[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-posthog-user-deep-dive":3,"mdc-fmymy4-key":34,"related-org-posthog-user-deep-dive":1146,"related-repo-posthog-user-deep-dive":1319},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"user-deep-dive","perform deep dive on PostHog users","Deep dive on a PostHog user by email address. Analyze what they do, where they spend time, and what products they use.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"posthog","PostHog","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fposthog.png",[12,14,17,20],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"User Research","user-research",{"name":18,"slug":19,"type":13},"Customer Success","customer-success",{"name":21,"slug":22,"type":13},"Analytics","analytics",56,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fskills","2026-04-06T18:46:37.221426",null,4,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"PostHog skills (under construction)","https:\u002F\u002Fgithub.com\u002FPostHog\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fteam\u002Fcustomer-success\u002Fuser-deep-dive","---\nname: user-deep-dive\ndescription: Deep dive on a PostHog user by email address. Analyze what they do, where they spend time, and what products they use.\n---\n\nDeep dive on a PostHog user by email address. Analyse what they do, where they spend time, and what products they use.\n\n**Input**: $ARGUMENTS (email address, e.g. `artis.conka@enlabs.com`)\n\n## Process\n\n### Step 0: Ask for time window\n\nBefore running any queries, ask the user:\n\n> \"What time window would you like to analyse? (default: last 14 days)\"\n\nIf they don't respond or say \"default\", use **14 days**. Use their answer to set `{days}` in all queries below.\n\n---\n\n### Step 1: Run queries in parallel\n\nRun all of the following queries simultaneously via the `query-run` MCP tool.\n\n**1. Activity overview** — event breakdown (excluding PostHog internals):\n```sql\nSELECT event, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND timestamp >= now() - interval {days} day\n  AND event NOT IN (\n    '$feature_flag_called',\n    '$ai_span',\n    '$ai_trace',\n    '$autocapture',\n    '$web_vitals',\n    'react_framerate',\n    'spinner_unloaded',\n    'replay_parse_timing',\n    '$dead_click'\n  )\nGROUP BY event\nORDER BY cnt DESC\nLIMIT 30\n```\n\n**2. Page views** — where they spend their time:\n```sql\nSELECT properties.$current_url as url, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = '$pageview'\n  AND timestamp >= now() - interval {days} day\nGROUP BY url\nORDER BY cnt DESC\nLIMIT 25\n```\n\n**3. Insight details** — which insights\u002Fdashboards they view:\n```sql\nSELECT properties.insight as insight_type, properties.insight_name as name, count() as views\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = 'insight viewed'\n  AND timestamp >= now() - interval {days} day\nGROUP BY insight_type, name\nORDER BY views DESC\nLIMIT 20\n```\n\n**4. Session replay views** — replays they've watched:\n```sql\nSELECT\n  properties.session_id as session_id,\n  properties.$current_url as url,\n  timestamp\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = '$recording_viewed'\n  AND timestamp >= now() - interval {days} day\nORDER BY timestamp DESC\nLIMIT 20\n```\n\n**5. Error tracking usage** — how they interact with error tracking in PostHog:\n```sql\nSELECT event, properties.issue_id as issue_id, properties.issue_name as issue_name, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event IN ('error tracking issue viewed', 'error tracking issue resolved', 'error tracking issue assigned', 'error tracking issue suppressed', 'error tracking list viewed')\n  AND timestamp >= now() - interval {days} day\nGROUP BY event, issue_id, issue_name\nORDER BY cnt DESC\nLIMIT 20\n```\n\n**6. PostHog AI usage** — Max and insight analysis counts:\n```sql\nSELECT event, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event IN ('$ai_generation', '$conversations_loaded', 'insight analyzed', 'chat with data opened')\n  AND timestamp >= now() - interval {days} day\nGROUP BY event\nORDER BY cnt DESC\n```\n\n**7. Where they open Max** — which pages\u002Fcontexts they use Max on:\n```sql\nSELECT\n  properties.$current_url as url,\n  count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = '$conversations_loaded'\n  AND timestamp >= now() - interval {days} day\n  AND properties.$current_url LIKE '%posthog.com\u002Fproject%'\nGROUP BY url\nORDER BY cnt DESC\nLIMIT 20\n```\n\n### Step 2: Cross-reference with Vitally\n\nUse Vitally tools to look up the user by email — get their role, title, account name, and any CRM data available.\n\n---\n\n## Output Format\n\n### Executive Summary\n2–3 sentences capturing who this person is, what they primarily use PostHog for, and the single most interesting or actionable thing about their usage. Write it as if briefing someone before a call with this user.\n\n---\n\n### Profile\n- Name, email, role\u002Ftitle, LinkedIn (if available)\n- Location (from timezone or geo data)\n- Account they belong to\n\n### Activity Summary (last {days} days)\n- Total events, key event types\n- How many queries run, insights viewed, dashboards checked, exports done\n\n### Where They Spend Time\n- Which PostHog projects (extract project IDs from URLs)\n- Which product areas (analytics, replay, flags, LLM analytics, data management, error tracking, etc.)\n- Specific dashboards or insights they revisit\n\n### What They're Doing\n- Interpret the insight names and patterns — what business questions are they answering?\n- Are they building things (creating insights, actions, destinations) or consuming (viewing dashboards, exporting)?\n- Error tracking: are they actively triaging errors (resolving, assigning, suppressing) or just browsing?\n\n### Session Recordings\n- Link directly to PostHog session replay filtered to this user:\n  `https:\u002F\u002Fus.posthog.com\u002Freplay?filters={\"type\":\"AND\",\"values\":[{\"type\":\"AND\",\"values\":[{\"key\":\"email\",\"value\":[\"{email}\"],\"operator\":\"exact\",\"type\":\"person\"}]}]}`\n- Summarise any patterns from the replays they've watched (query 4): which parts of the product, how recently\n\n### PostHog AI Usage\n- How often do they open Max (`$conversations_loaded` count) and make AI calls (`$ai_generation` count)?\n- Do they use insight analysis (`insight analyzed`)?\n- **Where do they open Max?** — Summarise the URLs from query 7. Extract the product area from each URL (e.g. `\u002Fdashboard\u002F` → \"dashboards\", `\u002Fsql` → \"SQL editor\", `\u002Finsights\u002F` → \"insights\", `\u002Fpersons\u002F` → \"person profiles\") and list the top contexts with counts. This tells us what they're trying to get help with.\n- Are they looking at LLM Analytics?\n\n### Outreach Angles\n- Based on their usage, suggest 2-3 conversation starters for the user's outreach\n- Flag any pain points (query failures, rage clicks, error tracking spikes, etc.)\n- Note any products they're NOT using that would be relevant\n\n---\n\n## Important\n- Ask for the time window **before** running any queries.\n- Use the PostHog MCP `query-run` tool, NOT curl. Fall back to curl only if MCP is unavailable.\n- Vitally `lastSeenTimestamp` data is stale — do NOT rely on it for activity. Always use PostHog event data.\n- Run all PostHog queries in parallel to save time.\n- If PostHog returns 503 (busy), wait a moment and retry once before giving up on that query.\n- The session replay link should use the user's actual email in the filter parameter.",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,47,67,74,81,86,95,115,119,125,138,148,322,332,399,409,477,487,570,580,646,656,713,723,810,816,821,824,830,836,841,844,850,870,876,889,895,913,919,937,943,962,968,1052,1058,1076,1079,1085,1140],{"type":40,"tag":41,"props":42,"children":43},"element","p",{},[44],{"type":45,"value":46},"text","Deep dive on a PostHog user by email address. Analyse what they do, where they spend time, and what products they use.",{"type":40,"tag":41,"props":48,"children":49},{},[50,56,58,65],{"type":40,"tag":51,"props":52,"children":53},"strong",{},[54],{"type":45,"value":55},"Input",{"type":45,"value":57},": $ARGUMENTS (email address, e.g. ",{"type":40,"tag":59,"props":60,"children":62},"code",{"className":61},[],[63],{"type":45,"value":64},"artis.conka@enlabs.com",{"type":45,"value":66},")",{"type":40,"tag":68,"props":69,"children":71},"h2",{"id":70},"process",[72],{"type":45,"value":73},"Process",{"type":40,"tag":75,"props":76,"children":78},"h3",{"id":77},"step-0-ask-for-time-window",[79],{"type":45,"value":80},"Step 0: Ask for time window",{"type":40,"tag":41,"props":82,"children":83},{},[84],{"type":45,"value":85},"Before running any queries, ask the user:",{"type":40,"tag":87,"props":88,"children":89},"blockquote",{},[90],{"type":40,"tag":41,"props":91,"children":92},{},[93],{"type":45,"value":94},"\"What time window would you like to analyse? (default: last 14 days)\"",{"type":40,"tag":41,"props":96,"children":97},{},[98,100,105,107,113],{"type":45,"value":99},"If they don't respond or say \"default\", use ",{"type":40,"tag":51,"props":101,"children":102},{},[103],{"type":45,"value":104},"14 days",{"type":45,"value":106},". Use their answer to set ",{"type":40,"tag":59,"props":108,"children":110},{"className":109},[],[111],{"type":45,"value":112},"{days}",{"type":45,"value":114}," in all queries below.",{"type":40,"tag":116,"props":117,"children":118},"hr",{},[],{"type":40,"tag":75,"props":120,"children":122},{"id":121},"step-1-run-queries-in-parallel",[123],{"type":45,"value":124},"Step 1: Run queries in parallel",{"type":40,"tag":41,"props":126,"children":127},{},[128,130,136],{"type":45,"value":129},"Run all of the following queries simultaneously via the ",{"type":40,"tag":59,"props":131,"children":133},{"className":132},[],[134],{"type":45,"value":135},"query-run",{"type":45,"value":137}," MCP tool.",{"type":40,"tag":41,"props":139,"children":140},{},[141,146],{"type":40,"tag":51,"props":142,"children":143},{},[144],{"type":45,"value":145},"1. Activity overview",{"type":45,"value":147}," — event breakdown (excluding PostHog internals):",{"type":40,"tag":149,"props":150,"children":155},"pre",{"className":151,"code":152,"language":153,"meta":154,"style":154},"language-sql shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","SELECT event, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND timestamp >= now() - interval {days} day\n  AND event NOT IN (\n    '$feature_flag_called',\n    '$ai_span',\n    '$ai_trace',\n    '$autocapture',\n    '$web_vitals',\n    'react_framerate',\n    'spinner_unloaded',\n    'replay_parse_timing',\n    '$dead_click'\n  )\nGROUP BY event\nORDER BY cnt DESC\nLIMIT 30\n","sql","",[156],{"type":40,"tag":59,"props":157,"children":158},{"__ignoreMap":154},[159,170,179,188,196,205,214,223,232,241,250,259,268,277,286,295,304,313],{"type":40,"tag":160,"props":161,"children":164},"span",{"class":162,"line":163},"line",1,[165],{"type":40,"tag":160,"props":166,"children":167},{},[168],{"type":45,"value":169},"SELECT event, count() as cnt\n",{"type":40,"tag":160,"props":171,"children":173},{"class":162,"line":172},2,[174],{"type":40,"tag":160,"props":175,"children":176},{},[177],{"type":45,"value":178},"FROM events\n",{"type":40,"tag":160,"props":180,"children":182},{"class":162,"line":181},3,[183],{"type":40,"tag":160,"props":184,"children":185},{},[186],{"type":45,"value":187},"WHERE person.properties.email = '{email}'\n",{"type":40,"tag":160,"props":189,"children":190},{"class":162,"line":27},[191],{"type":40,"tag":160,"props":192,"children":193},{},[194],{"type":45,"value":195},"  AND timestamp >= now() - interval {days} day\n",{"type":40,"tag":160,"props":197,"children":199},{"class":162,"line":198},5,[200],{"type":40,"tag":160,"props":201,"children":202},{},[203],{"type":45,"value":204},"  AND event NOT IN (\n",{"type":40,"tag":160,"props":206,"children":208},{"class":162,"line":207},6,[209],{"type":40,"tag":160,"props":210,"children":211},{},[212],{"type":45,"value":213},"    '$feature_flag_called',\n",{"type":40,"tag":160,"props":215,"children":217},{"class":162,"line":216},7,[218],{"type":40,"tag":160,"props":219,"children":220},{},[221],{"type":45,"value":222},"    '$ai_span',\n",{"type":40,"tag":160,"props":224,"children":226},{"class":162,"line":225},8,[227],{"type":40,"tag":160,"props":228,"children":229},{},[230],{"type":45,"value":231},"    '$ai_trace',\n",{"type":40,"tag":160,"props":233,"children":235},{"class":162,"line":234},9,[236],{"type":40,"tag":160,"props":237,"children":238},{},[239],{"type":45,"value":240},"    '$autocapture',\n",{"type":40,"tag":160,"props":242,"children":244},{"class":162,"line":243},10,[245],{"type":40,"tag":160,"props":246,"children":247},{},[248],{"type":45,"value":249},"    '$web_vitals',\n",{"type":40,"tag":160,"props":251,"children":253},{"class":162,"line":252},11,[254],{"type":40,"tag":160,"props":255,"children":256},{},[257],{"type":45,"value":258},"    'react_framerate',\n",{"type":40,"tag":160,"props":260,"children":262},{"class":162,"line":261},12,[263],{"type":40,"tag":160,"props":264,"children":265},{},[266],{"type":45,"value":267},"    'spinner_unloaded',\n",{"type":40,"tag":160,"props":269,"children":271},{"class":162,"line":270},13,[272],{"type":40,"tag":160,"props":273,"children":274},{},[275],{"type":45,"value":276},"    'replay_parse_timing',\n",{"type":40,"tag":160,"props":278,"children":280},{"class":162,"line":279},14,[281],{"type":40,"tag":160,"props":282,"children":283},{},[284],{"type":45,"value":285},"    '$dead_click'\n",{"type":40,"tag":160,"props":287,"children":289},{"class":162,"line":288},15,[290],{"type":40,"tag":160,"props":291,"children":292},{},[293],{"type":45,"value":294},"  )\n",{"type":40,"tag":160,"props":296,"children":298},{"class":162,"line":297},16,[299],{"type":40,"tag":160,"props":300,"children":301},{},[302],{"type":45,"value":303},"GROUP BY event\n",{"type":40,"tag":160,"props":305,"children":307},{"class":162,"line":306},17,[308],{"type":40,"tag":160,"props":309,"children":310},{},[311],{"type":45,"value":312},"ORDER BY cnt DESC\n",{"type":40,"tag":160,"props":314,"children":316},{"class":162,"line":315},18,[317],{"type":40,"tag":160,"props":318,"children":319},{},[320],{"type":45,"value":321},"LIMIT 30\n",{"type":40,"tag":41,"props":323,"children":324},{},[325,330],{"type":40,"tag":51,"props":326,"children":327},{},[328],{"type":45,"value":329},"2. Page views",{"type":45,"value":331}," — where they spend their time:",{"type":40,"tag":149,"props":333,"children":335},{"className":151,"code":334,"language":153,"meta":154,"style":154},"SELECT properties.$current_url as url, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = '$pageview'\n  AND timestamp >= now() - interval {days} day\nGROUP BY url\nORDER BY cnt DESC\nLIMIT 25\n",[336],{"type":40,"tag":59,"props":337,"children":338},{"__ignoreMap":154},[339,347,354,361,369,376,384,391],{"type":40,"tag":160,"props":340,"children":341},{"class":162,"line":163},[342],{"type":40,"tag":160,"props":343,"children":344},{},[345],{"type":45,"value":346},"SELECT properties.$current_url as url, count() as cnt\n",{"type":40,"tag":160,"props":348,"children":349},{"class":162,"line":172},[350],{"type":40,"tag":160,"props":351,"children":352},{},[353],{"type":45,"value":178},{"type":40,"tag":160,"props":355,"children":356},{"class":162,"line":181},[357],{"type":40,"tag":160,"props":358,"children":359},{},[360],{"type":45,"value":187},{"type":40,"tag":160,"props":362,"children":363},{"class":162,"line":27},[364],{"type":40,"tag":160,"props":365,"children":366},{},[367],{"type":45,"value":368},"  AND event = '$pageview'\n",{"type":40,"tag":160,"props":370,"children":371},{"class":162,"line":198},[372],{"type":40,"tag":160,"props":373,"children":374},{},[375],{"type":45,"value":195},{"type":40,"tag":160,"props":377,"children":378},{"class":162,"line":207},[379],{"type":40,"tag":160,"props":380,"children":381},{},[382],{"type":45,"value":383},"GROUP BY url\n",{"type":40,"tag":160,"props":385,"children":386},{"class":162,"line":216},[387],{"type":40,"tag":160,"props":388,"children":389},{},[390],{"type":45,"value":312},{"type":40,"tag":160,"props":392,"children":393},{"class":162,"line":225},[394],{"type":40,"tag":160,"props":395,"children":396},{},[397],{"type":45,"value":398},"LIMIT 25\n",{"type":40,"tag":41,"props":400,"children":401},{},[402,407],{"type":40,"tag":51,"props":403,"children":404},{},[405],{"type":45,"value":406},"3. Insight details",{"type":45,"value":408}," — which insights\u002Fdashboards they view:",{"type":40,"tag":149,"props":410,"children":412},{"className":151,"code":411,"language":153,"meta":154,"style":154},"SELECT properties.insight as insight_type, properties.insight_name as name, count() as views\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = 'insight viewed'\n  AND timestamp >= now() - interval {days} day\nGROUP BY insight_type, name\nORDER BY views DESC\nLIMIT 20\n",[413],{"type":40,"tag":59,"props":414,"children":415},{"__ignoreMap":154},[416,424,431,438,446,453,461,469],{"type":40,"tag":160,"props":417,"children":418},{"class":162,"line":163},[419],{"type":40,"tag":160,"props":420,"children":421},{},[422],{"type":45,"value":423},"SELECT properties.insight as insight_type, properties.insight_name as name, count() as views\n",{"type":40,"tag":160,"props":425,"children":426},{"class":162,"line":172},[427],{"type":40,"tag":160,"props":428,"children":429},{},[430],{"type":45,"value":178},{"type":40,"tag":160,"props":432,"children":433},{"class":162,"line":181},[434],{"type":40,"tag":160,"props":435,"children":436},{},[437],{"type":45,"value":187},{"type":40,"tag":160,"props":439,"children":440},{"class":162,"line":27},[441],{"type":40,"tag":160,"props":442,"children":443},{},[444],{"type":45,"value":445},"  AND event = 'insight viewed'\n",{"type":40,"tag":160,"props":447,"children":448},{"class":162,"line":198},[449],{"type":40,"tag":160,"props":450,"children":451},{},[452],{"type":45,"value":195},{"type":40,"tag":160,"props":454,"children":455},{"class":162,"line":207},[456],{"type":40,"tag":160,"props":457,"children":458},{},[459],{"type":45,"value":460},"GROUP BY insight_type, name\n",{"type":40,"tag":160,"props":462,"children":463},{"class":162,"line":216},[464],{"type":40,"tag":160,"props":465,"children":466},{},[467],{"type":45,"value":468},"ORDER BY views DESC\n",{"type":40,"tag":160,"props":470,"children":471},{"class":162,"line":225},[472],{"type":40,"tag":160,"props":473,"children":474},{},[475],{"type":45,"value":476},"LIMIT 20\n",{"type":40,"tag":41,"props":478,"children":479},{},[480,485],{"type":40,"tag":51,"props":481,"children":482},{},[483],{"type":45,"value":484},"4. Session replay views",{"type":45,"value":486}," — replays they've watched:",{"type":40,"tag":149,"props":488,"children":490},{"className":151,"code":489,"language":153,"meta":154,"style":154},"SELECT\n  properties.session_id as session_id,\n  properties.$current_url as url,\n  timestamp\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = '$recording_viewed'\n  AND timestamp >= now() - interval {days} day\nORDER BY timestamp DESC\nLIMIT 20\n",[491],{"type":40,"tag":59,"props":492,"children":493},{"__ignoreMap":154},[494,502,510,518,526,533,540,548,555,563],{"type":40,"tag":160,"props":495,"children":496},{"class":162,"line":163},[497],{"type":40,"tag":160,"props":498,"children":499},{},[500],{"type":45,"value":501},"SELECT\n",{"type":40,"tag":160,"props":503,"children":504},{"class":162,"line":172},[505],{"type":40,"tag":160,"props":506,"children":507},{},[508],{"type":45,"value":509},"  properties.session_id as session_id,\n",{"type":40,"tag":160,"props":511,"children":512},{"class":162,"line":181},[513],{"type":40,"tag":160,"props":514,"children":515},{},[516],{"type":45,"value":517},"  properties.$current_url as url,\n",{"type":40,"tag":160,"props":519,"children":520},{"class":162,"line":27},[521],{"type":40,"tag":160,"props":522,"children":523},{},[524],{"type":45,"value":525},"  timestamp\n",{"type":40,"tag":160,"props":527,"children":528},{"class":162,"line":198},[529],{"type":40,"tag":160,"props":530,"children":531},{},[532],{"type":45,"value":178},{"type":40,"tag":160,"props":534,"children":535},{"class":162,"line":207},[536],{"type":40,"tag":160,"props":537,"children":538},{},[539],{"type":45,"value":187},{"type":40,"tag":160,"props":541,"children":542},{"class":162,"line":216},[543],{"type":40,"tag":160,"props":544,"children":545},{},[546],{"type":45,"value":547},"  AND event = '$recording_viewed'\n",{"type":40,"tag":160,"props":549,"children":550},{"class":162,"line":225},[551],{"type":40,"tag":160,"props":552,"children":553},{},[554],{"type":45,"value":195},{"type":40,"tag":160,"props":556,"children":557},{"class":162,"line":234},[558],{"type":40,"tag":160,"props":559,"children":560},{},[561],{"type":45,"value":562},"ORDER BY timestamp DESC\n",{"type":40,"tag":160,"props":564,"children":565},{"class":162,"line":243},[566],{"type":40,"tag":160,"props":567,"children":568},{},[569],{"type":45,"value":476},{"type":40,"tag":41,"props":571,"children":572},{},[573,578],{"type":40,"tag":51,"props":574,"children":575},{},[576],{"type":45,"value":577},"5. Error tracking usage",{"type":45,"value":579}," — how they interact with error tracking in PostHog:",{"type":40,"tag":149,"props":581,"children":583},{"className":151,"code":582,"language":153,"meta":154,"style":154},"SELECT event, properties.issue_id as issue_id, properties.issue_name as issue_name, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event IN ('error tracking issue viewed', 'error tracking issue resolved', 'error tracking issue assigned', 'error tracking issue suppressed', 'error tracking list viewed')\n  AND timestamp >= now() - interval {days} day\nGROUP BY event, issue_id, issue_name\nORDER BY cnt DESC\nLIMIT 20\n",[584],{"type":40,"tag":59,"props":585,"children":586},{"__ignoreMap":154},[587,595,602,609,617,624,632,639],{"type":40,"tag":160,"props":588,"children":589},{"class":162,"line":163},[590],{"type":40,"tag":160,"props":591,"children":592},{},[593],{"type":45,"value":594},"SELECT event, properties.issue_id as issue_id, properties.issue_name as issue_name, count() as cnt\n",{"type":40,"tag":160,"props":596,"children":597},{"class":162,"line":172},[598],{"type":40,"tag":160,"props":599,"children":600},{},[601],{"type":45,"value":178},{"type":40,"tag":160,"props":603,"children":604},{"class":162,"line":181},[605],{"type":40,"tag":160,"props":606,"children":607},{},[608],{"type":45,"value":187},{"type":40,"tag":160,"props":610,"children":611},{"class":162,"line":27},[612],{"type":40,"tag":160,"props":613,"children":614},{},[615],{"type":45,"value":616},"  AND event IN ('error tracking issue viewed', 'error tracking issue resolved', 'error tracking issue assigned', 'error tracking issue suppressed', 'error tracking list viewed')\n",{"type":40,"tag":160,"props":618,"children":619},{"class":162,"line":198},[620],{"type":40,"tag":160,"props":621,"children":622},{},[623],{"type":45,"value":195},{"type":40,"tag":160,"props":625,"children":626},{"class":162,"line":207},[627],{"type":40,"tag":160,"props":628,"children":629},{},[630],{"type":45,"value":631},"GROUP BY event, issue_id, issue_name\n",{"type":40,"tag":160,"props":633,"children":634},{"class":162,"line":216},[635],{"type":40,"tag":160,"props":636,"children":637},{},[638],{"type":45,"value":312},{"type":40,"tag":160,"props":640,"children":641},{"class":162,"line":225},[642],{"type":40,"tag":160,"props":643,"children":644},{},[645],{"type":45,"value":476},{"type":40,"tag":41,"props":647,"children":648},{},[649,654],{"type":40,"tag":51,"props":650,"children":651},{},[652],{"type":45,"value":653},"6. PostHog AI usage",{"type":45,"value":655}," — Max and insight analysis counts:",{"type":40,"tag":149,"props":657,"children":659},{"className":151,"code":658,"language":153,"meta":154,"style":154},"SELECT event, count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event IN ('$ai_generation', '$conversations_loaded', 'insight analyzed', 'chat with data opened')\n  AND timestamp >= now() - interval {days} day\nGROUP BY event\nORDER BY cnt DESC\n",[660],{"type":40,"tag":59,"props":661,"children":662},{"__ignoreMap":154},[663,670,677,684,692,699,706],{"type":40,"tag":160,"props":664,"children":665},{"class":162,"line":163},[666],{"type":40,"tag":160,"props":667,"children":668},{},[669],{"type":45,"value":169},{"type":40,"tag":160,"props":671,"children":672},{"class":162,"line":172},[673],{"type":40,"tag":160,"props":674,"children":675},{},[676],{"type":45,"value":178},{"type":40,"tag":160,"props":678,"children":679},{"class":162,"line":181},[680],{"type":40,"tag":160,"props":681,"children":682},{},[683],{"type":45,"value":187},{"type":40,"tag":160,"props":685,"children":686},{"class":162,"line":27},[687],{"type":40,"tag":160,"props":688,"children":689},{},[690],{"type":45,"value":691},"  AND event IN ('$ai_generation', '$conversations_loaded', 'insight analyzed', 'chat with data opened')\n",{"type":40,"tag":160,"props":693,"children":694},{"class":162,"line":198},[695],{"type":40,"tag":160,"props":696,"children":697},{},[698],{"type":45,"value":195},{"type":40,"tag":160,"props":700,"children":701},{"class":162,"line":207},[702],{"type":40,"tag":160,"props":703,"children":704},{},[705],{"type":45,"value":303},{"type":40,"tag":160,"props":707,"children":708},{"class":162,"line":216},[709],{"type":40,"tag":160,"props":710,"children":711},{},[712],{"type":45,"value":312},{"type":40,"tag":41,"props":714,"children":715},{},[716,721],{"type":40,"tag":51,"props":717,"children":718},{},[719],{"type":45,"value":720},"7. Where they open Max",{"type":45,"value":722}," — which pages\u002Fcontexts they use Max on:",{"type":40,"tag":149,"props":724,"children":726},{"className":151,"code":725,"language":153,"meta":154,"style":154},"SELECT\n  properties.$current_url as url,\n  count() as cnt\nFROM events\nWHERE person.properties.email = '{email}'\n  AND event = '$conversations_loaded'\n  AND timestamp >= now() - interval {days} day\n  AND properties.$current_url LIKE '%posthog.com\u002Fproject%'\nGROUP BY url\nORDER BY cnt DESC\nLIMIT 20\n",[727],{"type":40,"tag":59,"props":728,"children":729},{"__ignoreMap":154},[730,737,744,752,759,766,774,781,789,796,803],{"type":40,"tag":160,"props":731,"children":732},{"class":162,"line":163},[733],{"type":40,"tag":160,"props":734,"children":735},{},[736],{"type":45,"value":501},{"type":40,"tag":160,"props":738,"children":739},{"class":162,"line":172},[740],{"type":40,"tag":160,"props":741,"children":742},{},[743],{"type":45,"value":517},{"type":40,"tag":160,"props":745,"children":746},{"class":162,"line":181},[747],{"type":40,"tag":160,"props":748,"children":749},{},[750],{"type":45,"value":751},"  count() as cnt\n",{"type":40,"tag":160,"props":753,"children":754},{"class":162,"line":27},[755],{"type":40,"tag":160,"props":756,"children":757},{},[758],{"type":45,"value":178},{"type":40,"tag":160,"props":760,"children":761},{"class":162,"line":198},[762],{"type":40,"tag":160,"props":763,"children":764},{},[765],{"type":45,"value":187},{"type":40,"tag":160,"props":767,"children":768},{"class":162,"line":207},[769],{"type":40,"tag":160,"props":770,"children":771},{},[772],{"type":45,"value":773},"  AND event = '$conversations_loaded'\n",{"type":40,"tag":160,"props":775,"children":776},{"class":162,"line":216},[777],{"type":40,"tag":160,"props":778,"children":779},{},[780],{"type":45,"value":195},{"type":40,"tag":160,"props":782,"children":783},{"class":162,"line":225},[784],{"type":40,"tag":160,"props":785,"children":786},{},[787],{"type":45,"value":788},"  AND properties.$current_url LIKE '%posthog.com\u002Fproject%'\n",{"type":40,"tag":160,"props":790,"children":791},{"class":162,"line":234},[792],{"type":40,"tag":160,"props":793,"children":794},{},[795],{"type":45,"value":383},{"type":40,"tag":160,"props":797,"children":798},{"class":162,"line":243},[799],{"type":40,"tag":160,"props":800,"children":801},{},[802],{"type":45,"value":312},{"type":40,"tag":160,"props":804,"children":805},{"class":162,"line":252},[806],{"type":40,"tag":160,"props":807,"children":808},{},[809],{"type":45,"value":476},{"type":40,"tag":75,"props":811,"children":813},{"id":812},"step-2-cross-reference-with-vitally",[814],{"type":45,"value":815},"Step 2: Cross-reference with Vitally",{"type":40,"tag":41,"props":817,"children":818},{},[819],{"type":45,"value":820},"Use Vitally tools to look up the user by email — get their role, title, account name, and any CRM data available.",{"type":40,"tag":116,"props":822,"children":823},{},[],{"type":40,"tag":68,"props":825,"children":827},{"id":826},"output-format",[828],{"type":45,"value":829},"Output Format",{"type":40,"tag":75,"props":831,"children":833},{"id":832},"executive-summary",[834],{"type":45,"value":835},"Executive Summary",{"type":40,"tag":41,"props":837,"children":838},{},[839],{"type":45,"value":840},"2–3 sentences capturing who this person is, what they primarily use PostHog for, and the single most interesting or actionable thing about their usage. Write it as if briefing someone before a call with this user.",{"type":40,"tag":116,"props":842,"children":843},{},[],{"type":40,"tag":75,"props":845,"children":847},{"id":846},"profile",[848],{"type":45,"value":849},"Profile",{"type":40,"tag":851,"props":852,"children":853},"ul",{},[854,860,865],{"type":40,"tag":855,"props":856,"children":857},"li",{},[858],{"type":45,"value":859},"Name, email, role\u002Ftitle, LinkedIn (if available)",{"type":40,"tag":855,"props":861,"children":862},{},[863],{"type":45,"value":864},"Location (from timezone or geo data)",{"type":40,"tag":855,"props":866,"children":867},{},[868],{"type":45,"value":869},"Account they belong to",{"type":40,"tag":75,"props":871,"children":873},{"id":872},"activity-summary-last-days-days",[874],{"type":45,"value":875},"Activity Summary (last {days} days)",{"type":40,"tag":851,"props":877,"children":878},{},[879,884],{"type":40,"tag":855,"props":880,"children":881},{},[882],{"type":45,"value":883},"Total events, key event types",{"type":40,"tag":855,"props":885,"children":886},{},[887],{"type":45,"value":888},"How many queries run, insights viewed, dashboards checked, exports done",{"type":40,"tag":75,"props":890,"children":892},{"id":891},"where-they-spend-time",[893],{"type":45,"value":894},"Where They Spend Time",{"type":40,"tag":851,"props":896,"children":897},{},[898,903,908],{"type":40,"tag":855,"props":899,"children":900},{},[901],{"type":45,"value":902},"Which PostHog projects (extract project IDs from URLs)",{"type":40,"tag":855,"props":904,"children":905},{},[906],{"type":45,"value":907},"Which product areas (analytics, replay, flags, LLM analytics, data management, error tracking, etc.)",{"type":40,"tag":855,"props":909,"children":910},{},[911],{"type":45,"value":912},"Specific dashboards or insights they revisit",{"type":40,"tag":75,"props":914,"children":916},{"id":915},"what-theyre-doing",[917],{"type":45,"value":918},"What They're Doing",{"type":40,"tag":851,"props":920,"children":921},{},[922,927,932],{"type":40,"tag":855,"props":923,"children":924},{},[925],{"type":45,"value":926},"Interpret the insight names and patterns — what business questions are they answering?",{"type":40,"tag":855,"props":928,"children":929},{},[930],{"type":45,"value":931},"Are they building things (creating insights, actions, destinations) or consuming (viewing dashboards, exporting)?",{"type":40,"tag":855,"props":933,"children":934},{},[935],{"type":45,"value":936},"Error tracking: are they actively triaging errors (resolving, assigning, suppressing) or just browsing?",{"type":40,"tag":75,"props":938,"children":940},{"id":939},"session-recordings",[941],{"type":45,"value":942},"Session Recordings",{"type":40,"tag":851,"props":944,"children":945},{},[946,957],{"type":40,"tag":855,"props":947,"children":948},{},[949,951],{"type":45,"value":950},"Link directly to PostHog session replay filtered to this user:\n",{"type":40,"tag":59,"props":952,"children":954},{"className":953},[],[955],{"type":45,"value":956},"https:\u002F\u002Fus.posthog.com\u002Freplay?filters={\"type\":\"AND\",\"values\":[{\"type\":\"AND\",\"values\":[{\"key\":\"email\",\"value\":[\"{email}\"],\"operator\":\"exact\",\"type\":\"person\"}]}]}",{"type":40,"tag":855,"props":958,"children":959},{},[960],{"type":45,"value":961},"Summarise any patterns from the replays they've watched (query 4): which parts of the product, how recently",{"type":40,"tag":75,"props":963,"children":965},{"id":964},"posthog-ai-usage",[966],{"type":45,"value":967},"PostHog AI Usage",{"type":40,"tag":851,"props":969,"children":970},{},[971,992,1005,1047],{"type":40,"tag":855,"props":972,"children":973},{},[974,976,982,984,990],{"type":45,"value":975},"How often do they open Max (",{"type":40,"tag":59,"props":977,"children":979},{"className":978},[],[980],{"type":45,"value":981},"$conversations_loaded",{"type":45,"value":983}," count) and make AI calls (",{"type":40,"tag":59,"props":985,"children":987},{"className":986},[],[988],{"type":45,"value":989},"$ai_generation",{"type":45,"value":991}," count)?",{"type":40,"tag":855,"props":993,"children":994},{},[995,997,1003],{"type":45,"value":996},"Do they use insight analysis (",{"type":40,"tag":59,"props":998,"children":1000},{"className":999},[],[1001],{"type":45,"value":1002},"insight analyzed",{"type":45,"value":1004},")?",{"type":40,"tag":855,"props":1006,"children":1007},{},[1008,1013,1015,1021,1023,1029,1031,1037,1039,1045],{"type":40,"tag":51,"props":1009,"children":1010},{},[1011],{"type":45,"value":1012},"Where do they open Max?",{"type":45,"value":1014}," — Summarise the URLs from query 7. Extract the product area from each URL (e.g. ",{"type":40,"tag":59,"props":1016,"children":1018},{"className":1017},[],[1019],{"type":45,"value":1020},"\u002Fdashboard\u002F",{"type":45,"value":1022}," → \"dashboards\", ",{"type":40,"tag":59,"props":1024,"children":1026},{"className":1025},[],[1027],{"type":45,"value":1028},"\u002Fsql",{"type":45,"value":1030}," → \"SQL editor\", ",{"type":40,"tag":59,"props":1032,"children":1034},{"className":1033},[],[1035],{"type":45,"value":1036},"\u002Finsights\u002F",{"type":45,"value":1038}," → \"insights\", ",{"type":40,"tag":59,"props":1040,"children":1042},{"className":1041},[],[1043],{"type":45,"value":1044},"\u002Fpersons\u002F",{"type":45,"value":1046}," → \"person profiles\") and list the top contexts with counts. This tells us what they're trying to get help with.",{"type":40,"tag":855,"props":1048,"children":1049},{},[1050],{"type":45,"value":1051},"Are they looking at LLM Analytics?",{"type":40,"tag":75,"props":1053,"children":1055},{"id":1054},"outreach-angles",[1056],{"type":45,"value":1057},"Outreach Angles",{"type":40,"tag":851,"props":1059,"children":1060},{},[1061,1066,1071],{"type":40,"tag":855,"props":1062,"children":1063},{},[1064],{"type":45,"value":1065},"Based on their usage, suggest 2-3 conversation starters for the user's outreach",{"type":40,"tag":855,"props":1067,"children":1068},{},[1069],{"type":45,"value":1070},"Flag any pain points (query failures, rage clicks, error tracking spikes, etc.)",{"type":40,"tag":855,"props":1072,"children":1073},{},[1074],{"type":45,"value":1075},"Note any products they're NOT using that would be relevant",{"type":40,"tag":116,"props":1077,"children":1078},{},[],{"type":40,"tag":68,"props":1080,"children":1082},{"id":1081},"important",[1083],{"type":45,"value":1084},"Important",{"type":40,"tag":851,"props":1086,"children":1087},{},[1088,1100,1112,1125,1130,1135],{"type":40,"tag":855,"props":1089,"children":1090},{},[1091,1093,1098],{"type":45,"value":1092},"Ask for the time window ",{"type":40,"tag":51,"props":1094,"children":1095},{},[1096],{"type":45,"value":1097},"before",{"type":45,"value":1099}," running any queries.",{"type":40,"tag":855,"props":1101,"children":1102},{},[1103,1105,1110],{"type":45,"value":1104},"Use the PostHog MCP ",{"type":40,"tag":59,"props":1106,"children":1108},{"className":1107},[],[1109],{"type":45,"value":135},{"type":45,"value":1111}," tool, NOT curl. Fall back to curl only if MCP is unavailable.",{"type":40,"tag":855,"props":1113,"children":1114},{},[1115,1117,1123],{"type":45,"value":1116},"Vitally ",{"type":40,"tag":59,"props":1118,"children":1120},{"className":1119},[],[1121],{"type":45,"value":1122},"lastSeenTimestamp",{"type":45,"value":1124}," data is stale — do NOT rely on it for activity. Always use PostHog event data.",{"type":40,"tag":855,"props":1126,"children":1127},{},[1128],{"type":45,"value":1129},"Run all PostHog queries in parallel to save time.",{"type":40,"tag":855,"props":1131,"children":1132},{},[1133],{"type":45,"value":1134},"If PostHog returns 503 (busy), wait a moment and retry once before giving up on that query.",{"type":40,"tag":855,"props":1136,"children":1137},{},[1138],{"type":45,"value":1139},"The session replay link should use the user's actual email in the filter parameter.",{"type":40,"tag":1141,"props":1142,"children":1143},"style",{},[1144],{"type":45,"value":1145},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1147,"total":1318},[1148,1165,1177,1190,1203,1218,1234,1251,1265,1280,1290,1308],{"slug":1149,"name":1149,"fn":1150,"description":1151,"org":1152,"tags":1153,"stars":1162,"repoUrl":1163,"updatedAt":1164},"analyzing-expensive-users","analyze expensive users in AI observability","Analyze the most expensive users in AI observability and explain why they cost so much. Use when the user asks about top spenders, expensive users, per-user LLM cost, user-level cost drivers, or patterns behind high AI observability spend.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1154,1155,1158,1161],{"name":21,"slug":22,"type":13},{"name":1156,"slug":1157,"type":13},"Cost Optimization","cost-optimization",{"name":1159,"slug":1160,"type":13},"Observability","observability",{"name":9,"slug":8,"type":13},35568,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog","2026-07-28T05:34:11.117757",{"slug":1166,"name":1166,"fn":1167,"description":1168,"org":1169,"tags":1170,"stars":1162,"repoUrl":1163,"updatedAt":1176},"auditing-endpoints","audit PostHog project endpoints","Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks \"what endpoints can I clean up?\", \"are any of my endpoints broken?\", \"which materialised versions are still being called?\", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1171,1172,1175],{"name":21,"slug":22,"type":13},{"name":1173,"slug":1174,"type":13},"Audit","audit",{"name":9,"slug":8,"type":13},"2026-06-08T08:08:33.693989",{"slug":1178,"name":1178,"fn":1179,"description":1180,"org":1181,"tags":1182,"stars":1162,"repoUrl":1163,"updatedAt":1189},"auditing-warehouse-source-health","audit PostHog data warehouse source health","Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel. Use when the user asks \"why are my imports failing?\", \"what's broken with my sources?\", \"why is my warehouse data stale?\", or wants a one-shot triage of source\u002Fsync health before deciding where to dig in. Produces a prioritized report grouped by severity, with recommended next steps. For materialized-view health use `auditing-warehouse-view-health`; for a single failing sync use `diagnosing-failed-warehouse-syncs`.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1183,1184,1187,1188],{"name":1173,"slug":1174,"type":13},{"name":1185,"slug":1186,"type":13},"Data Warehouse","data-warehouse",{"name":1159,"slug":1160,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:22:57.67984",{"slug":1191,"name":1191,"fn":1192,"description":1193,"org":1194,"tags":1195,"stars":1162,"repoUrl":1163,"updatedAt":1202},"auditing-warehouse-view-health","audit PostHog materialized view health","Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that cost storage and compute. Use when the user asks \"which of my views are broken?\", \"why is this materialized view failing?\", \"are any of my views wasting compute?\", or wants a one-shot triage of view health. For source\u002Fsync health use `auditing-warehouse-source-health`.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1196,1197,1198,1201],{"name":1173,"slug":1174,"type":13},{"name":1185,"slug":1186,"type":13},{"name":1199,"slug":1200,"type":13},"Performance","performance",{"name":9,"slug":8,"type":13},"2026-06-18T08:25:10.936787",{"slug":1204,"name":1204,"fn":1205,"description":1206,"org":1207,"tags":1208,"stars":1162,"repoUrl":1163,"updatedAt":1217},"authoring-error-tracking-alerts","author PostHog error tracking alerts","Author error tracking alerts that fire when an issue is created, reopened, or starts spiking. Use when the user asks to set up error notifications, route exceptions to Slack\u002Fwebhook\u002FLinear, or evaluate which error events are worth alerting on. Covers trigger-event selection, integration choice, dedup against existing alerts, and shipping with the canonical message body shape.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1209,1212,1215,1216],{"name":1210,"slug":1211,"type":13},"Alerting","alerting",{"name":1213,"slug":1214,"type":13},"Debugging","debugging",{"name":1159,"slug":1160,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:24:40.318583",{"slug":1219,"name":1219,"fn":1220,"description":1221,"org":1222,"tags":1223,"stars":1162,"repoUrl":1163,"updatedAt":1233},"authoring-log-alerts","author log alerts in PostHog","Author useful, low-noise log alerts on services in a PostHog project. Use when the user asks to set up alerts for their logs, suggest alerts they should add, or evaluate whether a service is worth monitoring. Covers service triage, baseline characterisation, threshold drafting, back-testing via simulate, and shipping with a notification destination.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1224,1225,1228,1229,1232],{"name":21,"slug":22,"type":13},{"name":1226,"slug":1227,"type":13},"Monitoring","monitoring",{"name":1159,"slug":1160,"type":13},{"name":1230,"slug":1231,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-18T05:10:54.430898",{"slug":1235,"name":1235,"fn":1236,"description":1237,"org":1238,"tags":1239,"stars":1162,"repoUrl":1163,"updatedAt":1250},"building-workflows","build and edit PostHog workflows","Build, edit, test, enable, and monitor PostHog workflows over MCP. Author the action\u002Fedge graph so it runs and opens cleanly in the visual editor, then change drafts surgically with patch operations. Use when asked to build, set up, automate, change, fix, or debug a workflow, campaign, broadcast, drip sequence, or event-triggered automation in the workflows product.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1240,1243,1246,1247],{"name":1241,"slug":1242,"type":13},"Automation","automation",{"name":1244,"slug":1245,"type":13},"MCP","mcp",{"name":9,"slug":8,"type":13},{"name":1248,"slug":1249,"type":13},"Workflow Automation","workflow-automation","2026-07-28T05:34:12.167015",{"slug":1252,"name":1252,"fn":1253,"description":1254,"org":1255,"tags":1256,"stars":1162,"repoUrl":1163,"updatedAt":1264},"check-posthog-loading","inspect PostHog SDK loading across URLs","Inspect how the PostHog JavaScript SDK is loaded across a list of URLs. Use to confirm consistent installation across pages, find pages missing the snippet, detect mismatched API keys or hosts between pages, and verify the load method (head snippet vs deferred vs array.js).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1257,1258,1259,1262,1263],{"name":21,"slug":22,"type":13},{"name":1213,"slug":1214,"type":13},{"name":1260,"slug":1261,"type":13},"Frontend","frontend",{"name":1159,"slug":1160,"type":13},{"name":9,"slug":8,"type":13},"2026-05-07T05:56:19.828048",{"slug":1266,"name":1266,"fn":1267,"description":1268,"org":1269,"tags":1270,"stars":1162,"repoUrl":1163,"updatedAt":1279},"consuming-endpoints-from-client-code","integrate PostHog endpoints into client applications","Wire a PostHog endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api\u002Fopenapi-ts, sending the right auth header, shaping the variables payload (HogQL code_name vs insight breakdown property), handling rate-limit and materialised-endpoint error responses. Use when the user says \"how do I call my endpoint\", \"generate a client for this\", or \"what auth header do I use\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1271,1274,1275,1276],{"name":1272,"slug":1273,"type":13},"API Development","api-development",{"name":1260,"slug":1261,"type":13},{"name":9,"slug":8,"type":13},{"name":1277,"slug":1278,"type":13},"SDK","sdk","2026-06-08T08:08:34.929454",{"slug":1281,"name":1281,"fn":1282,"description":1283,"org":1284,"tags":1285,"stars":1162,"repoUrl":1163,"updatedAt":1289},"copying-endpoints-across-projects","copy PostHog endpoints across projects","Copy a PostHog endpoint (a saved HogQL\u002Finsight query exposed as an API route) to another project in the same organization, or duplicate it under a new name in the same project. Use when the user wants to duplicate an endpoint, promote an endpoint from staging to production, replicate an endpoint's query\u002Fvariables\u002Ffreshness config in another workspace, or clone an endpoint to iterate on it. Unlike feature flags and experiments, endpoints have NO native cross-project copy tool — this skill covers the read-then-recreate flow (endpoint-get then endpoint-create), the active-project switching it requires, name-collision checks, and the safe defaults (land unmaterialised in the target, verify with endpoint-run). Does not cover editing endpoint versions (see managing-endpoint-versions) or authoring a brand-new endpoint from scratch (see creating-an-endpoint).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1286,1287,1288],{"name":1272,"slug":1273,"type":13},{"name":1230,"slug":1231,"type":13},{"name":9,"slug":8,"type":13},"2026-07-15T05:29:58.442727",{"slug":1291,"name":1291,"fn":1292,"description":1293,"org":1294,"tags":1295,"stars":1162,"repoUrl":1163,"updatedAt":1307},"creating-ai-subscription","schedule recurring AI-generated PostHog reports","Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email or Slack on each tick. Use when the user wants a recurring AI summary of X on any cadence (daily, weekly, monthly, yearly) rather than a one-off report. (To attach an AI summary to an existing insight\u002Fdashboard subscription instead of a free-text prompt, see `managing-subscriptions` and its `summary_enabled` option.)\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1296,1297,1300,1301,1304],{"name":1241,"slug":1242,"type":13},{"name":1298,"slug":1299,"type":13},"Email","email",{"name":9,"slug":8,"type":13},{"name":1302,"slug":1303,"type":13},"Reporting","reporting",{"name":1305,"slug":1306,"type":13},"Slack","slack","2026-06-09T07:32:27.935712",{"slug":1309,"name":1309,"fn":1310,"description":1311,"org":1312,"tags":1313,"stars":1162,"repoUrl":1163,"updatedAt":1317},"creating-an-endpoint","create PostHog API endpoints","Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs insight breakdown), data_freshness_seconds, and whether to materialise on day one. Use when the user says \"create an endpoint\", \"expose this query as an API\", \"turn this insight into an endpoint\", or asks for help structuring a new endpoint. Steers away from common mistakes: materialising a query with cohort breakdowns or compare mode, inline-only variables on a materialised endpoint, unbounded date ranges, ambiguous names.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1314,1315,1316],{"name":21,"slug":22,"type":13},{"name":1272,"slug":1273,"type":13},{"name":9,"slug":8,"type":13},"2026-06-08T08:08:29.624498",231,{"items":1320,"total":1423},[1321,1338,1354,1368,1384,1396,1407],{"slug":1322,"name":1322,"fn":1323,"description":1324,"org":1325,"tags":1326,"stars":23,"repoUrl":24,"updatedAt":1337},"account-handover","draft sales account handover notes","Draft structured handover notes for transitioning a PostHog account from one TAM or CSM to another. Use this skill when a TAM needs to hand over an account, prepare a transition briefing, write handover notes, create an account summary for a new owner, or any request involving account transitions between TAMs or CSMs. Triggers on \"hand over this account\", \"transition account to\", \"draft handover notes\", \"account briefing for new TAM\", \"prepare account transition\", or when a TAM names an account and says they're leaving or reassigning it.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1327,1330,1333,1334],{"name":1328,"slug":1329,"type":13},"Communications","communications",{"name":1331,"slug":1332,"type":13},"CRM","crm",{"name":9,"slug":8,"type":13},{"name":1335,"slug":1336,"type":13},"Sales","sales","2026-04-16T05:13:00.172732",{"slug":1339,"name":1339,"fn":1340,"description":1341,"org":1342,"tags":1343,"stars":23,"repoUrl":24,"updatedAt":1353},"auditing-warehouse-data-health","audit PostHog data warehouse health","Audit the health of a PostHog project's data warehouse — find every broken or degraded pipeline item across sources, sync schemas, materialized views, batch exports, and transformations. Use when the user asks \"what's broken in my warehouse?\", \"give me a health check\", \"audit my data pipeline\", \"why are some dashboards stale?\", or wants a one-shot triage summary before deciding where to spend time. Produces a prioritized report of issues grouped by severity and type, with recommended next steps.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1344,1345,1348,1351,1352],{"name":1173,"slug":1174,"type":13},{"name":1346,"slug":1347,"type":13},"Data Engineering","data-engineering",{"name":1349,"slug":1350,"type":13},"Data Quality","data-quality",{"name":1159,"slug":1160,"type":13},{"name":9,"slug":8,"type":13},"2026-06-21T08:19:05.85849",{"slug":1355,"name":1355,"fn":1356,"description":1357,"org":1358,"tags":1359,"stars":23,"repoUrl":24,"updatedAt":1367},"copying-flags-across-projects","copy feature flags across PostHog projects","Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a flag from staging to production, sync flags across projects, or replicate a flag configuration in a different workspace. Covers cohort remapping, scheduled-change handling, encrypted payloads, and the safe defaults (disabled in target, no scheduled changes).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1360,1363,1366],{"name":1361,"slug":1362,"type":13},"Deployment","deployment",{"name":1364,"slug":1365,"type":13},"Feature Flags","feature-flags",{"name":9,"slug":8,"type":13},"2026-05-04T05:56:44.484909",{"slug":1369,"name":1369,"fn":1370,"description":1371,"org":1372,"tags":1373,"stars":23,"repoUrl":24,"updatedAt":1383},"diagnosing-experiment-results","diagnose PostHog experiment results and anomalies","Diagnoses bias, anomalies, and strange-looking results on a specific PostHog experiment. Covers empty \u002F 0-exposure experiments, sample ratio mismatch, identity fragmentation, multi-variant exposure, uneven-split exclusion bias, significance traps (peeking, A\u002FA, Bayesian vs Frequentist), PostHog-vs-SQL discrepancies, and surprises after mid-run edits. Symptom-driven dispatch to the right diagnostic.\nTRIGGER when: user asks 'is my experiment biased?' or 'why 0 exposures?', references the bias banner, says a variant looks strange \u002F wrong \u002F off, sees significance flipping, notices PostHog numbers disagreeing with their SQL, sees an A\u002FA test showing significance, or reports surprises after mid-run edits.\nDO NOT TRIGGER when: creating a new experiment (use creating-experiments), only configuring rollout (use configuring-experiment-rollout) or metrics (use configuring-experiment-analytics), or only asking lifecycle questions (use managing-experiment-lifecycle).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1374,1377,1378,1381,1382],{"name":1375,"slug":1376,"type":13},"A\u002FB Testing","a-b-testing",{"name":21,"slug":22,"type":13},{"name":1379,"slug":1380,"type":13},"Data Analysis","data-analysis",{"name":1213,"slug":1214,"type":13},{"name":9,"slug":8,"type":13},"2026-05-22T06:59:58.103867",{"slug":1385,"name":1385,"fn":1386,"description":1387,"org":1388,"tags":1389,"stars":23,"repoUrl":24,"updatedAt":1395},"diagnosing-missing-recordings","diagnose missing PostHog session recordings","Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling, triggers, ad blockers, and quota\u002Fbilling scenarios.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1390,1391,1392,1393,1394],{"name":21,"slug":22,"type":13},{"name":1213,"slug":1214,"type":13},{"name":1260,"slug":1261,"type":13},{"name":1159,"slug":1160,"type":13},{"name":9,"slug":8,"type":13},"2026-04-22T05:06:51.989772",{"slug":1397,"name":1397,"fn":1398,"description":1399,"org":1400,"tags":1401,"stars":23,"repoUrl":24,"updatedAt":1406},"diagnosing-sdk-health","diagnose PostHog SDK health","Diagnoses the health of a project's PostHog SDK integrations — which SDKs are out of date and how to fix them. Use when a user asks about PostHog SDK versions, outdated SDKs, upgrade recommendations, \"SDK health\", \"SDK doctor\" (the former name), or when events or features seem off and it might be due to an old SDK.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1402,1403,1404,1405],{"name":21,"slug":22,"type":13},{"name":1213,"slug":1214,"type":13},{"name":1159,"slug":1160,"type":13},{"name":9,"slug":8,"type":13},"2026-04-27T05:46:14.554016",{"slug":1408,"name":1408,"fn":1409,"description":1410,"org":1411,"tags":1412,"stars":23,"repoUrl":24,"updatedAt":1422},"error-tracking-android","track Android errors with PostHog","PostHog error tracking for Android",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1413,1416,1417,1420,1421],{"name":1414,"slug":1415,"type":13},"Android","android",{"name":1213,"slug":1214,"type":13},{"name":1418,"slug":1419,"type":13},"Mobile","mobile",{"name":1159,"slug":1160,"type":13},{"name":9,"slug":8,"type":13},"2026-04-06T18:46:26.982494",110]