{ "schemaVersion": "1.0", "item": { "slug": "analytics-and-advisory-intelligence", "name": "Analytics And Advisory Intelligence", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/satoshistackalotto/analytics-and-advisory-intelligence", "canonicalUrl": "https://clawhub.ai/satoshistackalotto/analytics-and-advisory-intelligence", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/analytics-and-advisory-intelligence", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=analytics-and-advisory-intelligence", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "EVALS.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/analytics-and-advisory-intelligence" }, "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/analytics-and-advisory-intelligence", "agentPageUrl": "https://openagent3.xyz/skills/analytics-and-advisory-intelligence/agent", "manifestUrl": "https://openagent3.xyz/skills/analytics-and-advisory-intelligence/agent.json", "briefUrl": "https://openagent3.xyz/skills/analytics-and-advisory-intelligence/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": "Analytics and Advisory Intelligence", "body": "The previous 17 skills process, file, store, and protect. This skill thinks. It reads across all the data the system has built up and asks: what does this mean? What should the accountant know that they have not thought to ask?\n\nAn accountant managing 40 clients cannot spot a VAT liability trend building across one client's 12 months of data while simultaneously processing another client's payroll and preparing a third client's annual tax return. This skill does the cross-sectional, longitudinal reading that busy humans cannot. It surfaces the finding. The accountant decides what to do with it.\n\nThis skill is purely advisory. It reads, analyses, and reports. It never takes action, never modifies client records, and never submits anything. Every insight it surfaces is a prompt for human judgement, not a trigger for automated action." }, { "title": "Setup", "body": "export OPENCLAW_DATA_DIR=\"/data\"\nwhich jq || sudo apt install jq\n\nNo external credentials required. Analyzes financial data from local files to generate trend reports and advisory insights." }, { "title": "Core Philosophy", "body": "Proactive, Not Reactive: The system already handles reactive work. This skill looks ahead — identifying problems before they become crises and opportunities before they are missed\nCross-Client Vision: No single-client skill can see patterns that span the portfolio. This skill aggregates anonymised data across clients to detect sector trends, identify outliers, and benchmark clients against peers\nPlain English Findings: Every output is written for accounting assistants. No statistical jargon, no unexplained numbers. Finding + evidence + suggested action\nConfidence-Rated: Every finding carries a confidence level. A pattern with three data points is labelled differently from one with 18. The accountant knows how much weight to give each insight\nRead-Only Always: This skill reads from all data sources but writes only to /data/reports/analytics/. It has no write access to /data/clients/, /data/compliance/, or any operational directory\nOvernight Operation: Heavy analysis runs outside business hours. Lightweight queries run on demand but are bounded by pre-computed daily outputs" }, { "title": "Portfolio-Level Analysis", "body": "openclaw analytics portfolio-health --all-clients --period 2026-01\nopenclaw analytics portfolio-health --all-clients --period 2026-01 --rank-by risk\nopenclaw analytics compliance-risk --all-clients --period 2026-01\nopenclaw analytics compliance-risk --all-clients --flag-high-risk\nopenclaw analytics compliance-risk --sector retail --compare-to-sector\nopenclaw analytics workload --all-clients --period 2026-01 --by-accountant\nopenclaw analytics workload --forecast --next-quarter\nopenclaw analytics benchmark --afm EL123456789 --vs-sector retail --period 2026-01\nopenclaw analytics benchmark --afm EL123456789 --vs-sector retail --last 6-months" }, { "title": "Client-Level Analysis", "body": "openclaw analytics client-risk --afm EL123456789\nopenclaw analytics client-risk --afm EL123456789 --verbose\nopenclaw analytics trends --afm EL123456789 --metric vat-liability --last 12-months\nopenclaw analytics trends --afm EL123456789 --metric gross-margin --last 6-months\nopenclaw analytics trends --afm EL123456789 --all-metrics --period 2025\nopenclaw analytics anomalies --afm EL123456789 --period 2026-01\nopenclaw analytics anomalies --afm EL123456789 --last 6-months --flag-significant\nopenclaw analytics cashflow-forecast --afm EL123456789 --horizon 3-months\nopenclaw analytics cashflow-forecast --afm EL123456789 --horizon 3-months --include-tax-payments\nopenclaw analytics tax-planning --afm EL123456789 --year 2026\nopenclaw analytics tax-planning --afm EL123456789 --year 2026 --include-scenarios" }, { "title": "Anomaly Detection", "body": "openclaw analytics supplier-overlap --all-clients --flag-unusual\nopenclaw analytics supplier-overlap --threshold 5-clients\nopenclaw analytics expense-anomalies --all-clients --period 2026-01\nopenclaw analytics expense-anomalies --afm EL123456789 --vs-prior-periods\nopenclaw analytics vat-rate-check --all-clients --period 2026-01\nopenclaw analytics vat-rate-check --afm EL123456789 --last 6-months" }, { "title": "Scheduled Reports and Advisory", "body": "openclaw analytics morning-advisory --date today\nopenclaw analytics morning-advisory --date today --high-risk-only\nopenclaw analytics monthly-report --period 2026-01 --all-clients\nopenclaw analytics monthly-report --period 2026-01 --format pdf\nopenclaw analytics quarterly-review --quarter 2026-Q1 --all-clients\nopenclaw analytics ask --query \"which clients have increasing VAT liability over the last 6 months\"\nopenclaw analytics ask --query \"which clients are at risk of not meeting their Q2 tax payment\"\nopenclaw analytics ask --query \"are there any expense categories that look unusual this month\"" }, { "title": "1. Compliance Risk Scoring", "body": "Every client receives a compliance risk score on a 1-10 scale, computed nightly. Feeds the dashboard portfolio view and morning advisory.\n\nCompliance_Risk_Score:\n inputs:\n - Late filings in the last 12 months (weight: 30%)\n - Compliance gaps currently open (weight: 25%)\n - Missing documents pending more than 14 days (weight: 20%)\n - AADE penalty history (weight: 15%)\n - Days until next deadline vs documents received (weight: 10%)\n\n score_bands:\n 1-3: \"Low risk — all obligations current, no gaps\"\n 4-6: \"Medium risk — minor gaps or historical delays\"\n 7-8: \"High risk — active gaps or recent penalties\"\n 9-10: \"Critical — immediate attention required\"\n\n output_location: \"/data/reports/analytics/{YYYY-MM-DD}_risk-scores.json\"\n refreshed: \"Nightly at 01:00 Athens time\"" }, { "title": "2. Financial Trend Analysis", "body": "Reads Skill 15 financial statement outputs across multiple periods to detect directional movement.\n\nFinancial_Trends:\n metrics_tracked:\n gross_margin:\n calculation: \"(Revenue - Cost of Sales) / Revenue\"\n alert_threshold: \"Drop of more than 5 percentage points vs same period last year\"\n finding_template: \"{Client} gross margin has fallen from {X}% to {Y}% — {delta}pp decline over {N} months. Primary driver appears to be {top expense category change}.\"\n\n vat_liability_trend:\n calculation: \"Net VAT payable per period\"\n alert_threshold: \"Increase of more than 20% vs prior 3-month average\"\n finding_template: \"{Client} VAT liability has increased {X}% over {N} months. May reflect higher turnover, a change in customer mix, or a classification issue worth reviewing.\"\n\n staff_cost_ratio:\n calculation: \"Staff costs (EGLS account 64) / Revenue\"\n alert_threshold: \"Ratio increase of more than 3 percentage points\"\n\n cash_position:\n calculation: \"Cash and bank balances (account 38) trend\"\n alert_threshold: \"Declining for 3 consecutive months\"\n finding_template: \"{Client} cash position has declined for {N} consecutive months (from EUR {X} to EUR {Y}). With a tax payment of EUR {Z} due on {date}, this warrants a cash flow conversation.\"\n\n minimum_periods_required: 3\n preferred_periods: 12\n confidence_note: \"Findings with fewer than 6 data points are marked LOW CONFIDENCE\"" }, { "title": "3. Anomaly Detection", "body": "Values statistically unusual relative to a client's own history and sector peers.\n\nAnomaly_Detection:\n methods:\n own_history_comparison:\n description: \"Value more than 2 standard deviations from client's own trailing average\"\n example: \"Electricity costs EUR 4,200 in January vs trailing 12-month average of EUR 1,800\"\n\n sector_peer_comparison:\n description: \"Value more than 1.5x or less than 0.5x the sector median for that account\"\n note: \"Sector medians computed from anonymised aggregates across the portfolio\"\n\n vat_rate_anomaly:\n description: \"Transaction classified at incorrect VAT rate based on product/service category\"\n example: \"Food product invoice at 24% rather than correct 13% reduced rate\"\n action: \"Flag for accountant review — never auto-correct\"\n\n output_fields:\n - metric: \"What was measured\"\n - actual_value: \"What was found\"\n - expected_range: \"What is normal for this client / sector\"\n - deviation: \"How far outside normal\"\n - confidence: \"HIGH / MEDIUM / LOW\"\n - suggested_action: \"Plain English recommendation\"\n - data_source: \"Which files the finding is based on\"" }, { "title": "4. Cash Flow Forecasting", "body": "Projects cash position forward 1-3 months using historical patterns and known upcoming obligations.\n\nCashflow_Forecast:\n inputs:\n known_inflows:\n - Recurring revenue based on trailing 3-month average\n - Outstanding debtor invoices from registry\n known_outflows:\n - Upcoming tax deadlines from cli-deadline-monitor\n - Recurring supplier payments from banking history\n - EFKA contributions due\n - Payroll from prior period data\n uncertainty_ranges:\n - Revenue: +/- 15% based on historical variance\n - Ad-hoc expenses: +/- 20%\n\n output:\n - Best case / expected / worst case cash position at each month end\n - Months where cash may go negative (flagged HIGH RISK)\n - Specific upcoming payments that may cause strain\n\n confidence_degradation:\n 1_month: \"HIGH confidence\"\n 2_months: \"MEDIUM confidence\"\n 3_months: \"LOW confidence — directional only\"" }, { "title": "5. Portfolio Intelligence (Cross-Client)", "body": "Aggregated across the portfolio. All cross-client aggregation is anonymised.\n\nPortfolio_Intelligence:\n sector_benchmarks:\n computed_from: \"Anonymised aggregates of all active clients per sector\"\n metrics:\n - Median gross margin by sector\n - Median staff cost ratio by sector\n - Median VAT liability as percentage of revenue by sector\n refreshed: \"Monthly — after all monthly statements are generated\"\n minimum_clients_per_sector: 3\n\n portfolio_risk_distribution:\n description: \"Distribution of risk scores across the full portfolio over time\"\n\n workload_concentration:\n description: \"Risk-weighted workload per accountant — alerts if one person carries disproportionate risk\"\n\n common_issues:\n description: \"Issues appearing across multiple clients simultaneously\"\n examples:\n - \"6 retail clients showing declining margins — possible sector-wide trend\"\n - \"3 clients using the same supplier showing unusual payment patterns\"\n - \"4 clients with outstanding document requests over 21 days\"" }, { "title": "Morning Advisory Output Format", "body": "Pre-computed overnight. Ready by 08:00. Pulled by conversational assistant (Skill 14).\n\nMORNING ADVISORY — 19/02/2026\nGenerated: 19/02/2026 05:47 Athens time\n\nWATCH LIST — 3 clients warrant attention today\n\n1. GAMMA CONSTRUCTIONS AE (EL555444333) — RISK: HIGH (8/10)\n Cash position has declined 3 consecutive months. Current balance EUR 12,400.\n Tax payment of EUR 8,900 due 25/03/2026. Margin is tight.\n Suggest: Review with client before month end.\n\n2. DELTA SERVICES EPE (EL777888999) — RISK: MEDIUM (6/10)\n VAT liability increased 34% vs prior 3-month average. January: EUR 4,100\n vs average of EUR 3,060. Not yet investigated.\n Suggest: Check whether turnover genuinely increased or a classification\n issue exists in the January invoices. Confidence: MEDIUM (4 months data)\n\n3. EPSILON RETAIL OE (EL222333444) — RISK: MEDIUM (5/10)\n Bank statements for January not received. VAT filing due 25/02/2026 in 6 days.\n Suggest: Send document request today.\n\nPORTFOLIO SNAPSHOT\nActive clients: 42 | Low risk: 31 | Medium: 8 | High: 3 | Critical: 0\nNext high-volume deadline: VAT February 25/02/2026 (6 days, 18 clients affected)\n\nSECTOR NOTE\nRetail sector (7 clients): Gross margins down an average of 3.2pp vs Q4 2025.\nPattern appears sector-wide. May be worth raising with retail clients proactively.\nConfidence: MEDIUM (7 clients, 3 months of data)" }, { "title": "File System", "body": "Analytics_File_Structure:\n owns: \"/data/reports/analytics/\"\n\n daily_outputs:\n - \"{YYYY-MM-DD}_risk-scores.json\"\n - \"{YYYY-MM-DD}_morning-advisory.json\"\n - \"{YYYY-MM-DD}_morning-advisory.txt\"\n - \"{YYYY-MM-DD}_anomalies.json\"\n\n monthly_outputs:\n - \"{YYYY-MM}_portfolio-report.pdf\"\n - \"{YYYY-MM}_sector-benchmarks.json\"\n - \"{YYYY-MM}_trend-analysis.json\"\n\n on_demand_outputs:\n - \"{YYYY-MM-DD}_{AFM}_risk-detail.json\"\n - \"{YYYY-MM-DD}_{AFM}_forecast.json\"\n - \"{YYYY-MM-DD}_{AFM}_trends.json\"\n\n reads_from:\n - \"/data/clients/*/financial-statements/\"\n - \"/data/clients/*/compliance/\"\n - \"/data/clients/*/correspondence/\"\n - \"/data/banking/reconciliation/\"\n - \"/data/efka/\"\n - \"/data/reports/analytics/\" # Prior outputs for trend continuity\n\n never_writes_to:\n - \"/data/clients/\"\n - \"/data/compliance/\"\n - \"/data/banking/\"\n - \"/data/efka/\"" }, { "title": "Scheduling", "body": "Analytics_Schedule:\n nightly_run:\n time: \"01:30 Athens time (after backup and integrity check)\"\n operations:\n - \"Compute risk scores for all active clients\"\n - \"Run anomaly detection across all clients with new data\"\n - \"Update trend analysis for clients with new financial statements\"\n - \"Generate morning advisory\"\n duration_estimate: \"10-30 minutes depending on portfolio size\"\n\n monthly_run:\n trigger: \"After all monthly statements generated (typically 5th-10th of following month)\"\n operations:\n - \"Recompute sector benchmarks\"\n - \"Generate portfolio monthly report\"\n - \"Run 12-month trend analysis for all clients with sufficient history\"\n\n on_demand:\n available_during: \"Business hours\"\n rate_limit: \"Maximum 10 on-demand requests per hour\"\n bounded_by: \"Pre-computed daily outputs where possible\"" }, { "title": "Integration Points", "body": "Upstream_Skills_Read:\n greek-financial-statements: \"P&L, balance sheet, VAT summary — primary financial data\"\n client-data-management: \"Compliance history, document registry, correspondence log\"\n greek-banking-integration: \"Reconciliation data, cash position, transaction patterns\"\n efka-api-integration: \"Payroll costs, employee counts, contribution history\"\n cli-deadline-monitor: \"Upcoming deadlines — feeds cash flow forecast\"\n greek-compliance-aade: \"Filing history, penalty records\"\n client-communication-engine: \"Correspondence patterns — identifies chronic document requesters\"\n\nDownstream_Skills_Feed:\n conversational-ai-assistant: \"Answers analytics queries; morning advisory pulled via chat\"\n dashboard-greek-accounting: \"Risk scores, portfolio snapshot, watch list\"\n client-communication-engine: \"Advisory findings can prompt draft letters (human initiates)\"" }, { "title": "Memory Integration (Phase 4 — Skill 19 hooks)", "body": "Memory_Integration:\n log_episodes: true\n episode_types:\n - morning_advisory_generated\n - anomaly_detected_and_surfaced\n - risk_score_computed\n - forecast_generated\n\n log_failures: true\n failure_types:\n - insufficient_data_for_analysis\n - sector_benchmark_too_small\n - financial_statements_missing\n\n useful_patterns_to_detect:\n - \"Anomaly types consistently dismissed by accountants — thresholds may be too sensitive\"\n - \"Risk score bands that consistently predict actual compliance problems — calibration quality\"\n - \"Clients where forecasts are consistently wrong in one direction — systematic bias\"\n\n rate_limit_group: \"analytics_operations\"" }, { "title": "Error Handling", "body": "Error_Responses:\n\n insufficient_history:\n output: \"{Client} has only {N} periods of data — trend analysis requires at least 3. Showing available data with LOW CONFIDENCE marker.\"\n action: \"Produce what is possible, clearly labelled. Do not refuse to show anything.\"\n\n sector_too_small:\n output: \"Sector benchmark for {sector} cannot be computed — only {N} clients (minimum 3 required). Showing own-history analysis only.\"\n\n missing_statements:\n output: \"Financial trend analysis for {client} requires Skill 15 outputs for {period}. Statements not yet generated.\"\n action: \"Show analysis based on available periods. Note the gap explicitly.\"\n\n on_demand_rate_limit:\n output: \"On-demand analysis limit reached (10/hour). Pre-computed morning advisory is available now. Full analysis available after {time}.\"\n action: \"Direct to pre-computed outputs. Never drop the request silently.\"" }, { "title": "Success Metrics", "body": "A successful deployment of this skill should achieve:\n\nMorning advisory ready every business day before 08:00 Athens time\nRisk scores computed for 100% of active clients nightly\nAnomaly detection surfaces at least one actionable finding per week across the portfolio\nCash flow forecasts accurate within 15% for the 1-month horizon (measured retrospectively)\nZero false positives that cause unnecessary client alarm — confidence ratings are accurate\nAll findings in plain English that an accounting assistant can act on immediately\nRead-only confirmed — no writes to any operational directory, ever\n\nRemember: This skill is the difference between an accounting system that processes the past and one that helps the firm prepare for the future. The value is not in the data it holds — the value is in what it notices that humans would have missed." } ], "body": "Analytics and Advisory Intelligence\n\nThe previous 17 skills process, file, store, and protect. This skill thinks. It reads across all the data the system has built up and asks: what does this mean? What should the accountant know that they have not thought to ask?\n\nAn accountant managing 40 clients cannot spot a VAT liability trend building across one client's 12 months of data while simultaneously processing another client's payroll and preparing a third client's annual tax return. This skill does the cross-sectional, longitudinal reading that busy humans cannot. It surfaces the finding. The accountant decides what to do with it.\n\nThis skill is purely advisory. It reads, analyses, and reports. It never takes action, never modifies client records, and never submits anything. Every insight it surfaces is a prompt for human judgement, not a trigger for automated action.\n\nSetup\nexport OPENCLAW_DATA_DIR=\"/data\"\nwhich jq || sudo apt install jq\n\n\nNo external credentials required. Analyzes financial data from local files to generate trend reports and advisory insights.\n\nCore Philosophy\nProactive, Not Reactive: The system already handles reactive work. This skill looks ahead — identifying problems before they become crises and opportunities before they are missed\nCross-Client Vision: No single-client skill can see patterns that span the portfolio. This skill aggregates anonymised data across clients to detect sector trends, identify outliers, and benchmark clients against peers\nPlain English Findings: Every output is written for accounting assistants. No statistical jargon, no unexplained numbers. Finding + evidence + suggested action\nConfidence-Rated: Every finding carries a confidence level. A pattern with three data points is labelled differently from one with 18. The accountant knows how much weight to give each insight\nRead-Only Always: This skill reads from all data sources but writes only to /data/reports/analytics/. It has no write access to /data/clients/, /data/compliance/, or any operational directory\nOvernight Operation: Heavy analysis runs outside business hours. Lightweight queries run on demand but are bounded by pre-computed daily outputs\nOpenClaw Commands\nPortfolio-Level Analysis\nopenclaw analytics portfolio-health --all-clients --period 2026-01\nopenclaw analytics portfolio-health --all-clients --period 2026-01 --rank-by risk\nopenclaw analytics compliance-risk --all-clients --period 2026-01\nopenclaw analytics compliance-risk --all-clients --flag-high-risk\nopenclaw analytics compliance-risk --sector retail --compare-to-sector\nopenclaw analytics workload --all-clients --period 2026-01 --by-accountant\nopenclaw analytics workload --forecast --next-quarter\nopenclaw analytics benchmark --afm EL123456789 --vs-sector retail --period 2026-01\nopenclaw analytics benchmark --afm EL123456789 --vs-sector retail --last 6-months\n\nClient-Level Analysis\nopenclaw analytics client-risk --afm EL123456789\nopenclaw analytics client-risk --afm EL123456789 --verbose\nopenclaw analytics trends --afm EL123456789 --metric vat-liability --last 12-months\nopenclaw analytics trends --afm EL123456789 --metric gross-margin --last 6-months\nopenclaw analytics trends --afm EL123456789 --all-metrics --period 2025\nopenclaw analytics anomalies --afm EL123456789 --period 2026-01\nopenclaw analytics anomalies --afm EL123456789 --last 6-months --flag-significant\nopenclaw analytics cashflow-forecast --afm EL123456789 --horizon 3-months\nopenclaw analytics cashflow-forecast --afm EL123456789 --horizon 3-months --include-tax-payments\nopenclaw analytics tax-planning --afm EL123456789 --year 2026\nopenclaw analytics tax-planning --afm EL123456789 --year 2026 --include-scenarios\n\nAnomaly Detection\nopenclaw analytics supplier-overlap --all-clients --flag-unusual\nopenclaw analytics supplier-overlap --threshold 5-clients\nopenclaw analytics expense-anomalies --all-clients --period 2026-01\nopenclaw analytics expense-anomalies --afm EL123456789 --vs-prior-periods\nopenclaw analytics vat-rate-check --all-clients --period 2026-01\nopenclaw analytics vat-rate-check --afm EL123456789 --last 6-months\n\nScheduled Reports and Advisory\nopenclaw analytics morning-advisory --date today\nopenclaw analytics morning-advisory --date today --high-risk-only\nopenclaw analytics monthly-report --period 2026-01 --all-clients\nopenclaw analytics monthly-report --period 2026-01 --format pdf\nopenclaw analytics quarterly-review --quarter 2026-Q1 --all-clients\nopenclaw analytics ask --query \"which clients have increasing VAT liability over the last 6 months\"\nopenclaw analytics ask --query \"which clients are at risk of not meeting their Q2 tax payment\"\nopenclaw analytics ask --query \"are there any expense categories that look unusual this month\"\n\nAnalysis Modules\n1. Compliance Risk Scoring\n\nEvery client receives a compliance risk score on a 1-10 scale, computed nightly. Feeds the dashboard portfolio view and morning advisory.\n\nCompliance_Risk_Score:\n inputs:\n - Late filings in the last 12 months (weight: 30%)\n - Compliance gaps currently open (weight: 25%)\n - Missing documents pending more than 14 days (weight: 20%)\n - AADE penalty history (weight: 15%)\n - Days until next deadline vs documents received (weight: 10%)\n\n score_bands:\n 1-3: \"Low risk — all obligations current, no gaps\"\n 4-6: \"Medium risk — minor gaps or historical delays\"\n 7-8: \"High risk — active gaps or recent penalties\"\n 9-10: \"Critical — immediate attention required\"\n\n output_location: \"/data/reports/analytics/{YYYY-MM-DD}_risk-scores.json\"\n refreshed: \"Nightly at 01:00 Athens time\"\n\n2. Financial Trend Analysis\n\nReads Skill 15 financial statement outputs across multiple periods to detect directional movement.\n\nFinancial_Trends:\n metrics_tracked:\n gross_margin:\n calculation: \"(Revenue - Cost of Sales) / Revenue\"\n alert_threshold: \"Drop of more than 5 percentage points vs same period last year\"\n finding_template: \"{Client} gross margin has fallen from {X}% to {Y}% — {delta}pp decline over {N} months. Primary driver appears to be {top expense category change}.\"\n\n vat_liability_trend:\n calculation: \"Net VAT payable per period\"\n alert_threshold: \"Increase of more than 20% vs prior 3-month average\"\n finding_template: \"{Client} VAT liability has increased {X}% over {N} months. May reflect higher turnover, a change in customer mix, or a classification issue worth reviewing.\"\n\n staff_cost_ratio:\n calculation: \"Staff costs (EGLS account 64) / Revenue\"\n alert_threshold: \"Ratio increase of more than 3 percentage points\"\n\n cash_position:\n calculation: \"Cash and bank balances (account 38) trend\"\n alert_threshold: \"Declining for 3 consecutive months\"\n finding_template: \"{Client} cash position has declined for {N} consecutive months (from EUR {X} to EUR {Y}). With a tax payment of EUR {Z} due on {date}, this warrants a cash flow conversation.\"\n\n minimum_periods_required: 3\n preferred_periods: 12\n confidence_note: \"Findings with fewer than 6 data points are marked LOW CONFIDENCE\"\n\n3. Anomaly Detection\n\nValues statistically unusual relative to a client's own history and sector peers.\n\nAnomaly_Detection:\n methods:\n own_history_comparison:\n description: \"Value more than 2 standard deviations from client's own trailing average\"\n example: \"Electricity costs EUR 4,200 in January vs trailing 12-month average of EUR 1,800\"\n\n sector_peer_comparison:\n description: \"Value more than 1.5x or less than 0.5x the sector median for that account\"\n note: \"Sector medians computed from anonymised aggregates across the portfolio\"\n\n vat_rate_anomaly:\n description: \"Transaction classified at incorrect VAT rate based on product/service category\"\n example: \"Food product invoice at 24% rather than correct 13% reduced rate\"\n action: \"Flag for accountant review — never auto-correct\"\n\n output_fields:\n - metric: \"What was measured\"\n - actual_value: \"What was found\"\n - expected_range: \"What is normal for this client / sector\"\n - deviation: \"How far outside normal\"\n - confidence: \"HIGH / MEDIUM / LOW\"\n - suggested_action: \"Plain English recommendation\"\n - data_source: \"Which files the finding is based on\"\n\n4. Cash Flow Forecasting\n\nProjects cash position forward 1-3 months using historical patterns and known upcoming obligations.\n\nCashflow_Forecast:\n inputs:\n known_inflows:\n - Recurring revenue based on trailing 3-month average\n - Outstanding debtor invoices from registry\n known_outflows:\n - Upcoming tax deadlines from cli-deadline-monitor\n - Recurring supplier payments from banking history\n - EFKA contributions due\n - Payroll from prior period data\n uncertainty_ranges:\n - Revenue: +/- 15% based on historical variance\n - Ad-hoc expenses: +/- 20%\n\n output:\n - Best case / expected / worst case cash position at each month end\n - Months where cash may go negative (flagged HIGH RISK)\n - Specific upcoming payments that may cause strain\n\n confidence_degradation:\n 1_month: \"HIGH confidence\"\n 2_months: \"MEDIUM confidence\"\n 3_months: \"LOW confidence — directional only\"\n\n5. Portfolio Intelligence (Cross-Client)\n\nAggregated across the portfolio. All cross-client aggregation is anonymised.\n\nPortfolio_Intelligence:\n sector_benchmarks:\n computed_from: \"Anonymised aggregates of all active clients per sector\"\n metrics:\n - Median gross margin by sector\n - Median staff cost ratio by sector\n - Median VAT liability as percentage of revenue by sector\n refreshed: \"Monthly — after all monthly statements are generated\"\n minimum_clients_per_sector: 3\n\n portfolio_risk_distribution:\n description: \"Distribution of risk scores across the full portfolio over time\"\n\n workload_concentration:\n description: \"Risk-weighted workload per accountant — alerts if one person carries disproportionate risk\"\n\n common_issues:\n description: \"Issues appearing across multiple clients simultaneously\"\n examples:\n - \"6 retail clients showing declining margins — possible sector-wide trend\"\n - \"3 clients using the same supplier showing unusual payment patterns\"\n - \"4 clients with outstanding document requests over 21 days\"\n\nMorning Advisory Output Format\n\nPre-computed overnight. Ready by 08:00. Pulled by conversational assistant (Skill 14).\n\nMORNING ADVISORY — 19/02/2026\nGenerated: 19/02/2026 05:47 Athens time\n\nWATCH LIST — 3 clients warrant attention today\n\n1. GAMMA CONSTRUCTIONS AE (EL555444333) — RISK: HIGH (8/10)\n Cash position has declined 3 consecutive months. Current balance EUR 12,400.\n Tax payment of EUR 8,900 due 25/03/2026. Margin is tight.\n Suggest: Review with client before month end.\n\n2. DELTA SERVICES EPE (EL777888999) — RISK: MEDIUM (6/10)\n VAT liability increased 34% vs prior 3-month average. January: EUR 4,100\n vs average of EUR 3,060. Not yet investigated.\n Suggest: Check whether turnover genuinely increased or a classification\n issue exists in the January invoices. Confidence: MEDIUM (4 months data)\n\n3. EPSILON RETAIL OE (EL222333444) — RISK: MEDIUM (5/10)\n Bank statements for January not received. VAT filing due 25/02/2026 in 6 days.\n Suggest: Send document request today.\n\nPORTFOLIO SNAPSHOT\nActive clients: 42 | Low risk: 31 | Medium: 8 | High: 3 | Critical: 0\nNext high-volume deadline: VAT February 25/02/2026 (6 days, 18 clients affected)\n\nSECTOR NOTE\nRetail sector (7 clients): Gross margins down an average of 3.2pp vs Q4 2025.\nPattern appears sector-wide. May be worth raising with retail clients proactively.\nConfidence: MEDIUM (7 clients, 3 months of data)\n\nFile System\nAnalytics_File_Structure:\n owns: \"/data/reports/analytics/\"\n\n daily_outputs:\n - \"{YYYY-MM-DD}_risk-scores.json\"\n - \"{YYYY-MM-DD}_morning-advisory.json\"\n - \"{YYYY-MM-DD}_morning-advisory.txt\"\n - \"{YYYY-MM-DD}_anomalies.json\"\n\n monthly_outputs:\n - \"{YYYY-MM}_portfolio-report.pdf\"\n - \"{YYYY-MM}_sector-benchmarks.json\"\n - \"{YYYY-MM}_trend-analysis.json\"\n\n on_demand_outputs:\n - \"{YYYY-MM-DD}_{AFM}_risk-detail.json\"\n - \"{YYYY-MM-DD}_{AFM}_forecast.json\"\n - \"{YYYY-MM-DD}_{AFM}_trends.json\"\n\n reads_from:\n - \"/data/clients/*/financial-statements/\"\n - \"/data/clients/*/compliance/\"\n - \"/data/clients/*/correspondence/\"\n - \"/data/banking/reconciliation/\"\n - \"/data/efka/\"\n - \"/data/reports/analytics/\" # Prior outputs for trend continuity\n\n never_writes_to:\n - \"/data/clients/\"\n - \"/data/compliance/\"\n - \"/data/banking/\"\n - \"/data/efka/\"\n\nScheduling\nAnalytics_Schedule:\n nightly_run:\n time: \"01:30 Athens time (after backup and integrity check)\"\n operations:\n - \"Compute risk scores for all active clients\"\n - \"Run anomaly detection across all clients with new data\"\n - \"Update trend analysis for clients with new financial statements\"\n - \"Generate morning advisory\"\n duration_estimate: \"10-30 minutes depending on portfolio size\"\n\n monthly_run:\n trigger: \"After all monthly statements generated (typically 5th-10th of following month)\"\n operations:\n - \"Recompute sector benchmarks\"\n - \"Generate portfolio monthly report\"\n - \"Run 12-month trend analysis for all clients with sufficient history\"\n\n on_demand:\n available_during: \"Business hours\"\n rate_limit: \"Maximum 10 on-demand requests per hour\"\n bounded_by: \"Pre-computed daily outputs where possible\"\n\nIntegration Points\nUpstream_Skills_Read:\n greek-financial-statements: \"P&L, balance sheet, VAT summary — primary financial data\"\n client-data-management: \"Compliance history, document registry, correspondence log\"\n greek-banking-integration: \"Reconciliation data, cash position, transaction patterns\"\n efka-api-integration: \"Payroll costs, employee counts, contribution history\"\n cli-deadline-monitor: \"Upcoming deadlines — feeds cash flow forecast\"\n greek-compliance-aade: \"Filing history, penalty records\"\n client-communication-engine: \"Correspondence patterns — identifies chronic document requesters\"\n\nDownstream_Skills_Feed:\n conversational-ai-assistant: \"Answers analytics queries; morning advisory pulled via chat\"\n dashboard-greek-accounting: \"Risk scores, portfolio snapshot, watch list\"\n client-communication-engine: \"Advisory findings can prompt draft letters (human initiates)\"\n\nMemory Integration (Phase 4 — Skill 19 hooks)\nMemory_Integration:\n log_episodes: true\n episode_types:\n - morning_advisory_generated\n - anomaly_detected_and_surfaced\n - risk_score_computed\n - forecast_generated\n\n log_failures: true\n failure_types:\n - insufficient_data_for_analysis\n - sector_benchmark_too_small\n - financial_statements_missing\n\n useful_patterns_to_detect:\n - \"Anomaly types consistently dismissed by accountants — thresholds may be too sensitive\"\n - \"Risk score bands that consistently predict actual compliance problems — calibration quality\"\n - \"Clients where forecasts are consistently wrong in one direction — systematic bias\"\n\n rate_limit_group: \"analytics_operations\"\n\nError Handling\nError_Responses:\n\n insufficient_history:\n output: \"{Client} has only {N} periods of data — trend analysis requires at least 3. Showing available data with LOW CONFIDENCE marker.\"\n action: \"Produce what is possible, clearly labelled. Do not refuse to show anything.\"\n\n sector_too_small:\n output: \"Sector benchmark for {sector} cannot be computed — only {N} clients (minimum 3 required). Showing own-history analysis only.\"\n\n missing_statements:\n output: \"Financial trend analysis for {client} requires Skill 15 outputs for {period}. Statements not yet generated.\"\n action: \"Show analysis based on available periods. Note the gap explicitly.\"\n\n on_demand_rate_limit:\n output: \"On-demand analysis limit reached (10/hour). Pre-computed morning advisory is available now. Full analysis available after {time}.\"\n action: \"Direct to pre-computed outputs. Never drop the request silently.\"\n\nSuccess Metrics\n\nA successful deployment of this skill should achieve:\n\nMorning advisory ready every business day before 08:00 Athens time\nRisk scores computed for 100% of active clients nightly\nAnomaly detection surfaces at least one actionable finding per week across the portfolio\nCash flow forecasts accurate within 15% for the 1-month horizon (measured retrospectively)\nZero false positives that cause unnecessary client alarm — confidence ratings are accurate\nAll findings in plain English that an accounting assistant can act on immediately\nRead-only confirmed — no writes to any operational directory, ever\n\nRemember: This skill is the difference between an accounting system that processes the past and one that helps the firm prepare for the future. The value is not in the data it holds — the value is in what it notices that humans would have missed." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/satoshistackalotto/analytics-and-advisory-intelligence", "publisherUrl": "https://clawhub.ai/satoshistackalotto/analytics-and-advisory-intelligence", "owner": "satoshistackalotto", "version": "0.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/analytics-and-advisory-intelligence", "downloadUrl": "https://openagent3.xyz/downloads/analytics-and-advisory-intelligence", "agentUrl": "https://openagent3.xyz/skills/analytics-and-advisory-intelligence/agent", "manifestUrl": "https://openagent3.xyz/skills/analytics-and-advisory-intelligence/agent.json", "briefUrl": "https://openagent3.xyz/skills/analytics-and-advisory-intelligence/agent.md" } }