{ "schemaVersion": "1.0", "item": { "slug": "analyst", "name": "Analyst", "source": "tencent", "type": "skill", "category": "数据分析", "sourceUrl": "https://clawhub.ai/ivangdavila/analyst", "canonicalUrl": "https://clawhub.ai/ivangdavila/analyst", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/analyst", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=analyst", "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": "2026-04-23T16:43:11.935Z", "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/analyst" }, "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/analyst", "agentPageUrl": "https://openagent3.xyz/skills/analyst/agent", "manifestUrl": "https://openagent3.xyz/skills/analyst/agent.json", "briefUrl": "https://openagent3.xyz/skills/analyst/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": "Framing Questions", "body": "Clarify the decision being made — analysis without action is trivia\n\"What would change your mind?\" surfaces the real question\nScope before diving in — infinite data, limited time\nHypothesis first, then test — fishing expeditions waste time" }, { "title": "Data Quality", "body": "Validate data before analyzing — garbage in, garbage out\nCheck row counts, date ranges, null rates first\nDuplicates hide in joins — always verify uniqueness\nSource definitions matter — revenue means different things to different teams\nDocument assumptions — future you needs context" }, { "title": "SQL Patterns", "body": "CTEs over nested subqueries — readable beats clever\nAggregate before joining when possible — performance matters\nWindow functions for running totals, ranks, comparisons\nCASE statements for categorization — clean logic\nComment non-obvious filters — why are we excluding these?" }, { "title": "Analysis Approach", "body": "Start with the simplest cut — don't overcomplicate early\nCohorts reveal what aggregates hide — when did users join?\nTime series need seasonality awareness — don't compare Dec to Jan\nSegmentation surfaces patterns — average obscures variation\nCorrelation isn't causation — but it's where to look" }, { "title": "Visualization", "body": "Chart type matches data: trends (line), comparison (bar), distribution (histogram)\nOne message per chart — don't overload\nLabel axes, title clearly — standalone comprehension\nColor with purpose — highlight, don't decorate\nTables for precision, charts for patterns" }, { "title": "Communicating Findings", "body": "Lead with the insight, not the methodology\nSo what? Now what? — always answer these\nConfidence levels matter — don't oversell noisy data\nRecommendations are opinions — label them as such\nExecutive summary first, details available — respect their time" }, { "title": "Stakeholder Relationship", "body": "Understand their mental model before presenting\nRegular check-ins prevent surprise requests\nPush back on bad questions — help them ask better ones\nData literacy varies — adjust explanation depth\nTheir intuition is data too — triangulate" }, { "title": "Tools", "body": "Right tool for the job: SQL for querying, spreadsheets for ad-hoc, BI for dashboards\nReproducibility matters — scripts over clicking\nVersion control analysis code — changes need history\nAutomate recurring reports — manual refresh doesn't scale" }, { "title": "Common Mistakes", "body": "Answering the wrong question precisely\nCherry-picking data that confirms expectations\nOverfitting: explaining noise as signal\nDeath by dashboard: metrics nobody checks\nAnalysis paralysis: perfect insight never delivered" } ], "body": "Data Analysis Rules\nFraming Questions\nClarify the decision being made — analysis without action is trivia\n\"What would change your mind?\" surfaces the real question\nScope before diving in — infinite data, limited time\nHypothesis first, then test — fishing expeditions waste time\nData Quality\nValidate data before analyzing — garbage in, garbage out\nCheck row counts, date ranges, null rates first\nDuplicates hide in joins — always verify uniqueness\nSource definitions matter — revenue means different things to different teams\nDocument assumptions — future you needs context\nSQL Patterns\nCTEs over nested subqueries — readable beats clever\nAggregate before joining when possible — performance matters\nWindow functions for running totals, ranks, comparisons\nCASE statements for categorization — clean logic\nComment non-obvious filters — why are we excluding these?\nAnalysis Approach\nStart with the simplest cut — don't overcomplicate early\nCohorts reveal what aggregates hide — when did users join?\nTime series need seasonality awareness — don't compare Dec to Jan\nSegmentation surfaces patterns — average obscures variation\nCorrelation isn't causation — but it's where to look\nVisualization\nChart type matches data: trends (line), comparison (bar), distribution (histogram)\nOne message per chart — don't overload\nLabel axes, title clearly — standalone comprehension\nColor with purpose — highlight, don't decorate\nTables for precision, charts for patterns\nCommunicating Findings\nLead with the insight, not the methodology\nSo what? Now what? — always answer these\nConfidence levels matter — don't oversell noisy data\nRecommendations are opinions — label them as such\nExecutive summary first, details available — respect their time\nStakeholder Relationship\nUnderstand their mental model before presenting\nRegular check-ins prevent surprise requests\nPush back on bad questions — help them ask better ones\nData literacy varies — adjust explanation depth\nTheir intuition is data too — triangulate\nTools\nRight tool for the job: SQL for querying, spreadsheets for ad-hoc, BI for dashboards\nReproducibility matters — scripts over clicking\nVersion control analysis code — changes need history\nAutomate recurring reports — manual refresh doesn't scale\nCommon Mistakes\nAnswering the wrong question precisely\nCherry-picking data that confirms expectations\nOverfitting: explaining noise as signal\nDeath by dashboard: metrics nobody checks\nAnalysis paralysis: perfect insight never delivered" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/analyst", "publisherUrl": "https://clawhub.ai/ivangdavila/analyst", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/analyst", "downloadUrl": "https://openagent3.xyz/downloads/analyst", "agentUrl": "https://openagent3.xyz/skills/analyst/agent", "manifestUrl": "https://openagent3.xyz/skills/analyst/agent.json", "briefUrl": "https://openagent3.xyz/skills/analyst/agent.md" } }