{ "schemaVersion": "1.0", "item": { "slug": "finance-skill", "name": "Finance Skill", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/safaiyeh/finance-skill", "canonicalUrl": "https://clawhub.ai/safaiyeh/finance-skill", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/finance-skill", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=finance-skill", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "scripts/add-transactions.sh", "scripts/query.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/finance-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/finance-skill", "agentPageUrl": "https://openagent3.xyz/skills/finance-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/finance-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/finance-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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Finance Skill", "body": "Personal finance memory layer. Parse statements, store transactions, query spending." }, { "title": "Data Location", "body": "Transactions: ~/.openclaw/workspace/finance/transactions.json\nRaw statements: ~/.openclaw/workspace/finance/statements/\n\nStorage convention: OpenClaw workspace (~/.openclaw/workspace/) is the standard location for persistent user data. This matches where session-memory and other hooks store agent data. Credentials/config would go in ~/.config/finance/ if needed." }, { "title": "1. Parse Statement", "body": "When user shares a statement (image or PDF):\n\n⚠️ IMPORTANT: Telegram/channel previews truncate PDFs!\nAlways extract with pypdf first to get ALL pages:\n\npython3 -c \"\nimport pypdf\nreader = pypdf.PdfReader('/path/to/statement.pdf')\nfor i, page in enumerate(reader.pages):\n print(f'=== PAGE {i+1} ===')\n print(page.extract_text())\n\"\n\nThen parse the full text output:\n\nExtract transactions from ALL pages\nReturn JSON array: [{date, merchant, amount, category}, ...]\nRun scripts/add-transactions.sh to append to store\nVerify total matches statement (sum of expenses should equal \"Total purchases\")\n\nExtraction format:\n\nEach transaction: {\"date\": \"YYYY-MM-DD\", \"merchant\": \"name\", \"amount\": -XX.XX, \"category\": \"food|transport|shopping|bills|entertainment|health|travel|other\"}\nNegative = expense, positive = income/refund.\n\nCategories:\n\nfood: restaurants, groceries, coffee, fast food\ntransport: Waymo, Uber, gas, public transit\nshopping: retail, online purchases\nbills: utilities, subscriptions\nentertainment: movies, concerts, theme parks\nhealth: pharmacy, doctors\ntravel: hotels, flights" }, { "title": "2. Query Transactions", "body": "User asks about spending → read transactions.json → filter/aggregate → answer\n\nExample queries:\n\n\"How much did I spend last month?\" → sum all negative amounts in date range\n\"What did I spend on food?\" → filter by category\n\"Show my biggest expenses\" → sort by amount" }, { "title": "3. Add Manual Transaction", "body": "User says \"I spent $X at Y\" → append to transactions.json" }, { "title": "File Format", "body": "{\n \"transactions\": [\n {\n \"id\": \"uuid\",\n \"date\": \"2026-02-01\",\n \"merchant\": \"Whole Foods\",\n \"amount\": -87.32,\n \"category\": \"food\",\n \"source\": \"statement-2026-01.pdf\",\n \"added\": \"2026-02-09T19:48:00Z\"\n }\n ],\n \"accounts\": [\n {\n \"id\": \"uuid\",\n \"name\": \"Coinbase Card\",\n \"type\": \"credit\",\n \"lastUpdated\": \"2026-02-09T19:48:00Z\"\n }\n ]\n}" }, { "title": "Usage Flow", "body": "User: shares statement image\nAgent: extracts transactions via vision, confirms count\nAgent: runs add script to store\nUser: \"how much did I spend on food?\"\nAgent: reads store, filters, answers" }, { "title": "Dependencies", "body": "jq — for JSON transaction storage and querying (apt install jq / brew install jq)\npypdf — for full PDF text extraction (pip3 install pypdf)" }, { "title": "Lessons Learned", "body": "Telegram truncates PDF previews — always use pypdf to get all pages\nVerify totals — sum extracted expenses and compare to statement total before importing\nCoinbase Card — no Plaid support, statement upload only" }, { "title": "Future: Plaid Integration", "body": "Add finance_connect tool for Plaid OAuth flow\nAuto-sync transactions from connected banks\nSame query interface, different data source" } ], "body": "Finance Skill\n\nPersonal finance memory layer. Parse statements, store transactions, query spending.\n\nData Location\nTransactions: ~/.openclaw/workspace/finance/transactions.json\nRaw statements: ~/.openclaw/workspace/finance/statements/\n\nStorage convention: OpenClaw workspace (~/.openclaw/workspace/) is the standard location for persistent user data. This matches where session-memory and other hooks store agent data. Credentials/config would go in ~/.config/finance/ if needed.\n\nTools\n1. Parse Statement\n\nWhen user shares a statement (image or PDF):\n\n⚠️ IMPORTANT: Telegram/channel previews truncate PDFs! Always extract with pypdf first to get ALL pages:\n\npython3 -c \"\nimport pypdf\nreader = pypdf.PdfReader('/path/to/statement.pdf')\nfor i, page in enumerate(reader.pages):\n print(f'=== PAGE {i+1} ===')\n print(page.extract_text())\n\"\n\n\nThen parse the full text output:\n\nExtract transactions from ALL pages\nReturn JSON array: [{date, merchant, amount, category}, ...]\nRun scripts/add-transactions.sh to append to store\nVerify total matches statement (sum of expenses should equal \"Total purchases\")\n\nExtraction format:\n\nEach transaction: {\"date\": \"YYYY-MM-DD\", \"merchant\": \"name\", \"amount\": -XX.XX, \"category\": \"food|transport|shopping|bills|entertainment|health|travel|other\"}\nNegative = expense, positive = income/refund.\n\n\nCategories:\n\nfood: restaurants, groceries, coffee, fast food\ntransport: Waymo, Uber, gas, public transit\nshopping: retail, online purchases\nbills: utilities, subscriptions\nentertainment: movies, concerts, theme parks\nhealth: pharmacy, doctors\ntravel: hotels, flights\n2. Query Transactions\n\nUser asks about spending → read transactions.json → filter/aggregate → answer\n\nExample queries:\n\n\"How much did I spend last month?\" → sum all negative amounts in date range\n\"What did I spend on food?\" → filter by category\n\"Show my biggest expenses\" → sort by amount\n3. Add Manual Transaction\n\nUser says \"I spent $X at Y\" → append to transactions.json\n\nFile Format\n{\n \"transactions\": [\n {\n \"id\": \"uuid\",\n \"date\": \"2026-02-01\",\n \"merchant\": \"Whole Foods\",\n \"amount\": -87.32,\n \"category\": \"food\",\n \"source\": \"statement-2026-01.pdf\",\n \"added\": \"2026-02-09T19:48:00Z\"\n }\n ],\n \"accounts\": [\n {\n \"id\": \"uuid\",\n \"name\": \"Coinbase Card\",\n \"type\": \"credit\",\n \"lastUpdated\": \"2026-02-09T19:48:00Z\"\n }\n ]\n}\n\nUsage Flow\nUser: shares statement image\nAgent: extracts transactions via vision, confirms count\nAgent: runs add script to store\nUser: \"how much did I spend on food?\"\nAgent: reads store, filters, answers\nDependencies\njq — for JSON transaction storage and querying (apt install jq / brew install jq)\npypdf — for full PDF text extraction (pip3 install pypdf)\nLessons Learned\nTelegram truncates PDF previews — always use pypdf to get all pages\nVerify totals — sum extracted expenses and compare to statement total before importing\nCoinbase Card — no Plaid support, statement upload only\nFuture: Plaid Integration\nAdd finance_connect tool for Plaid OAuth flow\nAuto-sync transactions from connected banks\nSame query interface, different data source" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/safaiyeh/finance-skill", "publisherUrl": "https://clawhub.ai/safaiyeh/finance-skill", "owner": "safaiyeh", "version": "0.1.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/finance-skill", "downloadUrl": "https://openagent3.xyz/downloads/finance-skill", "agentUrl": "https://openagent3.xyz/skills/finance-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/finance-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/finance-skill/agent.md" } }