{"id":"ceaa6ebc-0634-40f0-8513-d9ca7fae97d8","shortId":"hvaRNK","kind":"skill","title":"crm-icp-analysis","tagline":"Analyze HubSpot CRM data to build a data-driven Ideal Customer Profile from closed-won deals, contacts, and companies","description":"# CRM ICP Analysis\n\nBuild a data-driven Ideal Customer Profile by analyzing closed-won deals, associated contacts, and companies in your HubSpot CRM. Identifies patterns in industries, company sizes, job titles, deal sizes, sales cycles, and lead sources that predict revenue.\n\n**Requires:** Cogny Agent subscription ($9/mo) — [Sign up](https://cogny.com/agent)\n\n## Usage\n\n`/crm-icp-analysis` — full ICP analysis across all dimensions\n`/crm-icp-analysis companies` — company firmographic analysis only\n`/crm-icp-analysis contacts` — buyer persona analysis only\n`/crm-icp-analysis deals` — deal pattern analysis only\n\n## Prerequisites Check\n\nCall `mcp__cogny__hubspot__get_user_details` to verify CRM access. Confirm read access to contacts, companies, and deals. If access is missing:\n\n```\nThis skill requires HubSpot CRM access via Cogny's MCP server.\nSign up at https://cogny.com/agent and connect your HubSpot account.\n```\n\n## Steps\n\n### 1. Discover available properties\n\nBefore querying data, understand what fields exist:\n\n```\nhubspot__get_properties(objectType: \"deals\")\nhubspot__get_properties(objectType: \"companies\")\nhubspot__get_properties(objectType: \"contacts\")\n```\n\nIdentify key properties for analysis:\n- **Deals:** dealstage, amount, closedate, createdate, pipeline, dealtype, hs_analytics_source\n- **Companies:** industry, numberofemployees, annualrevenue, city, state, country, type\n- **Contacts:** jobtitle, hs_persona, lifecyclestage, hs_analytics_source\n\nNote any custom properties that look ICP-relevant (e.g., custom industry fields, company tier, segment tags).\n\n### 2. Analyze closed-won deals\n\nSearch for closed-won deals to establish the revenue baseline:\n\n```\nhubspot__search_crm_objects(\n  objectType: \"deals\",\n  filterGroups: [{\"filters\": [{\"propertyName\": \"dealstage\", \"operator\": \"EQ\", \"value\": \"closedwon\"}]}],\n  properties: [\"dealname\", \"amount\", \"closedate\", \"createdate\", \"pipeline\", \"dealtype\", \"hs_analytics_source\"],\n  sorts: [{\"propertyName\": \"closedate\", \"direction\": \"DESCENDING\"}],\n  limit: 200\n)\n```\n\nCheck the `total` count — paginate if needed to capture full dataset.\n\nCalculate:\n- **Total closed-won deals** and **total revenue**\n- **Average deal size** (mean and median)\n- **Deal size distribution**: bucket into tiers (e.g., <$5K, $5-25K, $25-100K, $100K+)\n- **Average sales cycle length**: days from createdate to closedate\n- **Sales cycle by deal size tier**\n- **Win rate by pipeline** (if multiple pipelines exist)\n- **Lead source breakdown**: which sources produce closed-won deals\n\nAlso search closed-lost for comparison:\n\n```\nhubspot__search_crm_objects(\n  objectType: \"deals\",\n  filterGroups: [{\"filters\": [{\"propertyName\": \"dealstage\", \"operator\": \"EQ\", \"value\": \"closedlost\"}]}],\n  properties: [\"dealname\", \"amount\", \"closedate\", \"createdate\", \"pipeline\", \"hs_analytics_source\"],\n  limit: 200\n)\n```\n\nCompare closed-won vs closed-lost to identify discriminating patterns.\n\n### 3. Analyze winning companies\n\nFetch companies associated with closed-won deals. Use `get_crm_objects` with deal IDs to get associations, then batch-fetch the associated companies:\n\n```\nhubspot__get_crm_objects(\n  objectType: \"companies\",\n  objectIds: [<associated company IDs>],\n  properties: [\"name\", \"industry\", \"numberofemployees\", \"annualrevenue\", \"city\", \"state\", \"country\", \"type\", \"domain\"]\n)\n```\n\nBuild firmographic profile:\n- **Industry breakdown**: rank industries by deal count and total revenue\n- **Company size distribution**: by employee count bands (1-50, 51-200, 201-1000, 1000+)\n- **Revenue range**: annual revenue bands of winning companies\n- **Geography**: country, state/region concentration\n- **Company type**: customer, partner, prospect categorization\n\nFlag:\n- Industries that appear in >20% of closed-won deals (core ICP)\n- Company size sweet spots (highest win rate bands)\n- Geographic clusters\n\n### 4. Analyze buyer personas\n\nFetch contacts associated with closed-won deals, then batch-fetch:\n\n```\nhubspot__get_crm_objects(\n  objectType: \"contacts\",\n  objectIds: [<associated contact IDs>],\n  properties: [\"jobtitle\", \"hs_persona\", \"lifecyclestage\", \"hs_analytics_source\", \"email\", \"firstname\", \"lastname\"]\n)\n```\n\nBuild buyer persona profile:\n- **Job title clustering**: group similar titles (e.g., \"VP Marketing\", \"Head of Marketing\", \"Marketing Director\" = Marketing Leadership)\n- **Seniority distribution**: C-level, VP, Director, Manager, Individual Contributor\n- **Functional area**: Marketing, Sales, Product, Engineering, Finance, Operations\n- **Number of contacts per deal**: single-threaded vs multi-threaded deals\n- **Lead source by persona**: how different personas find you\n\nFlag:\n- Dominant buyer persona (>30% of closed-won contacts)\n- Multi-threaded deals that win at higher rates\n- Personas that correlate with larger deal sizes\n\n### 5. Cross-dimensional analysis\n\nCombine insights across deals, companies, and contacts:\n\n- **Best segment**: Industry + Company Size + Persona that produces highest win rate\n- **Highest-value segment**: combination that produces largest average deal size\n- **Fastest-closing segment**: combination with shortest sales cycle\n- **Lead source efficiency**: which sources produce best-fit leads (not just most leads)\n- **Anti-ICP patterns**: segments with low win rates or high loss rates\n\n### 6. Output ICP definition\n\n```\nCRM ICP Analysis\nData basis: [N] closed-won deals, [N] companies, [N] contacts\nPeriod: [earliest close date] to [latest close date]\nTotal revenue analyzed: $[X]\n\n═══════════════════════════════════════════════════\nIDEAL CUSTOMER PROFILE\n═══════════════════════════════════════════════════\n\nCompany Firmographics:\n  Industry:        [Top 1-3 industries] ([X]% of wins)\n  Employee Count:  [Range] (sweet spot: [X-Y])\n  Annual Revenue:  $[Range]\n  Geography:       [Top regions]\n\nBuyer Persona:\n  Primary Buyer:   [Title cluster] ([X]% of deals)\n  Secondary Buyer: [Title cluster] ([X]% of deals)\n  Seniority:       [Level] and above\n  Function:        [Department]\n\nDeal Characteristics:\n  Average Deal Size:    $[X] (median: $[Y])\n  Sweet Spot Range:     $[X] - $[Y]\n  Average Sales Cycle:  [N] days\n  Best Lead Sources:    [Source 1], [Source 2]\n\nWin Rate Analysis:\n  Overall Win Rate:     [X]%\n  Best Segment Rate:    [X]% ([segment description])\n  Worst Segment Rate:   [X]% ([segment description])\n\n═══════════════════════════════════════════════════\nICP FIT SCORING MODEL\n═══════════════════════════════════════════════════\n\nDimension          | Weight | Criteria\n───────────────────|────────|─────────────────────────\nIndustry           |  25%   | [Top industries] = match\nCompany Size       |  20%   | [Range] employees = match\nSeniority          |  20%   | [Level]+ = match\nJob Function       |  15%   | [Functions] = match\nDeal Size Potential|  10%   | $[X]+ = match\nLead Source        |  10%   | [Sources] = match\n\nScoring: 80-100 = Strong fit | 60-79 = Moderate fit | <60 = Weak fit\n\n═══════════════════════════════════════════════════\nANTI-ICP (AVOID)\n═══════════════════════════════════════════════════\n\n- [Pattern 1 that predicts losses]\n- [Pattern 2 that predicts losses]\n- [Pattern 3 that predicts losses]\n\nTop 3 Actions:\n1. [Highest-impact recommendation]\n2. [Second recommendation]\n3. [Third recommendation]\n```\n\n### 7. Record findings\n\nFor EVERY actionable ICP insight, call `mcp__cogny__create_finding`:\n\n```json\n{\n  \"title\": \"ICP sweet spot: SaaS companies 200-1000 employees close at 2.3x average rate\",\n  \"body\": \"Analysis of 87 closed-won deals shows SaaS companies with 200-1000 employees have a 42% win rate vs 18% overall. Average deal size $45K, 34-day sales cycle. These companies represent only 23% of pipeline but 51% of revenue. Recommend: prioritize this segment in outbound and ad targeting.\",\n  \"action_type\": \"icp_refinement\",\n  \"expected_outcome\": \"Increase win rate by focusing pipeline on high-fit segments\",\n  \"estimated_impact_usd\": 5000,\n  \"priority\": \"high\"\n}\n```\n\nAction types for ICP analysis:\n- `icp_refinement` — ICP definition updates, scoring model changes\n- `targeting_refinement` — ad/outbound targeting changes based on ICP\n- `pipeline_optimization` — sales process changes for specific segments\n- `lead_source_optimization` — invest more in high-ICP-fit lead sources\n- `disqualification_rule` — anti-ICP patterns to filter out early","tags":["crm","icp","analysis","claude","code","marketing","skills","cognyai","agent-skills","ai-agents","claude-code","claude-skills"],"capabilities":["skill","source-cognyai","skill-crm-icp-analysis","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/crm-icp-analysis","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 (8,313 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":"2026-05-01T06:56:25.836Z","embedding":null,"createdAt":"2026-04-18T22:23:30.534Z","updatedAt":"2026-05-01T06:56:25.836Z","lastSeenAt":"2026-05-01T06:56:25.836Z","tsv":"'-100':313,860 '-1000':464,924,945 '-200':462 '-25':310 '-3':735 '-50':460 '-79':864 '/agent':146 '/agent)':78 '/crm-icp-analysis':80,87,93,99 '1':153,459,734,798,875,892 '10':850,855 '1000':465 '100k':315 '15':844 '18':953 '2':227,800,880,897 '2.3':928 '20':489,834,839 '200':274,380,923,944 '201':463 '23':967 '25':312,828 '3':393,885,890,900 '30':605 '34':959 '4':507 '42':949 '45k':958 '5':309,627 '5000':1003 '51':461,971 '5k':308 '6':697 '60':863,867 '7':903 '80':859 '87':935 '9/mo':73 'access':117,120,127,135 'account':151 'across':84,634 'action':891,908,983,1006 'ad':981 'ad/outbound':1021 'agent':71 'also':349 'amount':186,260,372 'analysi':4,28,83,91,97,103,183,631,703,803,933,1010 'analyt':192,208,266,377,536 'analyz':5,38,228,394,508,725 'annual':468,748 'annualrevenu':197,433 'anti':685,871,1050 'anti-icp':684,870,1049 'appear':487 'area':572 'associ':43,399,414,420,513 'avail':155 'averag':295,316,658,778,789,930,955 'avoid':873 'band':458,470,504 'base':1024 'baselin':243 'basi':705 'batch':417,521 'batch-fetch':416,520 'best':639,677,794,808 'best-fit':676 'bodi':932 'breakdown':341,443 'bucket':304 'build':10,29,439,541 'buyer':95,509,542,603,754,757,764 'c':564 'c-level':563 'calcul':286 'call':107,911 'captur':283 'categor':483 'chang':1018,1023,1031 'characterist':777 'check':106,275 'citi':198,434 'close':20,40,230,236,289,346,352,383,387,402,492,516,608,663,708,717,721,926,937 'closed':187,261,270,324,373 'closed-lost':351,386 'closed-won':19,39,229,235,288,345,382,401,491,515,607,707,936 'closedlost':369 'closedwon':257 'cluster':506,547,759,766 'cogni':70,109,137,913 'cogny.com':77,145 'cogny.com/agent':144 'cogny.com/agent)':76 'combin':632,654,665 'compani':25,46,55,88,89,123,173,194,223,396,398,421,427,452,473,478,497,636,642,712,730,832,922,942,964 'compar':381 'comparison':355 'concentr':477 'confirm':118 'connect':148 'contact':23,44,94,122,178,202,512,528,581,610,638,714 'contributor':570 'core':495 'correl':622 'count':278,448,457,741 'countri':200,436,475 'creat':914 'created':188,262,322,374 'criteria':826 'crm':2,7,26,50,116,134,246,358,407,424,525,701 'crm-icp-analysi':1 'cross':629 'cross-dimension':628 'custom':16,35,212,220,480,728 'cycl':62,318,326,669,791,962 'data':8,13,32,159,704 'data-driven':12,31 'dataset':285 'date':718,722 'day':320,793,960 'deal':22,42,59,100,101,125,168,184,232,238,249,291,296,301,328,348,361,404,410,447,494,518,583,591,614,625,635,659,710,762,769,776,779,847,939,956 'dealnam':259,371 'dealstag':185,253,365 'dealtyp':190,264 'definit':700,1014 'depart':775 'descend':272 'descript':813,819 'detail':113 'differ':597 'dimens':86,824 'dimension':630 'direct':271 'director':558,567 'discov':154 'discrimin':391 'disqualif':1047 'distribut':303,454,562 'domain':438 'domin':602 'driven':14,33 'e.g':219,307,551 'earli':1056 'earliest':716 'effici':672 'email':538 'employe':456,740,836,925,946 'engin':576 'eq':255,367 'establish':240 'estim':1000 'everi':907 'exist':163,338 'expect':987 'fastest':662 'fastest-clos':661 'fetch':397,418,511,522 'field':162,222 'filter':251,363,1054 'filtergroup':250,362 'financ':577 'find':599,905,915 'firmograph':90,440,731 'firstnam':539 'fit':678,821,862,866,869,998,1044 'flag':484,601 'focus':993 'full':81,284 'function':571,774,843,845 'geograph':505 'geographi':474,751 'get':111,165,170,175,406,413,423,524 'group':548 'head':554 'high':694,997,1005,1042 'high-fit':996 'high-icp-fit':1041 'higher':618 'highest':501,647,651,894 'highest-impact':893 'highest-valu':650 'hs':191,204,207,265,376,532,535 'hubspot':6,49,110,133,150,164,169,174,244,356,422,523 'icp':3,27,82,217,496,686,699,702,820,872,909,918,985,1009,1011,1013,1026,1043,1051 'icp-relev':216 'id':411 'ideal':15,34,727 'identifi':51,179,390 'impact':895,1001 'increas':989 'individu':569 'industri':54,195,221,431,442,445,485,641,732,736,827,830 'insight':633,910 'invest':1038 'job':57,545,842 'jobtitl':203,531 'json':916 'k':311,314 'key':180 'larger':624 'largest':657 'lastnam':540 'latest':720 'lead':64,339,592,670,679,683,795,853,1035,1045 'leadership':560 'length':319 'level':565,771,840 'lifecyclestag':206,534 'limit':273,379 'look':215 'loss':695,878,883,888 'lost':353,388 'low':690 'manag':568 'market':553,556,557,559,573 'match':831,837,841,846,852,857 'mcp':108,139,912 'mean':298 'median':300,782 'miss':129 'model':823,1017 'moder':865 'multi':589,612 'multi-thread':588,611 'multipl':336 'n':706,711,713,792 'name':430 'need':281 'note':210 'number':579 'numberofemploye':196,432 'object':247,359,408,425,526 'objectid':428,529 'objecttyp':167,172,177,248,360,426,527 'oper':254,366,578 'optim':1028,1037 'outbound':979 'outcom':988 'output':698 'overal':804,954 'pagin':279 'partner':481 'pattern':52,102,392,687,874,879,884,1052 'per':582 'period':715 'persona':96,205,510,533,543,595,598,604,620,644,755 'pipelin':189,263,334,337,375,969,994,1027 'potenti':849 'predict':67,877,882,887 'prerequisit':105 'primari':756 'priorit':975 'prioriti':1004 'process':1030 'produc':344,646,656,675 'product':575 'profil':17,36,441,544,729 'properti':156,166,171,176,181,213,258,370,429,530 'propertynam':252,269,364 'prospect':482 'queri':158 'rang':467,742,750,786,835 'rank':444 'rate':332,503,619,649,692,696,802,806,810,816,931,951,991 'read':119 'recommend':896,899,902,974 'record':904 'refin':986,1012,1020 'region':753 'relev':218 'repres':965 'requir':69,132 'revenu':68,242,294,451,466,469,724,749,973 'rule':1048 'saa':921,941 'sale':61,317,325,574,668,790,961,1029 'score':822,858,1016 'search':233,245,350,357 'second':898 'secondari':763 'segment':225,640,653,664,688,809,812,815,818,977,999,1034 'senior':561,770,838 'server':140 'shortest':667 'show':940 'sign':74,141 'similar':549 'singl':585 'single-thread':584 'size':56,60,297,302,329,453,498,626,643,660,780,833,848,957 'skill':131 'skill-crm-icp-analysis' 'sort':268 'sourc':65,193,209,267,340,343,378,537,593,671,674,796,797,799,854,856,1036,1046 'source-cognyai' 'specif':1033 'spot':500,744,785,920 'state':199,435 'state/region':476 'step':152 'strong':861 'subscript':72 'sweet':499,743,784,919 'tag':226 'target':982,1019,1022 'third':901 'thread':586,590,613 'tier':224,306,330 'titl':58,546,550,758,765,917 'top':733,752,829,889 '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':277,287,293,450,723 'type':201,437,479,984,1007 'understand':160 'updat':1015 'usag':79 'usd':1002 'use':405 'user':112 'valu':256,368,652 'verifi':115 'via':136 'vp':552,566 'vs':385,587,952 'weak':868 'weight':825 'win':331,395,472,502,616,648,691,739,801,805,950,990 'won':21,41,231,237,290,347,384,403,493,517,609,709,938 'worst':814 'x':726,737,746,760,767,781,787,807,811,817,851,929 'x-i':745 'y':747,783,788","prices":[{"id":"2da5fd7c-3c52-4735-9456-02a56c692c66","listingId":"ceaa6ebc-0634-40f0-8513-d9ca7fae97d8","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":"2026-04-18T22:23:30.534Z"}],"sources":[{"listingId":"ceaa6ebc-0634-40f0-8513-d9ca7fae97d8","source":"github","sourceId":"cognyai/claude-code-marketing-skills/crm-icp-analysis","sourceUrl":"https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/crm-icp-analysis","isPrimary":false,"firstSeenAt":"2026-04-18T22:23:30.534Z","lastSeenAt":"2026-05-01T06:56:25.836Z"}],"details":{"listingId":"ceaa6ebc-0634-40f0-8513-d9ca7fae97d8","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"cognyai","slug":"crm-icp-analysis","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":"73a2002c7831c726078566c0060a184a6a9f0fa0","skill_md_path":"skills/crm-icp-analysis/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/cognyai/claude-code-marketing-skills/tree/main/skills/crm-icp-analysis"},"layout":"multi","source":"github","category":"claude-code-marketing-skills","frontmatter":{"name":"crm-icp-analysis","description":"Analyze HubSpot CRM data to build a data-driven Ideal Customer Profile from closed-won deals, contacts, and companies"},"skills_sh_url":"https://skills.sh/cognyai/claude-code-marketing-skills/crm-icp-analysis"},"updatedAt":"2026-05-01T06:56:25.836Z"}}