{ "schemaVersion": "1.0", "item": { "slug": "data-cog", "name": "data-cog", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/nitishgargiitd/data-cog", "canonicalUrl": "https://clawhub.ai/nitishgargiitd/data-cog", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/data-cog", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=data-cog", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/data-cog" }, "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/data-cog", "agentPageUrl": "https://openagent3.xyz/skills/data-cog/agent", "manifestUrl": "https://openagent3.xyz/skills/data-cog/agent.json", "briefUrl": "https://openagent3.xyz/skills/data-cog/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": "Data Cog - Your Data Has Answers, CellCog Finds Them", "body": "Your data has answers. CellCog asks the right questions. #1 on DeepResearch Bench (Feb 2026) + frontier coding agent.\n\nMost AI tools return code when you ask about data. CellCog returns answers — actual charts, clean datasets, statistical reports, and visual dashboards. Upload messy CSVs with a minimal prompt, and CellCog's coding agent explores your data, finds the patterns, and presents them beautifully. Full Python access for everything from data cleaning to ML model evaluation." }, { "title": "Prerequisites", "body": "This skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible.\n\nQuick pattern (v1.0+):\n\n# Fire-and-forget - returns immediately\nresult = client.create_chat(\n prompt=\"Analyze this dataset: /path/to/data.csv\",\n notify_session_key=\"agent:main:main\",\n task_label=\"data-analysis\",\n chat_mode=\"agent\" # Agent mode for most data work\n)\n# Daemon notifies you when complete - do NOT poll" }, { "title": "Code as Tool, Not as Output", "body": "Other AI tools give you Python code and say \"run this.\" CellCog runs the code for you and delivers the results:\n\nOther AI ToolsData-Cog\"Here's a pandas script to analyze your data\"Here are your actual insights with charts\"Run this matplotlib code to see the chart\"Here's the chart, annotated with findings\"This SQL query will find outliers\"Found 23 outliers, here's what they mean\"You'll need scikit-learn for this\"Model trained, here's accuracy and feature importance\n\nYou upload data. You get answers. The code runs behind the scenes." }, { "title": "Exploratory Data Analysis", "body": "Understand your data fast:\n\nDataset Profiling: \"Analyze this CSV — distributions, missing values, outliers, correlations, and data quality summary\"\nPattern Discovery: \"What patterns and trends exist in this sales data? Surprise me.\"\nAnomaly Detection: \"Find unusual patterns in this server log data — what looks abnormal?\"\nRelationship Analysis: \"What factors most strongly correlate with customer churn in this dataset?\"\n\nExample prompt:\n\n\"Analyze this dataset:\n/path/to/customer_data.csv\nI don't know much about this data yet. Give me:\n\nOverview: rows, columns, data types, missing values\nKey distributions and summary statistics\nMost interesting correlations\nAny outliers or data quality issues\n3-5 insights that jump out\n\nPresent findings as an interactive HTML report with charts.\"" }, { "title": "Data Cleaning & Transformation", "body": "Wrangle messy data into shape:\n\nClean Messy Data: \"Clean this CSV — fix inconsistent date formats, handle missing values, remove duplicates, standardize column names\"\nData Transformation: \"Pivot this transaction data into a monthly summary by product category\"\nData Merging: \"Join these three CSV files on customer_id and create a unified dataset\"\nFeature Engineering: \"Create useful features from this raw data for predicting house prices\"\n\nExample prompt:\n\n\"Clean and transform this dataset:\n/path/to/messy_data.csv\nIssues I know about:\n\nDates are in mixed formats (MM/DD/YYYY and YYYY-MM-DD)\n'Revenue' column has some values with $ signs and commas\nDuplicate rows exist\nMissing values in 'Region' column\n\nClean it up and give me back a clean CSV plus a summary of what you changed.\"" }, { "title": "Statistical Analysis", "body": "Rigorous analysis with real numbers:\n\nHypothesis Testing: \"Is there a statistically significant difference in conversion rates between our A and B variants?\"\nRegression Analysis: \"What factors predict employee salary in this HR dataset? Build a regression model.\"\nTime Series Analysis: \"Analyze this monthly revenue data — trend, seasonality, and forecast next 6 months\"\nCohort Analysis: \"Create a cohort analysis showing user retention by signup month\"\n\nExample prompt:\n\n\"I ran an A/B test on our checkout page:\n/path/to/ab_test_results.csv\nColumns: user_id, variant (A or B), converted (0/1), revenue, timestamp\nTell me:\n\nIs variant B statistically better? (p-value, confidence interval)\nConversion rate difference\nRevenue per user difference\nSample size adequacy check\nMy recommendation: ship B or keep testing?\n\nPresent with clear charts and a plain-English conclusion.\"" }, { "title": "Visualization & Reporting", "body": "Turn data into visual stories:\n\nChart Generation: \"Create a set of charts showing our quarterly performance from this data\"\nDashboard Reports: \"Build an interactive dashboard from this sales dataset with filters by region and product\"\nPresentation-Ready Visuals: \"Create publication-quality charts from this research data\"\nComparison Visuals: \"Visualize how our metrics compare to industry benchmarks\"" }, { "title": "Machine Learning", "body": "Applied ML without the setup:\n\nClassification: \"Predict which customers will churn based on this dataset — train a model, show feature importance\"\nClustering: \"Segment these customers into groups based on behavior — how many natural clusters exist?\"\nForecasting: \"Forecast next quarter's sales using this historical data\"\nModel Evaluation: \"I trained a model — here are the predictions. Evaluate: accuracy, precision, recall, confusion matrix, ROC curve\"\n\nExample prompt:\n\n\"Predict customer churn from this dataset:\n/path/to/customer_features.csv\nTarget column: 'churned'\n\nTrain a model, try at least 2 algorithms\nShow feature importance — what drives churn?\nConfusion matrix and ROC curve\nPlain-English summary: 'The top 3 reasons customers churn are...'\nActionable recommendations based on findings\n\nI want insights, not just metrics.\"" }, { "title": "Supported Data Formats", "body": "FormatHow to SendCSVUpload via SHOW_FILEExcel (XLSX)Upload via SHOW_FILEJSONUpload via SHOW_FILEParquetUpload via SHOW_FILESQL exportsUpload the dump via SHOW_FILEInline dataDescribe small datasets directly in prompt" }, { "title": "Output Formats", "body": "FormatBest ForInteractive HTML DashboardExplorable charts, filters, drill-downsPDF ReportShareable analysis reports with charts and findingsClean CSV/XLSXCleaned or transformed data files for downstream useMarkdownQuick insights for integration into docs" }, { "title": "Chat Mode for Data", "body": "ScenarioRecommended ModeQuick data cleaning, simple charts, basic statistics\"agent\"Deep analysis with multiple techniques, ML modeling, comprehensive reports\"agent team\"\n\nUse \"agent\" for most data work. Data cleaning, EDA, chart generation, and standard statistical analysis execute well in agent mode.\n\nUse \"agent team\" for complex analytical projects — multi-technique analysis, ML model comparisons, or when you need deep domain reasoning about what the data means." }, { "title": "Example Prompts", "body": "Minimal prompt, maximum insight:\n\n\"Analyze this:\n/path/to/data.csv\nTell me everything interesting.\"\n\nThat's it. CellCog's coding agent will profile the data, run exploratory analysis, find patterns, and present findings with charts. You don't need to know what to ask — the agent figures it out.\n\nBusiness analysis:\n\n\"Analyze our e-commerce data:\n/path/to/orders.csv\nI need:\n\nRevenue trends (daily, weekly, monthly)\nBest and worst performing products\nCustomer purchase frequency distribution\nAverage order value trends\nSeasonal patterns\nTop 5 actionable insights for growing revenue\n\nInteractive HTML dashboard with all charts.\"\n\nResearch data analysis:\n\n\"Analyze this survey data from 500 respondents:\n/path/to/survey.csv\nResearch questions:\n\nIs there a significant relationship between age group and product preference?\nDo satisfaction scores differ by region? (ANOVA)\nWhat factors best predict likelihood to recommend? (regression)\n\nInclude: statistical tests, p-values, effect sizes, and publication-ready charts.\nPDF report format.\"" }, { "title": "Tips for Better Data Analysis", "body": "Just upload and ask: You don't need to describe every column. CellCog reads the data and figures out what's there.\n\n\nState your question: \"What drives churn?\" is more focused than \"Analyze this data.\" Both work, but the first gets faster results.\n\n\nMention the audience: \"For my CEO\" means executive summary. \"For the data team\" means show the methodology.\n\n\nSpecify what you'll do with it: \"I need to present this to the board\" vs \"I need clean data for my ML pipeline\" — context shapes the output.\n\n\nDon't over-specify methods: Let CellCog choose the right statistical approach. Say what you want to learn, not which algorithm to use.\n\n\nIterate: Upload data → get initial analysis → ask follow-up questions → go deeper. CellCog maintains context across messages." } ], "body": "Data Cog - Your Data Has Answers, CellCog Finds Them\n\nYour data has answers. CellCog asks the right questions. #1 on DeepResearch Bench (Feb 2026) + frontier coding agent.\n\nMost AI tools return code when you ask about data. CellCog returns answers — actual charts, clean datasets, statistical reports, and visual dashboards. Upload messy CSVs with a minimal prompt, and CellCog's coding agent explores your data, finds the patterns, and presents them beautifully. Full Python access for everything from data cleaning to ML model evaluation.\n\nPrerequisites\n\nThis skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible.\n\nQuick pattern (v1.0+):\n\n# Fire-and-forget - returns immediately\nresult = client.create_chat(\n prompt=\"Analyze this dataset: /path/to/data.csv\",\n notify_session_key=\"agent:main:main\",\n task_label=\"data-analysis\",\n chat_mode=\"agent\" # Agent mode for most data work\n)\n# Daemon notifies you when complete - do NOT poll\n\nWhat Makes Data-Cog Different\nCode as Tool, Not as Output\n\nOther AI tools give you Python code and say \"run this.\" CellCog runs the code for you and delivers the results:\n\nOther AI Tools\tData-Cog\n\"Here's a pandas script to analyze your data\"\tHere are your actual insights with charts\n\"Run this matplotlib code to see the chart\"\tHere's the chart, annotated with findings\n\"This SQL query will find outliers\"\tFound 23 outliers, here's what they mean\n\"You'll need scikit-learn for this\"\tModel trained, here's accuracy and feature importance\n\nYou upload data. You get answers. The code runs behind the scenes.\n\nWhat Data Work You Can Do\nExploratory Data Analysis\n\nUnderstand your data fast:\n\nDataset Profiling: \"Analyze this CSV — distributions, missing values, outliers, correlations, and data quality summary\"\nPattern Discovery: \"What patterns and trends exist in this sales data? Surprise me.\"\nAnomaly Detection: \"Find unusual patterns in this server log data — what looks abnormal?\"\nRelationship Analysis: \"What factors most strongly correlate with customer churn in this dataset?\"\n\nExample prompt:\n\n\"Analyze this dataset: /path/to/customer_data.csv\n\nI don't know much about this data yet. Give me:\n\nOverview: rows, columns, data types, missing values\nKey distributions and summary statistics\nMost interesting correlations\nAny outliers or data quality issues\n3-5 insights that jump out\n\nPresent findings as an interactive HTML report with charts.\"\n\nData Cleaning & Transformation\n\nWrangle messy data into shape:\n\nClean Messy Data: \"Clean this CSV — fix inconsistent date formats, handle missing values, remove duplicates, standardize column names\"\nData Transformation: \"Pivot this transaction data into a monthly summary by product category\"\nData Merging: \"Join these three CSV files on customer_id and create a unified dataset\"\nFeature Engineering: \"Create useful features from this raw data for predicting house prices\"\n\nExample prompt:\n\n\"Clean and transform this dataset: /path/to/messy_data.csv\n\nIssues I know about:\n\nDates are in mixed formats (MM/DD/YYYY and YYYY-MM-DD)\n'Revenue' column has some values with $ signs and commas\nDuplicate rows exist\nMissing values in 'Region' column\n\nClean it up and give me back a clean CSV plus a summary of what you changed.\"\n\nStatistical Analysis\n\nRigorous analysis with real numbers:\n\nHypothesis Testing: \"Is there a statistically significant difference in conversion rates between our A and B variants?\"\nRegression Analysis: \"What factors predict employee salary in this HR dataset? Build a regression model.\"\nTime Series Analysis: \"Analyze this monthly revenue data — trend, seasonality, and forecast next 6 months\"\nCohort Analysis: \"Create a cohort analysis showing user retention by signup month\"\n\nExample prompt:\n\n\"I ran an A/B test on our checkout page: /path/to/ab_test_results.csv\n\nColumns: user_id, variant (A or B), converted (0/1), revenue, timestamp\n\nTell me:\n\nIs variant B statistically better? (p-value, confidence interval)\nConversion rate difference\nRevenue per user difference\nSample size adequacy check\nMy recommendation: ship B or keep testing?\n\nPresent with clear charts and a plain-English conclusion.\"\n\nVisualization & Reporting\n\nTurn data into visual stories:\n\nChart Generation: \"Create a set of charts showing our quarterly performance from this data\"\nDashboard Reports: \"Build an interactive dashboard from this sales dataset with filters by region and product\"\nPresentation-Ready Visuals: \"Create publication-quality charts from this research data\"\nComparison Visuals: \"Visualize how our metrics compare to industry benchmarks\"\nMachine Learning\n\nApplied ML without the setup:\n\nClassification: \"Predict which customers will churn based on this dataset — train a model, show feature importance\"\nClustering: \"Segment these customers into groups based on behavior — how many natural clusters exist?\"\nForecasting: \"Forecast next quarter's sales using this historical data\"\nModel Evaluation: \"I trained a model — here are the predictions. Evaluate: accuracy, precision, recall, confusion matrix, ROC curve\"\n\nExample prompt:\n\n\"Predict customer churn from this dataset: /path/to/customer_features.csv\n\nTarget column: 'churned'\n\nTrain a model, try at least 2 algorithms\nShow feature importance — what drives churn?\nConfusion matrix and ROC curve\nPlain-English summary: 'The top 3 reasons customers churn are...'\nActionable recommendations based on findings\n\nI want insights, not just metrics.\"\n\nSupported Data Formats\nFormat\tHow to Send\nCSV\tUpload via SHOW_FILE\nExcel (XLSX)\tUpload via SHOW_FILE\nJSON\tUpload via SHOW_FILE\nParquet\tUpload via SHOW_FILE\nSQL exports\tUpload the dump via SHOW_FILE\nInline data\tDescribe small datasets directly in prompt\nOutput Formats\nFormat\tBest For\nInteractive HTML Dashboard\tExplorable charts, filters, drill-downs\nPDF Report\tShareable analysis reports with charts and findings\nClean CSV/XLSX\tCleaned or transformed data files for downstream use\nMarkdown\tQuick insights for integration into docs\nChat Mode for Data\nScenario\tRecommended Mode\nQuick data cleaning, simple charts, basic statistics\t\"agent\"\nDeep analysis with multiple techniques, ML modeling, comprehensive reports\t\"agent team\"\n\nUse \"agent\" for most data work. Data cleaning, EDA, chart generation, and standard statistical analysis execute well in agent mode.\n\nUse \"agent team\" for complex analytical projects — multi-technique analysis, ML model comparisons, or when you need deep domain reasoning about what the data means.\n\nExample Prompts\n\nMinimal prompt, maximum insight:\n\n\"Analyze this: /path/to/data.csv\n\nTell me everything interesting.\"\n\nThat's it. CellCog's coding agent will profile the data, run exploratory analysis, find patterns, and present findings with charts. You don't need to know what to ask — the agent figures it out.\n\nBusiness analysis:\n\n\"Analyze our e-commerce data: /path/to/orders.csv\n\nI need:\n\nRevenue trends (daily, weekly, monthly)\nBest and worst performing products\nCustomer purchase frequency distribution\nAverage order value trends\nSeasonal patterns\nTop 5 actionable insights for growing revenue\n\nInteractive HTML dashboard with all charts.\"\n\nResearch data analysis:\n\n\"Analyze this survey data from 500 respondents: /path/to/survey.csv\n\nResearch questions:\n\nIs there a significant relationship between age group and product preference?\nDo satisfaction scores differ by region? (ANOVA)\nWhat factors best predict likelihood to recommend? (regression)\n\nInclude: statistical tests, p-values, effect sizes, and publication-ready charts. PDF report format.\"\n\nTips for Better Data Analysis\n\nJust upload and ask: You don't need to describe every column. CellCog reads the data and figures out what's there.\n\nState your question: \"What drives churn?\" is more focused than \"Analyze this data.\" Both work, but the first gets faster results.\n\nMention the audience: \"For my CEO\" means executive summary. \"For the data team\" means show the methodology.\n\nSpecify what you'll do with it: \"I need to present this to the board\" vs \"I need clean data for my ML pipeline\" — context shapes the output.\n\nDon't over-specify methods: Let CellCog choose the right statistical approach. Say what you want to learn, not which algorithm to use.\n\nIterate: Upload data → get initial analysis → ask follow-up questions → go deeper. CellCog maintains context across messages." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/nitishgargiitd/data-cog", "publisherUrl": "https://clawhub.ai/nitishgargiitd/data-cog", "owner": "nitishgargiitd", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/data-cog", "downloadUrl": "https://openagent3.xyz/downloads/data-cog", "agentUrl": "https://openagent3.xyz/skills/data-cog/agent", "manifestUrl": "https://openagent3.xyz/skills/data-cog/agent.json", "briefUrl": "https://openagent3.xyz/skills/data-cog/agent.md" } }