{ "schemaVersion": "1.0", "item": { "slug": "banking", "name": "Banking", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/ivangdavila/banking", "canonicalUrl": "https://clawhub.ai/ivangdavila/banking", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/banking", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=banking", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "compliance-scope.md", "customer-messaging.md", "incident-response.md", "intake-checklist.md", "memory-template.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/banking" }, "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/banking", "agentPageUrl": "https://openagent3.xyz/skills/banking/agent", "manifestUrl": "https://openagent3.xyz/skills/banking/agent.json", "briefUrl": "https://openagent3.xyz/skills/banking/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": "Setup", "body": "On first use, read setup.md for activation boundaries and context capture priorities." }, { "title": "When to Use", "body": "Use this skill for banking operations support: account onboarding workflows, payment operations, reconciliation triage, fraud incidents, and customer communication that must stay clear and compliant." }, { "title": "Architecture", "body": "Memory lives in ~/banking/. See memory-template.md for structure and status fields.\n\n~/banking/\n|-- memory.md # Status, activation scope, operating context\n|-- incidents.md # Open fraud and operations incidents\n|-- payment-controls.md # Verified controls by rail and account type\n`-- communication-notes.md # Approved customer messaging patterns" }, { "title": "Quick Reference", "body": "Use the smallest relevant file for the task to keep decisions precise under time pressure.\n\nTopicFileSetup processsetup.mdMemory templatememory-template.mdRequest intake and classificationintake-checklist.mdPayment rails and controlspayment-ops.mdFraud and outage handlingincident-response.mdCustomer-safe wordingcustomer-messaging.mdRegulatory and legal boundariescompliance-scope.md" }, { "title": "1. Classify the Request Before Giving Steps", "body": "Label each request first: onboarding, payment execution, reconciliation, fraud, dispute, or compliance question.\nIf the category is unclear, ask one short clarification before proposing actions." }, { "title": "2. Confirm Jurisdiction and Account Context", "body": "Capture country or region, customer type (consumer or business), and account type before compliance-sensitive guidance.\nNever give jurisdiction-specific legal conclusions without explicit location context." }, { "title": "3. Use Control-First Payment Guidance", "body": "For every transfer path, verify account ownership, amount, cutoff timing, approval threshold, and rollback options.\nIf any required control is unknown, pause execution advice and request the missing control." }, { "title": "4. Treat Incidents as Containment Then Recovery", "body": "For suspected fraud or unauthorized activity, prioritize containment actions before root-cause analysis.\nKeep incident actions timestamped and reversible where possible." }, { "title": "5. Keep Communication Clear, Neutral, and Accurate", "body": "Use plain language that states current status, next step, owner, and ETA window.\nAvoid guarantees, blame language, or speculative claims about pending investigations." }, { "title": "6. Keep Memory Actionable and Verifiable", "body": "Record only durable context: operating boundaries, approved controls, known constraints, and recurring failure patterns.\nDo not store full account numbers, authentication data, or sensitive personal identifiers in memory notes." }, { "title": "7. Escalate High-Risk or Restricted Requests", "body": "Escalate when requests involve sanctions, KYC circumvention, legal interpretation, or irreversible fund movement without controls.\nRefuse instructions that circumvent required approvals, customer consent, or regulatory safeguards." }, { "title": "Common Traps", "body": "Starting with product explanations instead of request classification -> slower resolution and wrong workflow.\nGiving transfer steps before confirming controls -> elevated operational and fraud risk.\nMixing legal interpretation with operations guidance -> compliance exposure and user confusion.\nResponding to incidents with generic advice only -> delayed containment and larger losses.\nUsing absolute language such as \"guaranteed\" or \"always\" -> credibility and regulatory risk.\nLogging sensitive data in memory notes -> avoidable privacy and security exposure." }, { "title": "Data Storage", "body": "Local notes only in ~/banking/ (memory file, incident notes, and control references).\nKeep stored content minimal and operational: controls, status, and decisions.\nDo not store full account numbers, authentication data, or unnecessary personal identifiers." }, { "title": "Security & Privacy", "body": "Data that leaves your machine:\n\nNone by default. This skill is instruction and workflow guidance only.\n\nData that stays local:\n\nOperational context and notes in ~/banking/.\n\nThis skill does NOT:\n\nAccess bank portals or execute fund transfers automatically.\nRequest undeclared network calls.\nStore authentication data or full account numbers in memory files.\nModify files outside ~/banking/ for storage.\nNEVER modifies its own skill definition file." }, { "title": "Related Skills", "body": "Install with clawhub install if user confirms:\n\npayments - Payment workflows and transaction operations patterns.\naccounting - Ledger, reconciliation, and financial reporting support.\ninvoice - Invoice lifecycle workflows and settlement tracking.\nmoney - Personal money management and budgeting fundamentals.\ninvest - Investment analysis workflows for portfolio decisions." }, { "title": "Feedback", "body": "If useful: clawhub star banking\nStay updated: clawhub sync" } ], "body": "Setup\n\nOn first use, read setup.md for activation boundaries and context capture priorities.\n\nWhen to Use\n\nUse this skill for banking operations support: account onboarding workflows, payment operations, reconciliation triage, fraud incidents, and customer communication that must stay clear and compliant.\n\nArchitecture\n\nMemory lives in ~/banking/. See memory-template.md for structure and status fields.\n\n~/banking/\n|-- memory.md # Status, activation scope, operating context\n|-- incidents.md # Open fraud and operations incidents\n|-- payment-controls.md # Verified controls by rail and account type\n`-- communication-notes.md # Approved customer messaging patterns\n\nQuick Reference\n\nUse the smallest relevant file for the task to keep decisions precise under time pressure.\n\nTopic\tFile\nSetup process\tsetup.md\nMemory template\tmemory-template.md\nRequest intake and classification\tintake-checklist.md\nPayment rails and controls\tpayment-ops.md\nFraud and outage handling\tincident-response.md\nCustomer-safe wording\tcustomer-messaging.md\nRegulatory and legal boundaries\tcompliance-scope.md\nCore Rules\n1. Classify the Request Before Giving Steps\nLabel each request first: onboarding, payment execution, reconciliation, fraud, dispute, or compliance question.\nIf the category is unclear, ask one short clarification before proposing actions.\n2. Confirm Jurisdiction and Account Context\nCapture country or region, customer type (consumer or business), and account type before compliance-sensitive guidance.\nNever give jurisdiction-specific legal conclusions without explicit location context.\n3. Use Control-First Payment Guidance\nFor every transfer path, verify account ownership, amount, cutoff timing, approval threshold, and rollback options.\nIf any required control is unknown, pause execution advice and request the missing control.\n4. Treat Incidents as Containment Then Recovery\nFor suspected fraud or unauthorized activity, prioritize containment actions before root-cause analysis.\nKeep incident actions timestamped and reversible where possible.\n5. Keep Communication Clear, Neutral, and Accurate\nUse plain language that states current status, next step, owner, and ETA window.\nAvoid guarantees, blame language, or speculative claims about pending investigations.\n6. Keep Memory Actionable and Verifiable\nRecord only durable context: operating boundaries, approved controls, known constraints, and recurring failure patterns.\nDo not store full account numbers, authentication data, or sensitive personal identifiers in memory notes.\n7. Escalate High-Risk or Restricted Requests\nEscalate when requests involve sanctions, KYC circumvention, legal interpretation, or irreversible fund movement without controls.\nRefuse instructions that circumvent required approvals, customer consent, or regulatory safeguards.\nCommon Traps\nStarting with product explanations instead of request classification -> slower resolution and wrong workflow.\nGiving transfer steps before confirming controls -> elevated operational and fraud risk.\nMixing legal interpretation with operations guidance -> compliance exposure and user confusion.\nResponding to incidents with generic advice only -> delayed containment and larger losses.\nUsing absolute language such as \"guaranteed\" or \"always\" -> credibility and regulatory risk.\nLogging sensitive data in memory notes -> avoidable privacy and security exposure.\nData Storage\nLocal notes only in ~/banking/ (memory file, incident notes, and control references).\nKeep stored content minimal and operational: controls, status, and decisions.\nDo not store full account numbers, authentication data, or unnecessary personal identifiers.\nSecurity & Privacy\n\nData that leaves your machine:\n\nNone by default. This skill is instruction and workflow guidance only.\n\nData that stays local:\n\nOperational context and notes in ~/banking/.\n\nThis skill does NOT:\n\nAccess bank portals or execute fund transfers automatically.\nRequest undeclared network calls.\nStore authentication data or full account numbers in memory files.\nModify files outside ~/banking/ for storage.\nNEVER modifies its own skill definition file.\nRelated Skills\n\nInstall with clawhub install if user confirms:\n\npayments - Payment workflows and transaction operations patterns.\naccounting - Ledger, reconciliation, and financial reporting support.\ninvoice - Invoice lifecycle workflows and settlement tracking.\nmoney - Personal money management and budgeting fundamentals.\ninvest - Investment analysis workflows for portfolio decisions.\nFeedback\nIf useful: clawhub star banking\nStay updated: clawhub sync" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/banking", "publisherUrl": "https://clawhub.ai/ivangdavila/banking", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/banking", "downloadUrl": "https://openagent3.xyz/downloads/banking", "agentUrl": "https://openagent3.xyz/skills/banking/agent", "manifestUrl": "https://openagent3.xyz/skills/banking/agent.json", "briefUrl": "https://openagent3.xyz/skills/banking/agent.md" } }