{
  "schemaVersion": "1.0",
  "item": {
    "slug": "retention",
    "name": "Retention",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/ivangdavila/retention",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/retention",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/retention",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=retention",
    "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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-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/retention"
    },
    "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/retention",
    "agentPageUrl": "https://openagent3.xyz/skills/retention/agent",
    "manifestUrl": "https://openagent3.xyz/skills/retention/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/retention/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": "Core Metrics",
        "body": "MetricFormulaHealthy RangeDay 1 retentionUsers active day 1 / signups40-60%Day 7 retentionUsers active day 7 / signups20-35%Day 30 retentionUsers active day 30 / signups10-20%Weekly retentionWAU this week / WAU last week85-95%Churn rateLost customers / start customers<5%/monthNRR (Net Revenue Retention)(Start MRR + expansion - churn) / Start MRR>100%"
      },
      {
        "title": "Cohort Analysis",
        "body": "Track by signup week, not calendar week:\n\nHorizontal axis: weeks since signup (0, 1, 2, 3...)\nVertical axis: signup cohort (Jan W1, Jan W2...)\nCell value: % of cohort still active\n\nIdentify:\n\nWhich cohorts retain better (product changes, marketing source)\nAt which week users drop off (week 2 cliff = aha moment too late)\nSeasonal patterns (holiday signups retain worse)"
      },
      {
        "title": "Churn Signals",
        "body": "Early warning indicators (flag before churn):\n\nLogin frequency drops 50%+ from baseline\nCore feature usage stops\nSupport tickets spike then go silent\nBilling page visits without upgrade\nTeam member removals\nData export requests"
      },
      {
        "title": "Engagement Loops",
        "body": "Retention requires habit formation:\n\nLoop TypeTriggerActionRewardPersonalEmail digestReview updatesProgress visibleSocialNotificationRespond to teamRecognitionContentNew content alertConsumeKnowledge gainedProgressStreak reminderComplete taskStreak maintained\n\nDesign for variable rewards - predictable = boring."
      },
      {
        "title": "Lifecycle Stages",
        "body": "StageTimeframeGoalTacticsActivationDay 0-3Reach aha momentOnboarding, setup wizardEngagementWeek 1-4Build habitUsage nudges, tipsRetentionMonth 1+Maintain valueFeature discovery, check-insExpansionOngoingIncrease usageUpsell, team invitesReactivationAfter churnWin backCampaigns, incentives"
      },
      {
        "title": "Reactivation Campaigns",
        "body": "Timing matters:\n\n7 days inactive: Soft nudge (\"We miss you\")\n14 days inactive: Value reminder + what's new\n30 days inactive: Incentive offer (discount, extended trial)\n90 days inactive: Last chance + feedback ask\n\nMessage formula:\n\n[Acknowledge absence] + [New value added] + [Easy re-entry CTA]\n\"Your dashboard is waiting. We added [feature]. One click to resume →\""
      },
      {
        "title": "Feature Stickiness",
        "body": "Measure which features predict retention:\n\nUsage correlation: Users of feature X retain 2x better\nTime to feature: Users who reach feature X in day 1 retain 3x\nFeature breadth: Users of 3+ features retain 5x vs 1 feature\n\nDouble down on sticky features in onboarding."
      },
      {
        "title": "Churn Prevention",
        "body": "When churn signal detected:\n\nImmediate: In-app message acknowledging drop (\"Need help?\")\nDay 3: Email from founder (personal, not marketing)\nDay 7: Offer call or live support\nBefore renewal: Proactive outreach with usage summary\n\nCancel flow optimization:\n\nAsk reason (required, 4-5 options)\nOffer pause instead of cancel\nShow what they'll lose (data, history, price lock)\nEasy return policy (\"reactivate anytime, data saved 90 days\")"
      },
      {
        "title": "Retention Benchmarks by Model",
        "body": "Business ModelGood D30Good Monthly ChurnB2C freemium10-15%N/A (free)B2C subscription8-12%5-7%B2B SMB15-25%3-5%B2B Enterprise25-40%1-2%"
      },
      {
        "title": "Common Mistakes",
        "body": "Measuring retention from signup, not activation\nTreating all churned users the same (voluntary vs involuntary)\nReactivation emails without new value proposition\nIgnoring payment failures as churn (30-40% of churn is involuntary)\nNo segmentation in cohort analysis (power users mask problems)"
      }
    ],
    "body": "Core Metrics\nMetric\tFormula\tHealthy Range\nDay 1 retention\tUsers active day 1 / signups\t40-60%\nDay 7 retention\tUsers active day 7 / signups\t20-35%\nDay 30 retention\tUsers active day 30 / signups\t10-20%\nWeekly retention\tWAU this week / WAU last week\t85-95%\nChurn rate\tLost customers / start customers\t<5%/month\nNRR (Net Revenue Retention)\t(Start MRR + expansion - churn) / Start MRR\t>100%\nCohort Analysis\n\nTrack by signup week, not calendar week:\n\nHorizontal axis: weeks since signup (0, 1, 2, 3...)\nVertical axis: signup cohort (Jan W1, Jan W2...)\nCell value: % of cohort still active\n\nIdentify:\n\nWhich cohorts retain better (product changes, marketing source)\nAt which week users drop off (week 2 cliff = aha moment too late)\nSeasonal patterns (holiday signups retain worse)\nChurn Signals\n\nEarly warning indicators (flag before churn):\n\nLogin frequency drops 50%+ from baseline\nCore feature usage stops\nSupport tickets spike then go silent\nBilling page visits without upgrade\nTeam member removals\nData export requests\nEngagement Loops\n\nRetention requires habit formation:\n\nLoop Type\tTrigger\tAction\tReward\nPersonal\tEmail digest\tReview updates\tProgress visible\nSocial\tNotification\tRespond to team\tRecognition\nContent\tNew content alert\tConsume\tKnowledge gained\nProgress\tStreak reminder\tComplete task\tStreak maintained\n\nDesign for variable rewards - predictable = boring.\n\nLifecycle Stages\nStage\tTimeframe\tGoal\tTactics\nActivation\tDay 0-3\tReach aha moment\tOnboarding, setup wizard\nEngagement\tWeek 1-4\tBuild habit\tUsage nudges, tips\nRetention\tMonth 1+\tMaintain value\tFeature discovery, check-ins\nExpansion\tOngoing\tIncrease usage\tUpsell, team invites\nReactivation\tAfter churn\tWin back\tCampaigns, incentives\nReactivation Campaigns\n\nTiming matters:\n\n7 days inactive: Soft nudge (\"We miss you\")\n14 days inactive: Value reminder + what's new\n30 days inactive: Incentive offer (discount, extended trial)\n90 days inactive: Last chance + feedback ask\n\nMessage formula:\n\n[Acknowledge absence] + [New value added] + [Easy re-entry CTA]\n\"Your dashboard is waiting. We added [feature]. One click to resume →\"\n\nFeature Stickiness\n\nMeasure which features predict retention:\n\nUsage correlation: Users of feature X retain 2x better\nTime to feature: Users who reach feature X in day 1 retain 3x\nFeature breadth: Users of 3+ features retain 5x vs 1 feature\n\nDouble down on sticky features in onboarding.\n\nChurn Prevention\n\nWhen churn signal detected:\n\nImmediate: In-app message acknowledging drop (\"Need help?\")\nDay 3: Email from founder (personal, not marketing)\nDay 7: Offer call or live support\nBefore renewal: Proactive outreach with usage summary\n\nCancel flow optimization:\n\nAsk reason (required, 4-5 options)\nOffer pause instead of cancel\nShow what they'll lose (data, history, price lock)\nEasy return policy (\"reactivate anytime, data saved 90 days\")\nRetention Benchmarks by Model\nBusiness Model\tGood D30\tGood Monthly Churn\nB2C freemium\t10-15%\tN/A (free)\nB2C subscription\t8-12%\t5-7%\nB2B SMB\t15-25%\t3-5%\nB2B Enterprise\t25-40%\t1-2%\nCommon Mistakes\nMeasuring retention from signup, not activation\nTreating all churned users the same (voluntary vs involuntary)\nReactivation emails without new value proposition\nIgnoring payment failures as churn (30-40% of churn is involuntary)\nNo segmentation in cohort analysis (power users mask problems)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/retention",
    "publisherUrl": "https://clawhub.ai/ivangdavila/retention",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/retention",
    "downloadUrl": "https://openagent3.xyz/downloads/retention",
    "agentUrl": "https://openagent3.xyz/skills/retention/agent",
    "manifestUrl": "https://openagent3.xyz/skills/retention/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/retention/agent.md"
  }
}