{ "schemaVersion": "1.0", "item": { "slug": "jmail", "name": "Jmail World", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/fabiantaboo/jmail", "canonicalUrl": "https://clawhub.ai/fabiantaboo/jmail", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/jmail", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=jmail", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/api-docs.md", "scripts/jmail-duckdb.sh", "scripts/jmail-search.sh" ], "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/jmail" }, "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/jmail", "agentPageUrl": "https://openagent3.xyz/skills/jmail/agent", "manifestUrl": "https://openagent3.xyz/skills/jmail/agent.json", "briefUrl": "https://openagent3.xyz/skills/jmail/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": "jmail-world — Epstein Archive Search & Analysis", "body": "Search and analyze Jeffrey Epstein's email archive, iMessages, documents, photos, and people on jmail.world." }, { "title": "When to Use", "body": "Researching Epstein connections and communications\nFinding emails between specific people\nExploring iMessage conversations\nAnalyzing communication networks and timelines\nLooking up people identified in photos\nSearching documents (DOJ releases, court records)" }, { "title": "1. Web Search API (quick lookups)", "body": "GET https://jmail.world/api/emails/search?q=QUERY&limit=50&page=1&source=all&from=NAME\n\nNo auth needed. Use web_fetch or curl. Good for quick keyword searches." }, { "title": "2. DuckDB + Parquet (deep analysis)", "body": "All datasets served as static Parquet files from https://data.jmail.world/v1/. No API key, no rate limit, no auth.\n\nUse the included scripts:\n\n# Full-text email search (Web API)\nbash scripts/jmail-search.sh \"query text\"\nbash scripts/jmail-search.sh \"scopolamine\" --from \"Epstein\" --limit 20\n\n# DuckDB queries (local Parquet, no rate limits)\nbash scripts/jmail-duckdb.sh search \"flight manifest\"\nbash scripts/jmail-duckdb.sh person \"Ghislaine Maxwell\"\nbash scripts/jmail-duckdb.sh imessages \"ghislaine-maxwell\"\nbash scripts/jmail-duckdb.sh imessage-search \"AfD\"\nbash scripts/jmail-duckdb.sh imessage-search \"Merkel\" --from \"Bannon\"\nbash scripts/jmail-duckdb.sh imessage-list\nbash scripts/jmail-duckdb.sh network \"Bill Clinton\"\nbash scripts/jmail-duckdb.sh timeline \"2005-01-01\" \"2005-12-31\"\nbash scripts/jmail-duckdb.sh top-senders\nbash scripts/jmail-duckdb.sh people\nbash scripts/jmail-duckdb.sh documents \"flight\"\nbash scripts/jmail-duckdb.sh photos \"person-name\"\nbash scripts/jmail-duckdb.sh photo-search \"pool\"\nbash scripts/jmail-duckdb.sh photo-download \"EFTA00000002-0.png\" ./output\nbash scripts/jmail-duckdb.sh download \"EFTA02406146\"\nbash scripts/jmail-duckdb.sh download \"HOUSE_OVERSIGHT_034601\"\nbash scripts/jmail-duckdb.sh stars" }, { "title": "Available Datasets", "body": "DatasetURLSizeRecordsEmails (full)emails.parquet334MB1.78MEmails (slim)emails-slim.parquet41MB1.78MDocumentsdocuments.parquet25MB1.41MPhotosphotos.parquet~1MB18KPeoplepeople.parquet<100KB473Photo Facesphoto_faces.parquet<100KB975iMessage Conversationsimessage_conversations.parquet——iMessage Messagesimessage_messages.parquet——Star Countsstar_counts.parquet~2MB414KRelease Batchesrelease_batches.parquet<10KB—\n\nAll under https://data.jmail.world/v1/." }, { "title": "Email Columns (slim)", "body": "id, doc_id, sender, subject, to_recipients (json), cc_recipients (json), bcc_recipients (json), sent_at (timestamp), account_email, email_drop_id, epstein_is_sender (bool)" }, { "title": "Email Additional (full)", "body": "content_markdown, content_html, attachments (int)" }, { "title": "iMessage Conversations", "body": "id, slug, name, bio, photo, last_message, last_message_time, pinned, confirmed, source_files (json), message_count" }, { "title": "iMessage Messages", "body": "id, conversation_slug, message_index, text, sender (\"me\" = Epstein, \"them\" = contact), time, timestamp, source_file, sender_name" }, { "title": "People", "body": "id, name, source, photo_count" }, { "title": "Documents", "body": "id, source, release_batch, original_filename, page_count, size, document_description, has_thumbnail" }, { "title": "Web Pages (browser needed)", "body": "/person/SLUG — Person profile\n/flights — Flight records\n/photos — Photo browser\n/drive/new-only — New documents\n/topic/SLUG — Topic pages" }, { "title": "Document Full-Text Search", "body": "Documents have sharded full-text files (large downloads):\n\ndocuments-full/VOL00008.parquet — DOJ Volume 8\ndocuments-full/VOL00009.parquet — DOJ Volume 9\ndocuments-full/VOL00010.parquet — DOJ Volume 10\ndocuments-full/DataSet11.parquet — DOJ Dataset 11\ndocuments-full/other.parquet — House Oversight, court records\n\nQuery with DuckDB:\n\nSELECT id, original_filename, extracted_text\nFROM read_parquet('https://data.jmail.world/v1/documents-full/other.parquet')\nWHERE extracted_text ILIKE '%rothschild%'\nLIMIT 10;" }, { "title": "Photo Columns (full schema)", "body": "id, source, release_batch, original_filename, content_type (MIME), width (px), height (px), image_description (AI-generated)\n\nSearch photos by description:\n\nSELECT original_filename, image_description, width, height\nFROM read_parquet('https://data.jmail.world/v1/photos.parquet')\nWHERE image_description ILIKE '%pool%'\nLIMIT 20;" }, { "title": "Universal Download (any document, email, or photo)", "body": "# Download by document ID — auto-detects type and source\nbash scripts/jmail-duckdb.sh download \"EFTA02406146\" # DOJ email PDF\nbash scripts/jmail-duckdb.sh download \"HOUSE_OVERSIGHT_034601\" # House Oversight photo\nbash scripts/jmail-duckdb.sh download \"COURT_giuffre-115cv07433_1\" # Court document\nbash scripts/jmail-duckdb.sh download \"vol00009-efta00462570-pdf\" # DOJ volume scan\nbash scripts/jmail-duckdb.sh download \"EFTA02406146\" ./output-dir # Custom output dir\n\nSupported sources:\n\nID PatternTypeFormatEFTA*DOJ emails & photosPDFvol*DOJ volume scansPDFHOUSE_OVERSIGHT_*House Oversight photosJPG (direct)COURT_giuffre*Giuffre court docsPDF" }, { "title": "Photo Search & Download", "body": "# Search photos by AI-generated description\nbash scripts/jmail-duckdb.sh photo-search \"swimming pool\"\nbash scripts/jmail-duckdb.sh photo-search \"forced entry\"\n\n# Download a specific photo (DOJ: extracts PNG from PDF, HO: direct JPG)\nbash scripts/jmail-duckdb.sh photo-download \"EFTA00000002-0.png\"\nbash scripts/jmail-duckdb.sh photo-download \"HOUSE_OVERSIGHT_034601.JPG\" ./output\n\nDOJ photos are stored as single-page PDFs — the download command automatically extracts the embedded image as PNG using pdfimages. House Oversight photos are direct JPGs. If pdfimages is not installed, DOJ photos are saved as PDF." }, { "title": "Security", "body": "SQL injection prevention: All user input is whitelist-sanitized (alphanumeric + safe chars only). SQL meta-characters, operators, and keywords are stripped before query construction.\nPath traversal prevention: Parquet filenames and document IDs are validated against strict patterns before use in file operations.\nRead-only queries: All DuckDB operations are SELECT on read_parquet() — no writes, no code execution, no network access beyond the cached Parquet files.\nData source: All data comes from jmail.world's public Parquet files and assets.getkino.com (DOJ document mirror). No private APIs or credentials involved." }, { "title": "Requirements", "body": "DuckDB (duckdb CLI) — must be installed manually (apt install duckdb / brew install duckdb / duckdb.org)\ncurl — for web search API and downloading Parquet files\npython3 — for URL encoding in search script\npdfimages (optional, for photo-download PNG extraction) — apt install poppler-utils\njq (optional, for JSON formatting)" }, { "title": "References", "body": "Official Docs\nDocs Index for LLMs\nAPI Reference\nDuckDB Examples\nPython Client (external) — not bundled, see official docs\nDatasets & URLs" } ], "body": "jmail-world — Epstein Archive Search & Analysis\n\nSearch and analyze Jeffrey Epstein's email archive, iMessages, documents, photos, and people on jmail.world.\n\nWhen to Use\nResearching Epstein connections and communications\nFinding emails between specific people\nExploring iMessage conversations\nAnalyzing communication networks and timelines\nLooking up people identified in photos\nSearching documents (DOJ releases, court records)\nData Access — Two Methods\n1. Web Search API (quick lookups)\nGET https://jmail.world/api/emails/search?q=QUERY&limit=50&page=1&source=all&from=NAME\n\n\nNo auth needed. Use web_fetch or curl. Good for quick keyword searches.\n\n2. DuckDB + Parquet (deep analysis)\n\nAll datasets served as static Parquet files from https://data.jmail.world/v1/. No API key, no rate limit, no auth.\n\nUse the included scripts:\n\n# Full-text email search (Web API)\nbash scripts/jmail-search.sh \"query text\"\nbash scripts/jmail-search.sh \"scopolamine\" --from \"Epstein\" --limit 20\n\n# DuckDB queries (local Parquet, no rate limits)\nbash scripts/jmail-duckdb.sh search \"flight manifest\"\nbash scripts/jmail-duckdb.sh person \"Ghislaine Maxwell\"\nbash scripts/jmail-duckdb.sh imessages \"ghislaine-maxwell\"\nbash scripts/jmail-duckdb.sh imessage-search \"AfD\"\nbash scripts/jmail-duckdb.sh imessage-search \"Merkel\" --from \"Bannon\"\nbash scripts/jmail-duckdb.sh imessage-list\nbash scripts/jmail-duckdb.sh network \"Bill Clinton\"\nbash scripts/jmail-duckdb.sh timeline \"2005-01-01\" \"2005-12-31\"\nbash scripts/jmail-duckdb.sh top-senders\nbash scripts/jmail-duckdb.sh people\nbash scripts/jmail-duckdb.sh documents \"flight\"\nbash scripts/jmail-duckdb.sh photos \"person-name\"\nbash scripts/jmail-duckdb.sh photo-search \"pool\"\nbash scripts/jmail-duckdb.sh photo-download \"EFTA00000002-0.png\" ./output\nbash scripts/jmail-duckdb.sh download \"EFTA02406146\"\nbash scripts/jmail-duckdb.sh download \"HOUSE_OVERSIGHT_034601\"\nbash scripts/jmail-duckdb.sh stars\n\nAvailable Datasets\nDataset\tURL\tSize\tRecords\nEmails (full)\temails.parquet\t334MB\t1.78M\nEmails (slim)\temails-slim.parquet\t41MB\t1.78M\nDocuments\tdocuments.parquet\t25MB\t1.41M\nPhotos\tphotos.parquet\t~1MB\t18K\nPeople\tpeople.parquet\t<100KB\t473\nPhoto Faces\tphoto_faces.parquet\t<100KB\t975\niMessage Conversations\timessage_conversations.parquet\t—\t—\niMessage Messages\timessage_messages.parquet\t—\t—\nStar Counts\tstar_counts.parquet\t~2MB\t414K\nRelease Batches\trelease_batches.parquet\t<10KB\t—\n\nAll under https://data.jmail.world/v1/.\n\nKey Schemas\nEmail Columns (slim)\n\nid, doc_id, sender, subject, to_recipients (json), cc_recipients (json), bcc_recipients (json), sent_at (timestamp), account_email, email_drop_id, epstein_is_sender (bool)\n\nEmail Additional (full)\n\ncontent_markdown, content_html, attachments (int)\n\niMessage Conversations\n\nid, slug, name, bio, photo, last_message, last_message_time, pinned, confirmed, source_files (json), message_count\n\niMessage Messages\n\nid, conversation_slug, message_index, text, sender (\"me\" = Epstein, \"them\" = contact), time, timestamp, source_file, sender_name\n\nPeople\n\nid, name, source, photo_count\n\nDocuments\n\nid, source, release_batch, original_filename, page_count, size, document_description, has_thumbnail\n\nWeb Pages (browser needed)\n/person/SLUG — Person profile\n/flights — Flight records\n/photos — Photo browser\n/drive/new-only — New documents\n/topic/SLUG — Topic pages\nDocument Full-Text Search\n\nDocuments have sharded full-text files (large downloads):\n\ndocuments-full/VOL00008.parquet — DOJ Volume 8\ndocuments-full/VOL00009.parquet — DOJ Volume 9\ndocuments-full/VOL00010.parquet — DOJ Volume 10\ndocuments-full/DataSet11.parquet — DOJ Dataset 11\ndocuments-full/other.parquet — House Oversight, court records\n\nQuery with DuckDB:\n\nSELECT id, original_filename, extracted_text\nFROM read_parquet('https://data.jmail.world/v1/documents-full/other.parquet')\nWHERE extracted_text ILIKE '%rothschild%'\nLIMIT 10;\n\nPhoto Columns (full schema)\n\nid, source, release_batch, original_filename, content_type (MIME), width (px), height (px), image_description (AI-generated)\n\nSearch photos by description:\n\nSELECT original_filename, image_description, width, height\nFROM read_parquet('https://data.jmail.world/v1/photos.parquet')\nWHERE image_description ILIKE '%pool%'\nLIMIT 20;\n\nDownloading Files\nUniversal Download (any document, email, or photo)\n# Download by document ID — auto-detects type and source\nbash scripts/jmail-duckdb.sh download \"EFTA02406146\" # DOJ email PDF\nbash scripts/jmail-duckdb.sh download \"HOUSE_OVERSIGHT_034601\" # House Oversight photo\nbash scripts/jmail-duckdb.sh download \"COURT_giuffre-115cv07433_1\" # Court document\nbash scripts/jmail-duckdb.sh download \"vol00009-efta00462570-pdf\" # DOJ volume scan\nbash scripts/jmail-duckdb.sh download \"EFTA02406146\" ./output-dir # Custom output dir\n\n\nSupported sources:\n\nID Pattern\tType\tFormat\nEFTA*\tDOJ emails & photos\tPDF\nvol*\tDOJ volume scans\tPDF\nHOUSE_OVERSIGHT_*\tHouse Oversight photos\tJPG (direct)\nCOURT_giuffre*\tGiuffre court docs\tPDF\nPhoto Search & Download\n# Search photos by AI-generated description\nbash scripts/jmail-duckdb.sh photo-search \"swimming pool\"\nbash scripts/jmail-duckdb.sh photo-search \"forced entry\"\n\n# Download a specific photo (DOJ: extracts PNG from PDF, HO: direct JPG)\nbash scripts/jmail-duckdb.sh photo-download \"EFTA00000002-0.png\"\nbash scripts/jmail-duckdb.sh photo-download \"HOUSE_OVERSIGHT_034601.JPG\" ./output\n\n\nDOJ photos are stored as single-page PDFs — the download command automatically extracts the embedded image as PNG using pdfimages. House Oversight photos are direct JPGs. If pdfimages is not installed, DOJ photos are saved as PDF.\n\nSecurity\nSQL injection prevention: All user input is whitelist-sanitized (alphanumeric + safe chars only). SQL meta-characters, operators, and keywords are stripped before query construction.\nPath traversal prevention: Parquet filenames and document IDs are validated against strict patterns before use in file operations.\nRead-only queries: All DuckDB operations are SELECT on read_parquet() — no writes, no code execution, no network access beyond the cached Parquet files.\nData source: All data comes from jmail.world's public Parquet files and assets.getkino.com (DOJ document mirror). No private APIs or credentials involved.\nRequirements\nDuckDB (duckdb CLI) — must be installed manually (apt install duckdb / brew install duckdb / duckdb.org)\ncurl — for web search API and downloading Parquet files\npython3 — for URL encoding in search script\npdfimages (optional, for photo-download PNG extraction) — apt install poppler-utils\njq (optional, for JSON formatting)\nReferences\nOfficial Docs\nDocs Index for LLMs\nAPI Reference\nDuckDB Examples\nPython Client (external) — not bundled, see official docs\nDatasets & URLs" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/fabiantaboo/jmail", "publisherUrl": "https://clawhub.ai/fabiantaboo/jmail", "owner": "fabiantaboo", "version": "1.6.5", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/jmail", "downloadUrl": "https://openagent3.xyz/downloads/jmail", "agentUrl": "https://openagent3.xyz/skills/jmail/agent", "manifestUrl": "https://openagent3.xyz/skills/jmail/agent.json", "briefUrl": "https://openagent3.xyz/skills/jmail/agent.md" } }