{"id":"161f603f-c2ae-4e84-b190-df66e5e3d201","shortId":"seT2tS","kind":"skill","title":"linkedin-micro-campaigns","tagline":"Create precision-targeted LinkedIn ad campaigns for specific ICP segments — translates CRM data to LinkedIn targeting","description":"# LinkedIn Micro Campaigns\n\nCreate highly targeted LinkedIn ad campaigns for specific ICP segments. Translates your Ideal Customer Profile (from CRM data or manual input) into precision LinkedIn targeting criteria, estimates audience sizes, and builds campaign groups with campaigns and creatives.\n\n**Requires:** Cogny Agent subscription ($9/mo) — [Sign up](https://cogny.com/agent)\n\n**Tip:** Run `/crm-icp-analysis` first to generate a data-driven ICP, then feed the output into this skill. You can also run `/crm-sales-momentum` to identify which segments close fastest and target those specifically.\n\n## Usage\n\n`/linkedin-micro-campaigns \"VP Marketing at SaaS companies, 200-1000 employees\"` — create campaigns from a description\n`/linkedin-micro-campaigns` — pull ICP from HubSpot CRM data automatically\n\n## Prerequisites Check\n\nVerify LinkedIn Ads access (required):\n\n```\nlinkedin_ads__tool_list_ad_accounts\n```\n\nIf HubSpot is also connected (for automatic ICP extraction), verify:\n\n```\nhubspot__get_user_details\n```\n\nIf LinkedIn Ads is not available:\n\n```\nThis skill requires Cogny's LinkedIn Ads MCP server.\nSign up at https://cogny.com/agent and connect your LinkedIn Ads account.\n\nHubSpot is optional — if connected, ICP data is extracted automatically.\nWithout HubSpot, provide your ICP description as an argument.\n```\n\n## Steps\n\n### 1. Establish ICP targeting inputs\n\n**If ICP description is provided as argument**, parse it for:\n- Job titles / functions / seniority\n- Industries\n- Company sizes\n- Geographic targets\n- Any other targeting dimensions mentioned\n\n**If no argument is provided and HubSpot is connected**, extract ICP from CRM:\n\nPull closed-won deal data to identify top-performing segments:\n\n```\nhubspot__search_crm_objects(\n  objectType: \"deals\",\n  filterGroups: [{\"filters\": [{\"propertyName\": \"dealstage\", \"operator\": \"EQ\", \"value\": \"closedwon\"}]}],\n  properties: [\"dealname\", \"amount\", \"closedate\"],\n  sorts: [{\"propertyName\": \"closedate\", \"direction\": \"DESCENDING\"}],\n  limit: 50\n)\n```\n\nFetch associated companies and contacts to extract:\n- **Top industries** from winning companies\n- **Company size bands** from winning companies\n- **Job titles and seniority** from buyer contacts\n- **Geographies** from winning companies\n\nGroup into 2-3 distinct micro-segments based on the data (e.g., \"Enterprise Marketing Leaders\", \"Mid-Market Sales Directors\", \"Startup Founders\").\n\n### 2. Translate ICP to LinkedIn targeting facets\n\nFor each micro-segment, map ICP dimensions to LinkedIn targeting entities.\n\n**Job Titles** — search for exact LinkedIn targeting entities:\n```\nlinkedin_ads__tool_search_targeting_entities(facet_urn: \"urn:li:adTargetingFacet:titles\", query: \"<title from ICP>\")\n```\n\n**Job Functions:**\n```\nlinkedin_ads__tool_get_targeting_facets()\n```\nThen search within job functions for relevant matches.\n\n**Seniorities:**\n```\nlinkedin_ads__tool_search_targeting_entities(facet_urn: \"urn:li:adTargetingFacet:seniorities\", query: \"<level>\")\n```\n\n**Industries:**\n```\nlinkedin_ads__tool_search_targeting_entities(facet_urn: \"urn:li:adTargetingFacet:industries\", query: \"<industry from ICP>\")\n```\n\n**Company Sizes:**\n```\nlinkedin_ads__tool_search_targeting_entities(facet_urn: \"urn:li:adTargetingFacet:staffCountRanges\", query: \"<size range>\")\n```\n\n**Locations:**\n```\nlinkedin_ads__tool_search_targeting_entities(facet_urn: \"urn:li:adTargetingFacet:locations\", query: \"<geo from ICP>\")\n```\n\nBuild the targeting criteria object for each micro-segment using AND logic:\n```json\n{\n  \"include\": {\n    \"and\": [\n      {\"or\": {\"urn:li:adTargetingFacet:titles\": [\"<title URNs>\"]}},\n      {\"or\": {\"urn:li:adTargetingFacet:seniorities\": [\"<seniority URNs>\"]}},\n      {\"or\": {\"urn:li:adTargetingFacet:industries\": [\"<industry URNs>\"]}},\n      {\"or\": {\"urn:li:adTargetingFacet:staffCountRanges\": [\"<size URNs>\"]}},\n      {\"or\": {\"urn:li:adTargetingFacet:locations\": [\"<location URNs>\"]}}\n    ]\n  }\n}\n```\n\n### 3. Estimate audience sizes\n\nFor each micro-segment targeting combination, check the audience size:\n\n```\nlinkedin_ads__tool_get_audience_counts(ad_account_id: <id>, targeting_criteria: <targeting object>)\n```\n\nEvaluate each segment:\n- **Too narrow** (<1,000): broaden titles or add related job functions\n- **Narrow but viable** (1,000-10,000): good for ABM, may need higher bids\n- **Sweet spot** (10,000-100,000): ideal for micro-campaigns\n- **Too broad** (>300,000): add more filters to tighten\n\nIterate on targeting until each segment hits a viable audience size. Document adjustments made.\n\n### 4. Check for overlap with existing campaigns\n\nReview existing campaigns to avoid audience overlap:\n\n```\nlinkedin_ads__tool_get_campaign_groups(ad_account_id: <id>)\nlinkedin_ads__tool_get_campaigns(ad_account_id: <id>, status_filter: \"ACTIVE\")\n```\n\nFor each active campaign, compare targeting criteria. Flag overlaps and recommend:\n- Exclude overlapping audiences\n- Merge with existing campaigns if targeting is very similar\n- Proceed if distinct enough\n\n### 5. Present campaign structure for approval\n\n**CRITICAL: Wait for user approval before creating anything.**\n\nPresent the proposed structure:\n\n```\n┌─────────────────────────────────────────────────────────────────────┐\n│ PROPOSED MICRO-CAMPAIGN STRUCTURE                                   │\n├─────────────────────────────────────────────────────────────────────┤\n│                                                                     │\n│ Campaign Group: \"[ICP Segment] — Micro Campaigns\"                   │\n│                                                                     │\n│ ├── Campaign 1: \"[Segment A Name]\"                                  │\n│ │   Objective: [Lead Gen / Website Visits / Engagement]             │\n│ │   Targeting:                                                      │\n│ │     Titles: [list]                                                │\n│ │     Seniority: [level]                                            │\n│ │     Industries: [list]                                            │\n│ │     Company Size: [range]                                         │\n│ │     Location: [geo]                                               │\n│ │   Est. Audience: [N]                                              │\n│ │   Daily Budget: $[X]                                              │\n│ │   Bid Strategy: [strategy]                                        │\n│ │                                                                   │\n│ ├── Campaign 2: \"[Segment B Name]\"                                  │\n│ │   [same structure]                                                │\n│ │                                                                   │\n│ └── Campaign 3: \"[Segment C Name]\"                                  │\n│     [same structure]                                                │\n│                                                                     │\n│ Total Daily Budget: $[X]                                            │\n│ Total Est. Audience: [N]                                            │\n│ Recommended Duration: [N] weeks minimum                             │\n└─────────────────────────────────────────────────────────────────────┘\n\nApprove all? Or select specific campaigns (e.g., \"1 and 2 only\")\n```\n\n### 6. Create campaign group\n\nAfter user approval, create the campaign group:\n\n```\nlinkedin_ads__tool_create_campaign_group(\n  ad_account_id: <id>,\n  name: \"[ICP Segment] — Micro Campaigns\",\n  status: \"PAUSED\"\n)\n```\n\n### 7. Create campaigns\n\nFor each approved micro-segment, create a campaign in PAUSED status:\n\n```\nlinkedin_ads__tool_create_campaign(\n  ad_account_id: <id>,\n  campaign_group_id: <group_id>,\n  name: \"[Segment Name]\",\n  objective_type: \"LEAD_GENERATION\",\n  targeting_criteria: <targeting object from step 2>,\n  daily_budget_amount: <amount>,\n  daily_budget_currency: \"USD\",\n  cost_type: \"CPM\",\n  status: \"PAUSED\"\n)\n```\n\nAll campaigns are created PAUSED — the user controls when to activate.\n\n### 8. Create creatives\n\nFor each campaign, create 2 creative variations for A/B testing.\n\nAsk the user for:\n- Landing page URL\n- Any specific messaging, value props, or offers to include\n\nThen create variations:\n\n**Variation A — Pain point focus:**\n```\nlinkedin_ads__tool_create_creative(\n  campaign_id: <id>,\n  commentary: \"<Segment-specific pain point intro — 150 chars visible>\",\n  share_media_title: \"<Pain point headline — 70 chars max>\",\n  share_media_description: \"<Supporting detail>\",\n  destination_url: \"<landing page URL>\",\n  call_to_action_type: \"LEARN_MORE\",\n  status: \"PAUSED\"\n)\n```\n\n**Variation B — Outcome focus:**\n```\nlinkedin_ads__tool_create_creative(\n  campaign_id: <id>,\n  commentary: \"<Segment-specific outcome/result intro — 150 chars visible>\",\n  share_media_title: \"<Outcome headline — 70 chars max>\",\n  share_media_description: \"<Supporting detail>\",\n  destination_url: \"<landing page URL>\",\n  call_to_action_type: \"LEARN_MORE\",\n  status: \"PAUSED\"\n)\n```\n\nCreative guidelines per segment:\n- **Headlines**: reference the persona's role or pain point directly\n- **Intro text**: speak to the specific segment's challenges, not generic benefits\n- **CTA**: match the campaign objective (LEARN_MORE for awareness, SIGN_UP for lead gen, REQUEST_DEMO for high-intent)\n\n### 9. Output campaign summary\n\n```\nLinkedIn Micro Campaigns — Created\n═══════════════════════════════════════════════════\n\nCampaign Group: [Name] (PAUSED)\nAd Account: [Account Name]\n\n┌──────────────────────┬──────────┬───────────┬──────────┬──────────────┐\n│ Campaign             │ Audience │ Budget/day│ Status   │ Creatives    │\n├──────────────────────┼──────────┼───────────┼──────────┼──────────────┤\n│ [Segment A]          │ [N]      │ $[X]      │ PAUSED   │ 2 variations │\n│ [Segment B]          │ [N]      │ $[X]      │ PAUSED   │ 2 variations │\n│ [Segment C]          │ [N]      │ $[X]      │ PAUSED   │ 2 variations │\n├──────────────────────┼──────────┼───────────┼──────────┼──────────────┤\n│ TOTAL                │ [N]      │ $[X]      │          │ [N] total    │\n└──────────────────────┴──────────┴───────────┴──────────┴──────────────┘\n\nTargeting Summary per Campaign:\n[Campaign 1]: [titles] + [seniority] + [industries] + [size] + [geo]\n[Campaign 2]: [titles] + [seniority] + [industries] + [size] + [geo]\n[Campaign 3]: [titles] + [seniority] + [industries] + [size] + [geo]\n\nICP Data Source: [HubSpot CRM / Manual Input]\nDeals Analyzed: [N] (if from CRM)\n\nNext Steps:\n1. Review creatives and update copy/images as needed\n2. Set campaign group status to ACTIVE when ready to launch\n3. Monitor for 7 days before optimizing\n4. Run /linkedin-ads-audit after 14 days to evaluate performance\n\nEstimated Monthly Spend: $[X]\nEstimated Monthly Reach: [N] impressions\n```\n\n### 10. Record findings\n\nFor each micro-campaign created, call `mcp__cogny__create_finding`:\n\n```json\n{\n  \"title\": \"Micro-campaign created: VP Marketing at SaaS 200-1K employees (audience: 34,200)\",\n  \"body\": \"Created LinkedIn campaign targeting VP/Director Marketing at SaaS companies with 200-1000 employees in US/UK. Audience size 34,200. Daily budget $50. Based on CRM analysis showing this segment has 42% win rate and $45K avg deal size. 2 creative variations (pain point + outcome). Campaign in PAUSED status.\",\n  \"action_type\": \"campaign_creation\",\n  \"expected_outcome\": \"Generate 15-25 qualified leads per month at <$80 CPL\",\n  \"estimated_impact_usd\": 3000,\n  \"priority\": \"medium\"\n}\n```\n\nAction types for micro-campaigns:\n- `campaign_creation` — new campaigns built from ICP data\n- `targeting_refinement` — audience adjustments based on size/overlap\n- `creative_refresh` — new ad variations for testing\n- `budget_optimization` — spend reallocation across segments\n- `audience_overlap` — overlap detection and exclusion recommendations","tags":["linkedin","micro","campaigns","claude","code","marketing","skills","cognyai","agent-skills","ai-agents","claude-code","claude-skills"],"capabilities":["skill","source-cognyai","skill-linkedin-micro-campaigns","topic-agent-skills","topic-ai-agents","topic-claude-code","topic-claude-skills","topic-cluade-mcp","topic-cursor","topic-geo","topic-growth-hacking","topic-llm","topic-marketing","topic-mcp","topic-seo"],"categories":["claude-code-marketing-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/cognyai/claude-code-marketing-skills/linkedin-micro-campaigns","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add cognyai/claude-code-marketing-skills","source_repo":"https://github.com/cognyai/claude-code-marketing-skills","install_from":"skills.sh"}},"qualityScore":"0.471","qualityRationale":"deterministic score 0.47 from registry signals: · indexed on github topic:agent-skills · 42 github stars · SKILL.md body (11,731 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":"2026-05-01T06:56:27.112Z","embedding":null,"createdAt":"2026-04-18T22:23:39.028Z","updatedAt":"2026-05-01T06:56:27.112Z","lastSeenAt":"2026-05-01T06:56:27.112Z","tsv":"'-1':1139 '-10':532 '-100':545 '-1000':113,1157 '-25':1202 '-3':313 '/agent':175 '/agent)':71 '/crm-icp-analysis':74 '/crm-sales-momentum':94 '/linkedin-ads-audit':1098 '/linkedin-micro-campaigns':106,120 '000':519,531,533,544,546,555 '1':202,518,530,666,731,1035,1070 '10':543,1114 '14':1100 '15':1201 '150':871,913 '2':312,333,698,733,827,1009,1016,1023,1042,1078,1184 '200':112,1138,1144,1156,1164 '3':487,705,1049,1089 '300':554 '3000':1213 '34':1143,1163 '4':575,1096 '42':1176 '45k':1180 '5':636 '50':280,1167 '6':735 '7':762,1092 '70':880,921 '8':820 '80':1208 '9':983 '9/mo':66 'a/b':831 'abm':536 'access':133 'account':140,181,509,596,604,753,783,996,997 'across':1248 'action':890,931,1194,1216 'activ':608,611,819,1084 'ad':10,29,132,136,139,157,167,180,361,376,391,405,420,434,503,508,590,595,599,603,747,752,778,782,858,901,995,1240 'add':523,556 'adjust':573,1233 'adtargetingfacet':370,400,414,429,443,465,470,475,480,485 'agent':64 'also':92,144 'amount':272,799 'analysi':1171 'analyz':1063 'anyth':649 'approv':641,646,724,741,767 'argument':200,213,233 'ask':833 'associ':282 'audienc':52,489,500,506,570,587,622,689,717,1000,1142,1161,1232,1250 'automat':127,147,191 'avail':160 'avg':1181 'avoid':586 'awar':971 'b':700,897,1012 'band':295 'base':318,1168,1234 'benefit':962 'bid':540,694 'bodi':1145 'broad':553 'broaden':520 'budget':692,713,798,801,1166,1244 'budget/day':1001 'build':55,446 'built':1226 'buyer':304 'c':707,1019 'call':888,929,1123 'campaign':4,11,24,30,56,59,116,551,581,584,593,602,612,626,638,657,659,664,665,697,704,729,737,744,750,759,764,773,781,785,810,825,862,905,966,985,989,991,999,1033,1034,1041,1048,1080,1121,1132,1148,1190,1196,1221,1222,1225 'challeng':959 'char':872,881,914,922 'check':129,498,576 'close':99,246 'closed':273,276 'closed-won':245 'closedwon':269 'cogni':63,164,1125 'cogny.com':70,174 'cogny.com/agent':173 'cogny.com/agent)':69 'combin':497 'commentari':864,907 'compani':111,222,283,292,293,298,309,417,683,1154 'compar':613 'connect':145,177,186,239 'contact':285,305 'control':816 'copy/images':1075 'cost':804 'count':507 'cpl':1209 'cpm':806 'creat':5,25,115,648,736,742,749,763,771,780,812,821,826,850,860,903,990,1122,1126,1133,1146 'creation':1197,1223 'creativ':61,822,828,861,904,937,1003,1072,1185,1237 'criteria':50,449,512,615,796 'critic':642 'crm':17,41,125,243,258,1059,1067,1170 'cta':963 'currenc':802 'custom':38 'daili':691,712,797,800,1165 'data':18,42,80,126,188,249,321,1056,1229 'data-driven':79 'day':1093,1101 'deal':248,261,1062,1182 'dealnam':271 'dealstag':265 'demo':978 'descend':278 'descript':119,197,209,885,926 'destin':886,927 'detail':154 'detect':1253 'dimens':229,347 'direct':277,950 'director':330 'distinct':314,634 'document':572 'driven':81 'durat':720 'e.g':322,730 'employe':114,1141,1158 'engag':675 'enough':635 'enterpris':323 'entiti':351,359,365,395,409,424,438 'eq':267 'est':688,716 'establish':203 'estim':51,488,1105,1109,1210 'evalu':513,1103 'exact':356 'exclud':620 'exclus':1255 'exist':580,583,625 'expect':1198 'extract':149,190,240,287 'facet':339,366,380,396,410,425,439 'fastest':100 'feed':84 'fetch':281 'filter':263,558,607 'filtergroup':262 'find':1116,1127 'first':75 'flag':616 'focus':856,899 'founder':332 'function':219,374,385,526 'gen':672,976 'generat':77,794,1200 'generic':961 'geo':687,1040,1047,1054 'geograph':224 'geographi':306 'get':152,378,505,592,601 'good':534 'group':57,310,594,660,738,745,751,786,992,1081 'guidelin':938 'headlin':879,920,941 'high':26,981 'high-int':980 'higher':539 'hit':567 'hubspot':124,142,151,182,193,237,256,1058 'icp':14,33,82,122,148,187,196,204,208,241,335,346,661,756,1055,1228 'id':510,597,605,754,784,787,863,906 'ideal':37,547 'identifi':96,251 'impact':1211 'impress':1113 'includ':460,848 'industri':221,289,403,415,476,681,1038,1045,1052 'input':45,206,1061 'intent':982 'intro':870,912,951 'iter':561 'job':217,299,352,373,384,525 'json':459,1128 'k':1140 'land':837 'launch':1088 'lead':671,793,975,1204 'leader':325 'learn':892,933,968 'level':680 'li':369,399,413,428,442,464,469,474,479,484 'limit':279 'linkedin':2,9,20,22,28,48,131,135,156,166,179,337,349,357,360,375,390,404,419,433,502,589,598,746,777,857,900,987,1147 'linkedin-micro-campaign':1 'list':138,678,682 'locat':432,444,486,686 'logic':458 'made':574 'manual':44,1060 'map':345 'market':108,324,328,1135,1151 'match':388,964 'max':882,923 'may':537 'mcp':168,1124 'media':875,884,917,925 'medium':1215 'mention':230 'merg':623 'messag':842 'micro':3,23,316,343,454,494,550,656,663,758,769,988,1120,1131,1220 'micro-campaign':549,655,1119,1130,1219 'micro-seg':315,342,453,493,768 'mid':327 'mid-market':326 'minimum':723 'monitor':1090 'month':1106,1110,1206 'n':690,718,721,1006,1013,1020,1026,1028,1064,1112 'name':669,701,708,755,788,790,993,998 'narrow':517,527 'need':538,1077 'new':1224,1239 'next':1068 'object':259,450,670,791,967 'objecttyp':260 'offer':846 'oper':266 'optim':1095,1245 'option':184 'outcom':898,919,1189,1199 'outcome/result':911 'output':86,984 'overlap':578,588,617,621,1251,1252 'page':838 'pain':854,868,877,948,1187 'pars':214 'paus':761,775,808,813,895,936,994,1008,1015,1022,1192 'per':939,1032,1205 'perform':254,1104 'persona':944 'point':855,869,878,949,1188 'precis':7,47 'precision-target':6 'prerequisit':128 'present':637,650 'prioriti':1214 'proceed':632 'profil':39 'prop':844 'properti':270 'propertynam':264,275 'propos':652,654 'provid':194,211,235 'pull':121,244 'qualifi':1203 'queri':372,402,416,431,445 'rang':685 'rate':1178 'reach':1111 'readi':1086 'realloc':1247 'recommend':619,719,1256 'record':1115 'refer':942 'refin':1231 'refresh':1238 'relat':524 'relev':387 'request':977 'requir':62,134,163 'review':582,1071 'role':946 'run':73,93,1097 'saa':110,1137,1153 'sale':329 'search':257,354,363,382,393,407,422,436 'segment':15,34,98,255,317,344,455,495,515,566,662,667,699,706,757,770,789,866,909,940,957,1004,1011,1018,1174,1249 'segment-specif':865,908 'select':727 'senior':220,302,389,401,471,679,1037,1044,1051 'server':169 'set':1079 'share':874,883,916,924 'show':1172 'sign':67,170,972 'similar':631 'size':53,223,294,418,490,501,571,684,1039,1046,1053,1162,1183 'size/overlap':1236 'skill':89,162 'skill-linkedin-micro-campaigns' 'sort':274 'sourc':1057 'source-cognyai' 'speak':953 'specif':13,32,104,728,841,867,910,956 'spend':1107,1246 'spot':542 'staffcountrang':430,481 'startup':331 'status':606,760,776,807,894,935,1002,1082,1193 'step':201,1069 'strategi':695,696 'structur':639,653,658,703,710 'subscript':65 'summari':986,1031 'sweet':541 'target':8,21,27,49,102,205,225,228,338,350,358,364,379,394,408,423,437,448,496,511,563,614,628,676,795,1030,1149,1230 'test':832,1243 'text':952 'tighten':560 'tip':72 'titl':218,300,353,371,466,521,677,876,918,1036,1043,1050,1129 'tool':137,362,377,392,406,421,435,504,591,600,748,779,859,902 'top':253,288 'top-perform':252 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-claude-skills' 'topic-cluade-mcp' 'topic-cursor' 'topic-geo' 'topic-growth-hacking' 'topic-llm' 'topic-marketing' 'topic-mcp' 'topic-seo' 'total':711,715,1025,1029 'translat':16,35,334 'type':792,805,891,932,1195,1217 'updat':1074 'url':839,887,928 'urn':367,368,397,398,411,412,426,427,440,441,463,468,473,478,483 'us/uk':1160 'usag':105 'usd':803,1212 'use':456 'user':153,645,740,815,835 'valu':268,843 'variat':829,851,852,896,1010,1017,1024,1186,1241 'verifi':130,150 'viabl':529,569 'visibl':873,915 'visit':674 'vp':107,1134 'vp/director':1150 'wait':643 'websit':673 'week':722 'win':291,297,308,1177 'within':383 'without':192 'won':247 'x':693,714,1007,1014,1021,1027,1108","prices":[{"id":"975b6f30-a8aa-4187-8b5c-d78b792ed624","listingId":"161f603f-c2ae-4e84-b190-df66e5e3d201","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"cognyai","category":"claude-code-marketing-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T22:23:39.028Z"}],"sources":[{"listingId":"161f603f-c2ae-4e84-b190-df66e5e3d201","source":"github","sourceId":"cognyai/claude-code-marketing-skills/linkedin-micro-campaigns","sourceUrl":"https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/linkedin-micro-campaigns","isPrimary":false,"firstSeenAt":"2026-04-18T22:23:39.028Z","lastSeenAt":"2026-05-01T06:56:27.112Z"}],"details":{"listingId":"161f603f-c2ae-4e84-b190-df66e5e3d201","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"cognyai","slug":"linkedin-micro-campaigns","github":{"repo":"cognyai/claude-code-marketing-skills","stars":42,"topics":["agent-skills","ai-agents","claude-code","claude-skills","cluade-mcp","cursor","geo","growth-hacking","llm","marketing","mcp","seo","vibe","windsurf"],"license":null,"html_url":"https://github.com/cognyai/claude-code-marketing-skills","pushed_at":"2026-04-29T13:43:50Z","description":"Marketing skills for Claude Code — SEO audits and implementation, ad analysis, ad optimization. Free skills need no account. $9/mo for live Search Console, Bing & LinkedIn data.","skill_md_sha":"020de4cdf9395455b9bd27024f795cf21b8f9529","skill_md_path":"skills/linkedin-micro-campaigns/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/linkedin-micro-campaigns"},"layout":"multi","source":"github","category":"claude-code-marketing-skills","frontmatter":{"name":"linkedin-micro-campaigns","description":"Create precision-targeted LinkedIn ad campaigns for specific ICP segments — translates CRM data to LinkedIn targeting"},"skills_sh_url":"https://skills.sh/cognyai/claude-code-marketing-skills/linkedin-micro-campaigns"},"updatedAt":"2026-05-01T06:56:27.112Z"}}