{"id":"02d9d530-3183-436a-98a0-0d26ec36854d","shortId":"45NYqJ","kind":"skill","title":"retention-engagement","tagline":"Improve retention and engagement: diagnosis, aha moment, lever hypotheses, experiment backlog. See also: user-onboarding (first-time UX).","description":"# Retention & Engagement\n\n## Scope\n\n**Covers**\n- Diagnosing retention + engagement (cohorts/curves, frequency, segments, drop-offs)\n- Identifying the **activation / “aha moment”** and reducing time-to-value\n- Designing habit + re-engagement interventions (daily return, reminders, content loops)\n- Creating **accruing value** and ethical **switching costs** (“mounting loss”)\n- Turning insights into a prioritized experiment + measurement plan\n\n**When to use**\n- “Improve retention / reduce churn”\n- “Increase engagement / DAU/WAU”\n- “Define our activation / aha moment”\n- “D1/D7 retention is low—fix onboarding and time-to-value”\n- “Create a retention experiment backlog and a 30/60/90 plan”\n\n**When NOT to use**\n- You don’t have (or can’t assume) a stable value proposition / ICP (use `problem-definition`).\n- You’re primarily deciding pricing/packaging/paywalls (this skill can add retention context but won’t replace pricing work).\n- You need acquisition loop design (use `designing-growth-loops`).\n- You need to synthesize qualitative churn feedback before proposing experiments (use `analyzing-user-feedback` or interviews).\n- The problem is specifically first-time onboarding UX (signup flow, empty states, guided setup) rather than full-lifecycle retention (use `user-onboarding`).\n- You want to apply behavioral science frameworks (habit loops, nudge theory, loss aversion mechanics) as the primary lens rather than a retention metrics lens (use `behavioral-product-design`).\n- You need to determine whether you have product-market fit before optimizing retention (use `measuring-product-market-fit`).\n\n## Inputs\n\n**Minimum required**\n- Product + target user/ICP and 1–2 key segments\n- Current stage (pre-PMF / early PMF / growth / mature)\n- Best-available baseline metrics (even rough):\n  - retention (D1/D7/D30 or weekly cohort), churn, engagement (DAU/WAU/MAU), activation rate, time-to-value\n- Onboarding flow summary (steps/screens + where users drop)\n- Constraints: timebox, engineering/design capacity, allowed channels (email/push/in-app), privacy/legal/brand limits\n\n**Missing-info strategy**\n- Ask up to 5 questions from [references/INTAKE.md](references/INTAKE.md), then proceed.\n- If metrics are missing, proceed with explicit assumptions and label confidence.\n- Do not request secrets or PII; prefer aggregated metrics and redacted funnels.\n\n## Outputs (deliverables)\n\nProduce a **Retention & Engagement Improvement Pack** (Markdown in-chat; or as files if requested) containing:\n\n1) Context snapshot (goal, segments, constraints, timebox)\n2) Metric definitions + guardrails (how “retention” and “engagement” are measured)\n3) Retention + engagement diagnosis (cohorts/curves, segments, drop-offs, churn drivers)\n4) Activation / aha moment definition (candidate behaviors + threshold + validation plan)\n5) Lever hypotheses map (onboarding → habit → accruing value → re-engagement)\n6) Experiment backlog (prioritized; experiment cards with success metrics + guardrails)\n7) Measurement + instrumentation plan (events, dashboards, owners if known)\n8) 30/60/90 execution plan\n9) Risks / Open questions / Next steps (always included)\n\nTemplates and checklists:\n- [references/TEMPLATES.md](references/TEMPLATES.md)\n- [references/WORKFLOW.md](references/WORKFLOW.md)\n- [references/CHECKLISTS.md](references/CHECKLISTS.md)\n- [references/RUBRIC.md](references/RUBRIC.md)\n\n## Workflow (7 steps)\n\n### 1) Intake + goal framing\n- **Inputs:** User prompt; [references/INTAKE.md](references/INTAKE.md).\n- **Actions:** Define the retention problem (segment, time horizon, metric) and the decision this work will drive (what will change). Confirm constraints (timebox, capacity, channels, privacy/brand).\n- **Outputs:** Context snapshot + metric definitions draft.\n- **Checks:** Goal is a sentence with a number and a date (e.g., “Improve paid D30 retention from 18%→24% by end of Q2”).\n\n### 2) Data + instrumentation sanity check\n- **Inputs:** Current tracking/events (or best guess), funnel steps, dashboards (if any).\n- **Actions:** List what you can/can’t measure today. Define the minimum event schema needed to learn (activation, engagement, churn). Identify 1–3 highest-impact instrumentation gaps.\n- **Outputs:** Instrumentation gap list + “minimum viable measurement” plan.\n- **Checks:** Every key metric in the goal has a data source or an explicit assumption.\n\n### 3) Diagnose: where retention fails (and why)\n- **Inputs:** Baseline metrics, cohorts/curves, funnel drop-offs, segments, any churn feedback.\n- **Actions:** Build a diagnosis across three failure modes:\n  - **Activation failure** (users never reach value)\n  - **Engagement decay** (users get value once, don’t build a habit)\n  - **Monetization churn** (value exists, but price/packaging/friction drives churn)\n  Segment results (at least 2 segments) and identify the largest “leak.”\n- **Outputs:** Retention + engagement diagnosis table + primary failure mode(s).\n- **Checks:** Diagnosis points to one primary lever to test first (onboarding vs habit vs value vs comms).\n\n### 4) Define the activation / “aha moment” (data-backed)\n- **Inputs:** Candidate value behaviors + journey; usage events; retention outcome definition.\n- **Actions:** Propose 3–5 candidate “aha” behaviors, then define an activation threshold (e.g., “uses X feature twice within 7 days” or “invites 2 teammates + uses 2 key features within 14 days”). Document how you’ll validate (correlation with D30/D60 retention; holdout if possible).\n- **Outputs:** Activation/aha moment spec + validation plan + tracking requirements.\n- **Checks:** The activation definition is behavioral and measurable (not a survey response or opinion).\n\n### 5) Generate lever hypotheses (convert insights → rules)\n- **Inputs:** Diagnosis + activation spec; constraints.\n- **Actions:** Create a lever map with hypotheses tied to failure modes:\n  - **Onboarding/time-to-value:** get users to aha faster and more reliably\n  - **Habit/daily return:** design cues, routines, rewards; reduce friction to “come back tomorrow”\n  - **Accruing value + mounting loss (ethical):** personalization, progress/history, saved work, identity/data repository\n  - **Re-engagement:** lifecycle messaging, winback, content reminders, in-product nudges\n  Convert each hypothesis into a rule + check (see [references/SOURCE_SUMMARY.md](references/SOURCE_SUMMARY.md)).\n- **Outputs:** Lever hypotheses map + candidate interventions.\n- **Checks:** Every hypothesis ties to (a) a failure mode, and (b) a measurable leading indicator.\n\n### 6) Design + prioritize experiments (with measurement)\n- **Inputs:** Hypotheses; measurement plan; capacity.\n- **Actions:** Turn top hypotheses into experiment cards (1–2 weeks each). Prioritize using a simple score (Impact × Confidence ÷ Effort). Define success metrics and guardrails; note required instrumentation and rollout/rollback.\n- **Outputs:** Prioritized experiment backlog + experiment cards + metric/guardrail spec.\n- **Checks:** Top 3 experiments are runnable with current constraints and have unambiguous “win/lose/learn” criteria.\n\n### 7) Build the 30/60/90 plan + quality gate\n- **Inputs:** Draft pack; [references/CHECKLISTS.md](references/CHECKLISTS.md) and [references/RUBRIC.md](references/RUBRIC.md).\n- **Actions:** Sequence work into a 30/60/90 plan (instrumentation, experiments, analysis cadence). Run the checklist and score the rubric. Always include **Risks / Open questions / Next steps**.\n- **Outputs:** Final Retention & Engagement Improvement Pack.\n- **Checks:** Next 2 weeks of work are unblocked; measurement is in place to learn.\n\n## Anti-patterns (common failure modes)\n\n1. **Vanity-metric retention** — Reporting DAU/MAU ratios without segmenting by cohort or user type; masks churn behind new-user influx and leads to false confidence.\n2. **Notification spam as \"re-engagement\"** — Defaulting to push/email frequency increases instead of addressing the underlying value gap; temporarily lifts open rates but accelerates unsubscribes and erodes trust.\n3. **Activation theater** — Defining the \"aha moment\" based on internal opinion (\"they saw the dashboard\") rather than correlating specific behaviors with downstream retention; produces interventions that move a proxy but not real retention.\n4. **One-size-fits-all diagnosis** — Running the same retention playbook for all segments instead of diagnosing distinct failure modes (activation failure vs. engagement decay vs. monetization churn) per segment; wastes experiment capacity on wrong levers.\n5. **Dark-pattern switching costs** — Engineering \"mounting loss\" that traps users (hidden data lock-in, punitive cancellation flows) rather than building genuinely accruing value; creates regulatory risk and brand damage.\n\n## Quality gate (required)\n- Use [references/CHECKLISTS.md](references/CHECKLISTS.md) and [references/RUBRIC.md](references/RUBRIC.md).\n- Always include: **Risks**, **Open questions**, **Next steps**.\n\n## Examples\n\n**Example 1 (B2C subscription, churn reduction):**  \n“Use `retention-engagement`. Product: meditation app. Segment: paid subscribers. Baseline: D30 paid retention 22%, churn spikes after week 2. Constraint: 4-week sprint, no major redesign. Output: a Retention & Engagement Improvement Pack with an activation/aha definition, a diagnosis, and a prioritized experiment backlog + 30/60/90 plan.”\n\n**Example 2 (B2B SaaS, activation + habit):**  \n“New users activate but don’t return weekly. Define our aha moment, identify the biggest engagement decay point, and propose 5 experiments (in-product + email) with success metrics and guardrails.”\n\n**Boundary example (upstream problem):**\n“Write a brand new value prop and pick an ICP for our product.”\nResponse: that’s upstream strategy/problem definition; use `problem-definition` (and optionally PMF measurement) before retention optimization.\n\n**Boundary example (onboarding-specific):**\n“Redesign our signup flow and first-time empty states to reduce drop-off before activation.”\nResponse: this is first-time onboarding UX, not full-lifecycle retention; use `user-onboarding` for signup-to-activation flow design. Come back to `retention-engagement` once users are activated and you need to improve post-activation retention.\n\n**Boundary example (growth loop design):**\n“Design a referral loop so our existing users bring in new users.”\nResponse: referral/viral loop design is acquisition, not retention; use `designing-growth-loops`. This skill focuses on keeping existing users engaged and retained, not on building loops that acquire new users.","tags":["retention","engagement","lenny","skills","plus","liqiongyu","agent-skills","ai-agents","automation","claude","codex","prompt-engineering"],"capabilities":["skill","source-liqiongyu","skill-retention-engagement","topic-agent-skills","topic-ai-agents","topic-automation","topic-claude","topic-codex","topic-prompt-engineering","topic-refoundai","topic-skillpack"],"categories":["lenny_skills_plus"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/liqiongyu/lenny_skills_plus/retention-engagement","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add liqiongyu/lenny_skills_plus","source_repo":"https://github.com/liqiongyu/lenny_skills_plus","install_from":"skills.sh"}},"qualityScore":"0.474","qualityRationale":"deterministic score 0.47 from registry signals: · indexed on github topic:agent-skills · 49 github stars · SKILL.md body (10,561 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T00:56:24.722Z","embedding":null,"createdAt":"2026-04-18T22:16:58.727Z","updatedAt":"2026-04-22T00:56:24.722Z","lastSeenAt":"2026-04-22T00:56:24.722Z","tsv":"'1':257,362,456,555,874,984,1160 '14':722 '18':513 '2':258,369,519,641,715,718,875,966,1011,1184,1212 '22':1179 '24':514 '3':379,556,585,695,906,1040 '30/60/90':109,431,921,938,1209 '4':390,674,1073,1186 '5':314,400,696,758,1110,1237 '6':411,856 '7':421,454,711,918 '8':430 '9':434 'acceler':1035 'accru':60,406,802,1134 'acquir':1392 'acquisit':151,1369 'across':608 'action':465,535,604,693,770,867,933 'activ':39,88,285,391,551,612,677,703,746,767,1041,1094,1215,1219,1303,1325,1337,1345 'activation/aha':737,1200 'add':140 'address':1025 'aggreg':339 'aha':9,40,89,392,678,698,785,1045,1227 'allow':302 'also':16 'alway':440,951,1151 'analysi':942 'analyz':171 'analyzing-user-feedback':170 'anti':979 'anti-pattern':978 'app':1171 'appli':204 'ask':311 'assum':122 'assumpt':328,584 'avail':272 'avers':213 'b':851 'b2b':1213 'b2c':1161 'back':682,800,1329 'backlog':14,106,413,899,1208 'base':1047 'baselin':273,593,1175 'behavior':205,227,396,686,699,749,1059 'behavioral-product-design':226 'behind':1001 'best':271,528 'best-avail':270 'biggest':1231 'boundari':1248,1282,1347 'brand':1140,1254 'bring':1360 'build':605,626,919,1132,1389 'cadenc':943 'can/can':539 'cancel':1128 'candid':395,684,697,839 'capac':301,487,866,1106 'card':416,873,901 'chang':483 'channel':303,488 'chat':355 'check':496,523,570,657,744,831,841,904,964 'checklist':444,946 'churn':82,164,282,388,553,602,630,636,1000,1101,1163,1180 'cohort':281,995 'cohorts/curves':31,383,595 'come':799,1328 'comm':673 'common':981 'confid':331,884,1010 'confirm':484 'constraint':298,367,485,769,912,1185 'contain':361 'content':57,819 'context':142,363,491 'convert':762,825 'correl':729,1057 'cost':65,1115 'cover':27 'creat':59,102,771,1136 'criteria':917 'cue':793 'current':261,525,911 'd1/d7':91 'd1/d7/d30':278 'd30':510,1176 'd30/d60':731 'daili':54 'damag':1141 'dark':1112 'dark-pattern':1111 'dashboard':426,532,1054 'data':520,579,681,1123 'data-back':680 'date':506 'dau/mau':990 'dau/wau':85 'dau/wau/mau':284 'day':712,723 'decay':619,1098,1233 'decid':135 'decis':476 'default':1018 'defin':86,466,543,675,701,886,1043,1225 'definit':131,371,394,494,692,747,1201,1270,1274 'deliver':345 'design':48,153,156,229,792,857,1327,1351,1352,1367,1374 'designing-growth-loop':155,1373 'determin':233 'diagnos':28,586,1090 'diagnosi':8,382,607,651,658,766,1079,1203 'distinct':1091 'document':724 'downstream':1061 'draft':495,926 'drive':480,635 'driver':389 'drop':35,297,386,598,1300 'drop-off':34,385,597,1299 'e.g':507,705 'earli':266 'effort':885 'email':1242 'email/push/in-app':304 'empti':187,1295 'end':516 'engag':3,7,25,30,52,84,283,349,376,381,410,552,618,650,815,961,1017,1097,1168,1195,1232,1333,1384 'engin':1116 'engineering/design':300 'erod':1038 'ethic':63,806 'even':275 'event':425,546,689 'everi':571,842 'exampl':1158,1159,1211,1249,1283,1348 'execut':432 'exist':632,1358,1382 'experi':13,73,105,168,412,415,859,872,898,900,907,941,1105,1207,1238 'explicit':327,583 'fail':589 'failur':610,613,654,779,848,982,1092,1095 'fals':1009 'faster':786 'featur':708,720 'feedback':165,173,603 'file':358 'final':959 'first':21,181,666,1293,1308 'first-tim':20,180,1292,1307 'fit':240,249,1077 'fix':95 'flow':186,292,1129,1290,1326 'focus':1379 'frame':459 'framework':207 'frequenc':32,1021 'friction':797 'full':194,1314 'full-lifecycl':193,1313 'funnel':343,530,596 'gap':561,564,1029 'gate':924,1143 'generat':759 'genuin':1133 'get':621,782 'goal':365,458,497,576 'growth':157,268,1349,1375 'guardrail':372,420,890,1247 'guess':529 'guid':189 'habit':49,208,405,628,669,1216 'habit/daily':790 'hidden':1122 'highest':558 'highest-impact':557 'holdout':733 'horizon':472 'hypothes':12,402,761,776,837,863,870 'hypothesi':827,843 'icp':127,1261 'identifi':37,554,644,1229 'identity/data':811 'impact':559,883 'improv':4,79,350,508,962,1196,1342 'in-chat':353 'in-product':821,1239 'includ':441,952,1152 'increas':83,1022 'indic':855 'influx':1005 'info':309 'input':250,460,524,592,683,765,862,925 'insight':69,763 'instead':1023,1088 'instrument':423,521,560,563,893,940 'intak':457 'intern':1049 'intervent':53,840,1064 'interview':175 'invit':714 'journey':687 'keep':1381 'key':259,572,719 'known':429 'label':330 'largest':646 'lead':854,1007 'leak':647 'learn':550,977 'least':640 'len':218,224 'lever':11,401,663,760,773,836,1109 'lifecycl':195,816,1315 'lift':1031 'limit':306 'list':536,565 'll':727 'lock':1125 'lock-in':1124 'loop':58,152,158,209,1350,1355,1366,1376,1390 'loss':67,212,805,1118 'low':94 'major':1190 'map':403,774,838 'markdown':352 'market':239,248 'mask':999 'matur':269 'measur':74,246,378,422,541,568,751,853,861,864,972,1278 'measuring-product-market-fit':245 'mechan':214 'medit':1170 'messag':817 'metric':223,274,322,340,370,419,473,493,573,594,888,987,1245 'metric/guardrail':902 'minimum':251,545,566 'miss':308,324 'missing-info':307 'mode':611,655,780,849,983,1093 'moment':10,41,90,393,679,738,1046,1228 'monet':629,1100 'mount':66,804,1117 'move':1066 'need':150,160,231,548,1340 'never':615 'new':1003,1217,1255,1362,1393 'new-us':1002 'next':438,956,965,1156 'note':891 'notif':1012 'nudg':210,824 'number':503 'off':36,387,599 'onboard':19,96,183,200,291,404,667,1285,1310,1320 'onboarding-specif':1284 'onboarding/time-to-value':781 'one':661,1075 'one-size-fits-al':1074 'open':436,954,1032,1154 'opinion':757,1050 'optim':242,1281 'option':1276 'outcom':691 'output':344,490,562,648,736,835,896,958,1192 'owner':427 'pack':351,927,963,1197 'paid':509,1173,1177 'pattern':980,1113 'per':1102 'person':807 'pick':1259 'pii':337 'place':975 'plan':75,110,399,424,433,569,741,865,922,939,1210 'playbook':1084 'pmf':265,267,1277 'point':659,1234 'possibl':735 'post':1344 'post-activ':1343 'pre':264 'pre-pmf':263 'prefer':338 'price':147 'price/packaging/friction':634 'pricing/packaging/paywalls':136 'primari':217,653,662 'primarili':134 'priorit':72,414,858,878,897,1206 'privacy/brand':489 'privacy/legal/brand':305 'problem':130,177,469,1251,1273 'problem-definit':129,1272 'proceed':320,325 'produc':346,1063 'product':228,238,247,253,823,1169,1241,1264 'product-market':237 'progress/history':808 'prompt':462 'prop':1257 'propos':167,694,1236 'proposit':126 'proxi':1068 'punit':1127 'push/email':1020 'q2':518 'qualit':163 'qualiti':923,1142 'question':315,437,955,1155 'rate':286,1033 'rather':191,219,1055,1130 'ratio':991 're':51,133,409,814,1016 're-engag':50,408,813,1015 'reach':616 'real':1071 'redact':342 'redesign':1191,1287 'reduc':43,81,796,1298 'reduct':1164 'references/checklists.md':449,450,928,929,1146,1147 'references/intake.md':317,318,463,464 'references/rubric.md':451,452,931,932,1149,1150 'references/source_summary.md':833,834 'references/templates.md':445,446 'references/workflow.md':447,448 'referr':1354 'referral/viral':1365 'regulatori':1137 'reliabl':789 'remind':56,820 'replac':146 'report':989 'repositori':812 'request':334,360 'requir':252,743,892,1144 'respons':755,1265,1304,1364 'result':638 'retain':1386 'retent':2,5,24,29,80,92,104,141,196,222,243,277,348,374,380,468,511,588,649,690,732,960,988,1062,1072,1083,1167,1178,1194,1280,1316,1332,1346,1371 'retention-engag':1,1166,1331 'return':55,791,1223 'reward':795 'risk':435,953,1138,1153 'rollout/rollback':895 'rough':276 'routin':794 'rubric':950 'rule':764,830 'run':944,1080 'runnabl':909 'saa':1214 'saniti':522 'save':809 'saw':1052 'schema':547 'scienc':206 'scope':26 'score':882,948 'secret':335 'see':15,832 'segment':33,260,366,384,470,600,637,642,993,1087,1103,1172 'sentenc':500 'sequenc':934 'setup':190 'signup':185,1289,1323 'signup-to-activ':1322 'simpl':881 'size':1076 'skill':138,1378 'skill-retention-engagement' 'snapshot':364,492 'sourc':580 'source-liqiongyu' 'spam':1013 'spec':739,768,903 'specif':179,1058,1286 'spike':1181 'sprint':1188 'stabl':124 'stage':262 'state':188,1296 'step':439,455,531,957,1157 'steps/screens':294 'strategi':310 'strategy/problem':1269 'subscrib':1174 'subscript':1162 'success':418,887,1244 'summari':293 'survey':754 'switch':64,1114 'synthes':162 'tabl':652 'target':254 'teammat':716 'templat':442 'temporarili':1030 'test':665 'theater':1042 'theori':211 'three':609 'threshold':397,704 'tie':777,844 'time':22,45,99,182,288,471,1294,1309 'time-to-valu':44,98,287 'timebox':299,368,486 'today':542 'tomorrow':801 'top':869,905 'topic-agent-skills' 'topic-ai-agents' 'topic-automation' 'topic-claude' 'topic-codex' 'topic-prompt-engineering' 'topic-refoundai' 'topic-skillpack' 'track':742 'tracking/events':526 'trap':1120 'trust':1039 'turn':68,868 'twice':709 'type':998 'unambigu':915 'unblock':971 'under':1027 'unsubscrib':1036 'upstream':1250,1268 'usag':688 'use':78,114,128,154,169,197,225,244,706,717,879,1145,1165,1271,1317,1372 'user':18,172,199,296,461,614,620,783,997,1004,1121,1218,1319,1335,1359,1363,1383,1394 'user-onboard':17,198,1318 'user/icp':255 'ux':23,184,1311 'valid':398,728,740 'valu':47,61,101,125,290,407,617,622,631,671,685,803,1028,1135,1256 'vaniti':986 'vanity-metr':985 'viabl':567 'vs':668,670,672,1096,1099 'want':202 'wast':1104 'week':280,876,967,1183,1187,1224 'whether':234 'win/lose/learn':916 'winback':818 'within':710,721 'without':992 'won':144 'work':148,478,810,935,969 'workflow':453 'write':1252 'wrong':1108 'x':707","prices":[{"id":"e74842d8-1ab8-4b9d-98a1-9f8cb62fc591","listingId":"02d9d530-3183-436a-98a0-0d26ec36854d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"liqiongyu","category":"lenny_skills_plus","install_from":"skills.sh"},"createdAt":"2026-04-18T22:16:58.727Z"}],"sources":[{"listingId":"02d9d530-3183-436a-98a0-0d26ec36854d","source":"github","sourceId":"liqiongyu/lenny_skills_plus/retention-engagement","sourceUrl":"https://github.com/liqiongyu/lenny_skills_plus/tree/main/skills/retention-engagement","isPrimary":false,"firstSeenAt":"2026-04-18T22:16:58.727Z","lastSeenAt":"2026-04-22T00:56:24.722Z"}],"details":{"listingId":"02d9d530-3183-436a-98a0-0d26ec36854d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"liqiongyu","slug":"retention-engagement","github":{"repo":"liqiongyu/lenny_skills_plus","stars":49,"topics":["agent-skills","ai-agents","automation","claude","codex","prompt-engineering","refoundai","skillpack"],"license":"apache-2.0","html_url":"https://github.com/liqiongyu/lenny_skills_plus","pushed_at":"2026-04-04T06:30:11Z","description":"86 agent-executable skill packs converted from RefoundAI’s Lenny skills (unofficial). Works with Codex + Claude Code.","skill_md_sha":"4cd1014d88377d6c7d935d363d134165279fb5c3","skill_md_path":"skills/retention-engagement/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/liqiongyu/lenny_skills_plus/tree/main/skills/retention-engagement"},"layout":"multi","source":"github","category":"lenny_skills_plus","frontmatter":{"name":"retention-engagement","description":"Improve retention and engagement: diagnosis, aha moment, lever hypotheses, experiment backlog. See also: user-onboarding (first-time UX)."},"skills_sh_url":"https://skills.sh/liqiongyu/lenny_skills_plus/retention-engagement"},"updatedAt":"2026-04-22T00:56:24.722Z"}}