Za-z0-9.]+ [0-9]+\" brief.txt\nCross-reference ToA: diff <(grep -oE \"[0-9]+ [A-Z]\\.\\S+ [0-9]+\" brief.txt | sort -u) <(sort toa.txt)"
      },
      {
        "title": "Notes",
        "body": "All processing runs locally—no cloud uploads—so client confidentiality is preserved\nConvert proprietary formats (DOCX, DOC) to plain text via pandoc before analysis\nUse wdiff for word-level comparison: install via brew install wdiff\nCombine with gog skill for Google Workspace integration (Drive, Gmail, Sheets)\nConfirm with supervising attorney before automated batch operations on case files\nFor OCR on scanned PDFs, install tesseract: brew install tesseract"
      },
      {
        "title": "Security & Ethics Reminders",
        "body": "Verify all OCR-extracted text for accuracy before relying on it in filings\nMaintain privilege logs when processing communications\nUse redaction tools for PII before document production\nComply with court e-discovery orders, ESI protocols, and local rules\nKeep audit trails of all document processing for chain-of-custody challenges\nNever transmit client data to external services without written consent"
      }
    ],
    "body": "lawclaw\n\nDrop a contract, get answers.\n\nlawclaw tears through legal documents the way you wish your associates would—fast, thorough, and without missing the indemnification clause buried on page 47. It extracts text from PDFs, flags key clauses, generates redline comparisons, validates citations, and searches entire discovery sets for the one sentence that wins your case.\n\nEverything runs locally on your machine. No uploads, no third-party servers, no risk to attorney-client privilege. Just you, your terminal, and a very sharp claw.\n\nWho it's for: Attorneys, paralegals, and legal ops teams doing contract review, litigation support, due diligence, e-discovery, or brief-writing.\n\nWhat it replaces: Hours of Ctrl+F across dozens of PDFs.\n\nCore Capabilities\n\nDocument Analysis\n\nExtract text from legal PDFs: pdftotext <file.pdf> <output.txt>\nSearch for specific clauses: grep -i \"indemnification\\|liability\\|warranty\" contract.txt\nWord count for billing: wc -w document.txt\nExtract metadata: pdfinfo <file.pdf>\n\nContract Clause Extraction Use grep with regex to find common clauses:\n\nIndemnification: grep -i \"indemnif\\|hold harmless\" contract.txt\nTermination: grep -i \"terminat\\|cancellation\" contract.txt -A 3\nConfidentiality: grep -i \"confidential\\|proprietary\\|NDA\" contract.txt -A 3\nForce majeure: grep -i \"force majeure\\|act of god\" contract.txt -A 3\nJurisdiction: grep -i \"jurisdiction\\|venue\\|governing law\" contract.txt -A 2\nArbitration: grep -i \"arbitration\\|dispute resolution\" contract.txt -A 3\nNon-compete: grep -i \"non-compete\\|noncompete\\|restrictive covenant\" contract.txt -A 3\nAssignment: grep -i \"assign\\|transfer\\|delegate\" contract.txt -A 2\n\nRedline / Comparison\n\nCompare two versions: diff -u original.txt revised.txt > redline.diff\nSide-by-side view: diff -y original.txt revised.txt | less\nWord-level diff: wdiff original.txt revised.txt > changes.txt\nConvert Word to text first: pandoc contract.docx -t plain -o contract.txt\n\nCitation and Reference Checking\n\nFind case citations: grep -E \"[0-9]+ [A-Z]\\.[A-Za-z0-9.]+ [0-9]+\" brief.txt\nFind U.S. Code refs: grep -E \"[0-9]+ U\\.S\\.C\\. § [0-9]+\" document.txt\nFind CFR refs: grep -E \"[0-9]+ C\\.F\\.R\\. § [0-9]+\" document.txt\nExtract footnotes: grep -E \"\\[[0-9]+\\]\" brief.txt\nFind Bluebook short cites: grep -E \"[A-Z][a-z]+, [0-9]+ [A-Z]\\.\" brief.txt\n\nDocument Organization\n\nFind specific file types: find . -name \"*.pdf\" -type f\nSearch within discovery docs: grep -r \"key term\" ./discovery/\nList recent modifications: find . -name \"*.pdf\" -mtime -7 -ls\nBatch rename exhibits: for f in *.pdf; do mv \"$f\" \"Exhibit_${f}\"; done\n\nDiscovery Support\n\nCount pages in PDF: pdfinfo document.pdf | grep Pages\nBatch convert PDFs: for f in *.pdf; do pdftotext \"$f\" \"${f%.pdf}.txt\"; done\nCreate production log: ls -lh *.pdf > production_log.txt\nSearch Bates numbers: grep -r \"PROD[0-9]\\{6\\}\" ./documents/\n\nDue Diligence\n\nScan for key terms: grep -i \"material adverse\\|intellectual property\\|pending litigation\" diligence/*.txt\nExtract dates: grep -E \"[0-9]{1,2}/[0-9]{1,2}/[0-9]{4}\" contract.txt\nFind monetary amounts: grep -E \"\\$[0-9,]+(\\.[0-9]{2})?\" agreement.txt\nIdentify parties: grep -E \"WHEREAS|Party|Seller|Buyer|Lessor|Lessee\" contract.txt\n\nDeposition / Transcript Analysis\n\nSearch testimony: grep -i \"Q\\.\" deposition.txt | grep -i \"keyword\"\nExtract witness answers: grep \"A\\.\" deposition.txt -A 2\nCount pages/lines: wc -l transcript.txt\n\nPrivilege Log Support\n\nGenerate file list: find ./documents -type f -exec ls -lh {} \\; > privilege_log.csv\nSearch for privileged terms: grep -ri \"attorney-client\\|work product\" ./emails/\nTag privileged docs: grep -rli \"attorney-client\" ./emails/ > privileged_files.txt\nCommon Workflows\n\nContract Review Checklist\n\nExtract text: pdftotext contract.pdf contract.txt\nScan key clauses:\ngrep -i \"limitation of liability\" contract.txt\ngrep -i \"indemnification\" contract.txt\ngrep -i \"termination\" contract.txt\ngrep -i \"confidentiality\" contract.txt\ngrep -i \"governing law\" contract.txt\nExtract monetary terms: grep -E \"\\$[0-9,]+\" contract.txt\nFlag deadlines: grep -i \"within [0-9]+ days\\|business days\\|calendar days\" contract.txt\n\nRedline Workflow\n\nConvert both versions: pandoc original.docx -t plain -o original.txt && pandoc revised.docx -t plain -o revised.txt\nGenerate diff: diff -u original.txt revised.txt > changes.diff\nSide-by-side: diff -y original.txt revised.txt | less\n\nDiscovery Review\n\nExtract all PDFs: for pdf in discovery/*.pdf; do pdftotext \"$pdf\" \"${pdf%.pdf}.txt\"; done\nSearch across all docs: grep -ri \"responsive term\" discovery/*.txt\nGenerate document index: ls -lh discovery/*.pdf > document_index.txt\n\nDue Diligence Package Review\n\nExtract all docs: find diligence/ -name \"*.pdf\" -exec pdftotext {} \\;\nSearch for red flags: grep -ri \"litigation\\|breach\\|default\\|bankruptcy\" diligence/*.txt\nExtract unique dates: grep -Eroh \"[0-9]{1,2}/[0-9]{1,2}/[0-9]{4}\" diligence/*.txt | sort -u\n\nBrief / Motion Citation Check\n\nExtract citations: grep -E \"[0-9]+ [A-Z]\\.[A-Za-z0-9.]+ [0-9]+\" brief.txt\nCross-reference ToA: diff <(grep -oE \"[0-9]+ [A-Z]\\.\\S+ [0-9]+\" brief.txt | sort -u) <(sort toa.txt)\nNotes\nAll processing runs locally—no cloud uploads—so client confidentiality is preserved\nConvert proprietary formats (DOCX, DOC) to plain text via pandoc before analysis\nUse wdiff for word-level comparison: install via brew install wdiff\nCombine with gog skill for Google Workspace integration (Drive, Gmail, Sheets)\nConfirm with supervising attorney before automated batch operations on case files\nFor OCR on scanned PDFs, install tesseract: brew install tesseract\nSecurity & Ethics Reminders\nVerify all OCR-extracted text for accuracy before relying on it in filings\nMaintain privilege logs when processing communications\nUse redaction tools for PII before document production\nComply with court e-discovery orders, ESI protocols, and local rules\nKeep audit trails of all document processing for chain-of-custody challenges\nNever transmit client data to external services without written consent"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jagadeeshmurali-coder/lawclaw",
    "publisherUrl": "https://clawhub.ai/jagadeeshmurali-coder/lawclaw",
    "owner": "jagadeeshmurali-coder",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/lawclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/lawclaw",
    "agentUrl": "https://openagent3.xyz/skills/lawclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/lawclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/lawclaw/agent.md"
  }
}