# Send Retention to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/retention", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=retention", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "retention", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T02:42:42.580Z", "expiresAt": "2026-05-08T02:42:42.580Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=retention", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=retention", "contentDisposition": "attachment; filename=\"retention-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "retention" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "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." ] } }, "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" } } ``` ## Documentation ### Core Metrics 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% ### Cohort Analysis Track by signup week, not calendar week: Horizontal axis: weeks since signup (0, 1, 2, 3...) Vertical axis: signup cohort (Jan W1, Jan W2...) Cell value: % of cohort still active Identify: Which cohorts retain better (product changes, marketing source) At which week users drop off (week 2 cliff = aha moment too late) Seasonal patterns (holiday signups retain worse) ### Churn Signals Early warning indicators (flag before churn): Login frequency drops 50%+ from baseline Core feature usage stops Support tickets spike then go silent Billing page visits without upgrade Team member removals Data export requests ### Engagement Loops Retention requires habit formation: Loop TypeTriggerActionRewardPersonalEmail digestReview updatesProgress visibleSocialNotificationRespond to teamRecognitionContentNew content alertConsumeKnowledge gainedProgressStreak reminderComplete taskStreak maintained Design for variable rewards - predictable = boring. ### Lifecycle Stages StageTimeframeGoalTacticsActivationDay 0-3Reach aha momentOnboarding, setup wizardEngagementWeek 1-4Build habitUsage nudges, tipsRetentionMonth 1+Maintain valueFeature discovery, check-insExpansionOngoingIncrease usageUpsell, team invitesReactivationAfter churnWin backCampaigns, incentives ### Reactivation Campaigns Timing matters: 7 days inactive: Soft nudge ("We miss you") 14 days inactive: Value reminder + what's new 30 days inactive: Incentive offer (discount, extended trial) 90 days inactive: Last chance + feedback ask Message formula: [Acknowledge absence] + [New value added] + [Easy re-entry CTA] "Your dashboard is waiting. We added [feature]. One click to resume →" ### Feature Stickiness Measure which features predict retention: Usage correlation: Users of feature X retain 2x better Time to feature: Users who reach feature X in day 1 retain 3x Feature breadth: Users of 3+ features retain 5x vs 1 feature Double down on sticky features in onboarding. ### Churn Prevention When churn signal detected: Immediate: In-app message acknowledging drop ("Need help?") Day 3: Email from founder (personal, not marketing) Day 7: Offer call or live support Before renewal: Proactive outreach with usage summary Cancel flow optimization: Ask reason (required, 4-5 options) Offer pause instead of cancel Show what they'll lose (data, history, price lock) Easy return policy ("reactivate anytime, data saved 90 days") ### Retention Benchmarks by Model 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% ### Common Mistakes Measuring retention from signup, not activation Treating all churned users the same (voluntary vs involuntary) Reactivation emails without new value proposition Ignoring payment failures as churn (30-40% of churn is involuntary) No segmentation in cohort analysis (power users mask problems) ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ivangdavila - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T02:42:42.580Z - Expires at: 2026-05-08T02:42:42.580Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/retention) - [Send to Agent page](https://openagent3.xyz/skills/retention/agent) - [JSON manifest](https://openagent3.xyz/skills/retention/agent.json) - [Markdown brief](https://openagent3.xyz/skills/retention/agent.md) - [Download page](https://openagent3.xyz/downloads/retention)