[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-posthog-creating-experiments":3,"mdc-x2i5z3-key":38,"related-org-posthog-creating-experiments":1143,"related-repo-posthog-creating-experiments":1316},{"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":33,"sourceUrl":36,"mdContent":37},"creating-experiments","create experiments in PostHog","Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics.\nTRIGGER when: user asks to create a new experiment or A\u002FB test, OR when you are about to call experiment-create.\nDO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.",{"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},"Product Management","product-management",{"name":18,"slug":19,"type":13},"Analytics","analytics",{"name":21,"slug":22,"type":13},"A\u002FB Testing","a-b-testing",59,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fai-plugin","2026-07-18T05:11:43.415403",null,11,[29,30,31,32],"claude-code-plugin","codex-plugin","cursor-plugin","gemini-cli-extension",{"repoUrl":24,"stars":23,"forks":27,"topics":34,"description":35},[29,30,31,32],"Official PostHog plugin for Claude Code, Cursor, Gemini, Codex and other AI coding tools","https:\u002F\u002Fgithub.com\u002FPostHog\u002Fai-plugin\u002Ftree\u002FHEAD\u002Fskills\u002Fcreating-experiments","---\nname: creating-experiments\ndescription: \"Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics.\\nTRIGGER when: user asks to create a new experiment or A\u002FB test, OR when you are about to call experiment-create.\\nDO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.\"\n---\n\n# Creating experiments\n\nThis skill walks through the 3-step flow for creating a new A\u002FB test experiment.\n\n## Core principle: draft first, iterate on details\n\nCreate the experiment as a draft quickly, then iterate on metrics and configuration.\nThe user gets a tangible draft immediately and can refine it.\n\n## The 3-step creation flow\n\n### Step 1: What are we testing?\n\nGather these before calling `experiment-create`:\n\n- **Experiment name** — descriptive, inferred from context when possible\n- **Hypothesis** — what you expect to happen (goes in `description`)\n- **Feature flag key** — kebab-case. Ask if they want a new flag or to reuse an existing one.\n  The flag is auto-created — do NOT create one separately.\n- **Type** — leave empty (will internally default to `\"product\"`. The `\"web\"` value is reserved for no-code experiments configured visually with the PostHog\n  toolbar in a browser; it cannot be meaningfully driven via MCP. If a user asks for a\n  no-code\u002Ftoolbar experiment, point them to the PostHog UI instead of creating one here.)\n\nIf the user gives enough context to infer these, don't ask — just proceed.\n\n### Step 2: Who sees what variant?\n\nThis is about rollout configuration.\n\n**Before asking any rollout question, load `configuring-experiment-rollout`.** The disambiguation wording, recommendations, and post-answer branches live there — do not formulate rollout questions yourself, and do not assume an example you remember covers the user's path.\n\nKey decision points (covered in detail by `configuring-experiment-rollout`):\n\n- Variant split (how many variants, what percentage each)\n- Overall rollout percentage (what % of all users enter the experiment)\n- Whether to persist the flag across authentication steps\n\nIf the user doesn't mention rollout specifics, use defaults: 50\u002F50 control\u002Ftest, 100% rollout.\n\n### Step 3: How to measure impact?\n\nThis is about analytics and metrics. **Load the `configuring-experiment-analytics` skill** for guidance.\nThat skill's first step checks for an existing **shared metric** to reuse before building a new one —\ndon't duplicate a metric the project already has set up.\n\n**Do NOT configure metrics on creation.** Metrics are not passed to `experiment-create` — they are added\nafterwards via `experiment-update`. This keeps the creation call lightweight.\n\nWhen the user specifies metrics upfront, acknowledge them and add them immediately after creation.\nWhen they don't, create the draft and then guide them through metric setup as a follow-up.\n\n## How to create\n\nCall `experiment-create` with:\n\n```json\n{\n  \"name\": \"Descriptive experiment name\",\n  \"feature_flag_key\": \"kebab-case-key\",\n  \"description\": \"Hypothesis: [what you expect to happen]\",\n  \"feature_flag\": {\n    \"filters\": {\n      \"multivariate\": {\n        \"variants\": [\n          { \"key\": \"control\", \"name\": \"Control\", \"rollout_percentage\": 50 },\n          { \"key\": \"test\", \"name\": \"Test\", \"rollout_percentage\": 50 }\n        ]\n      },\n      \"groups\": [{ \"properties\": [], \"rollout_percentage\": 100 }]\n    },\n    \"ensure_experience_continuity\": false\n  }\n}\n```\n\nFlag config goes in the `feature_flag` object, in the flag's own filters shape (not the deprecated `parameters` keys).\nTwo different percentages live in there, do NOT mix them up:\n\n- `filters.multivariate.variants[].rollout_percentage` is how users **inside** the experiment are split across variants (must sum to 100, recommended to have an even split).\n- `filters.groups[0].rollout_percentage` is the overall gate: what fraction of **all** users enter the experiment at all (0-100, defaults to 100).\n\nKey details:\n\n- Minimum 2, maximum 20 variants. No specific variant key is required — the analysis baseline defaults to the variant keyed `\"control\"` when present, else the first variant (override with `stats_config.baseline_variant_key`). Convention: key the baseline `\"control\"` unless the user asks for specific keys.\n- `filters.groups[0].rollout_percentage` defaults to 100 if omitted.\n- `ensure_experience_continuity` persists a user's variant across authentication steps; leave it `false` unless the flag is shown to both logged-out and logged-in users (see `configuring-experiment-rollout`).\n- Stats default to Bayesian. Only set `stats_config` if the user requests Frequentist.\n\n## After creation\n\n1. **Always show the experiment URL.** The `experiment-create` response includes `_posthogUrl` — always display this link so the user can view and configure the experiment in the UI.\n\n2. **Remind the user to implement the feature flag in code.** Link to the experiment page and say \"implement the flag as shown here\" — the experiment detail page shows implementation snippets for the user's SDK.\n\n3. **Guide through metrics** if not yet configured — load the `configuring-experiment-analytics` skill.\n\n4. **Launch** when ready — use the `experiment-launch` tool.\n",{"data":39,"body":40},{"name":4,"description":6},{"type":41,"children":42},"root",[43,51,57,64,69,75,82,96,166,171,177,182,200,212,230,235,241,268,293,298,304,316,914,934,973,978,1057,1063,1137],{"type":44,"tag":45,"props":46,"children":47},"element","h1",{"id":4},[48],{"type":49,"value":50},"text","Creating experiments",{"type":44,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"This skill walks through the 3-step flow for creating a new A\u002FB test experiment.",{"type":44,"tag":58,"props":59,"children":61},"h2",{"id":60},"core-principle-draft-first-iterate-on-details",[62],{"type":49,"value":63},"Core principle: draft first, iterate on details",{"type":44,"tag":52,"props":65,"children":66},{},[67],{"type":49,"value":68},"Create the experiment as a draft quickly, then iterate on metrics and configuration.\nThe user gets a tangible draft immediately and can refine it.",{"type":44,"tag":58,"props":70,"children":72},{"id":71},"the-3-step-creation-flow",[73],{"type":49,"value":74},"The 3-step creation flow",{"type":44,"tag":76,"props":77,"children":79},"h3",{"id":78},"step-1-what-are-we-testing",[80],{"type":49,"value":81},"Step 1: What are we testing?",{"type":44,"tag":52,"props":83,"children":84},{},[85,87,94],{"type":49,"value":86},"Gather these before calling ",{"type":44,"tag":88,"props":89,"children":91},"code",{"className":90},[],[92],{"type":49,"value":93},"experiment-create",{"type":49,"value":95},":",{"type":44,"tag":97,"props":98,"children":99},"ul",{},[100,112,130,140],{"type":44,"tag":101,"props":102,"children":103},"li",{},[104,110],{"type":44,"tag":105,"props":106,"children":107},"strong",{},[108],{"type":49,"value":109},"Experiment name",{"type":49,"value":111}," — descriptive, inferred from context when possible",{"type":44,"tag":101,"props":113,"children":114},{},[115,120,122,128],{"type":44,"tag":105,"props":116,"children":117},{},[118],{"type":49,"value":119},"Hypothesis",{"type":49,"value":121}," — what you expect to happen (goes in ",{"type":44,"tag":88,"props":123,"children":125},{"className":124},[],[126],{"type":49,"value":127},"description",{"type":49,"value":129},")",{"type":44,"tag":101,"props":131,"children":132},{},[133,138],{"type":44,"tag":105,"props":134,"children":135},{},[136],{"type":49,"value":137},"Feature flag key",{"type":49,"value":139}," — kebab-case. Ask if they want a new flag or to reuse an existing one.\nThe flag is auto-created — do NOT create one separately.",{"type":44,"tag":101,"props":141,"children":142},{},[143,148,150,156,158,164],{"type":44,"tag":105,"props":144,"children":145},{},[146],{"type":49,"value":147},"Type",{"type":49,"value":149}," — leave empty (will internally default to ",{"type":44,"tag":88,"props":151,"children":153},{"className":152},[],[154],{"type":49,"value":155},"\"product\"",{"type":49,"value":157},". The ",{"type":44,"tag":88,"props":159,"children":161},{"className":160},[],[162],{"type":49,"value":163},"\"web\"",{"type":49,"value":165}," value is reserved for no-code experiments configured visually with the PostHog\ntoolbar in a browser; it cannot be meaningfully driven via MCP. If a user asks for a\nno-code\u002Ftoolbar experiment, point them to the PostHog UI instead of creating one here.)",{"type":44,"tag":52,"props":167,"children":168},{},[169],{"type":49,"value":170},"If the user gives enough context to infer these, don't ask — just proceed.",{"type":44,"tag":76,"props":172,"children":174},{"id":173},"step-2-who-sees-what-variant",[175],{"type":49,"value":176},"Step 2: Who sees what variant?",{"type":44,"tag":52,"props":178,"children":179},{},[180],{"type":49,"value":181},"This is about rollout configuration.",{"type":44,"tag":52,"props":183,"children":184},{},[185,198],{"type":44,"tag":105,"props":186,"children":187},{},[188,190,196],{"type":49,"value":189},"Before asking any rollout question, load ",{"type":44,"tag":88,"props":191,"children":193},{"className":192},[],[194],{"type":49,"value":195},"configuring-experiment-rollout",{"type":49,"value":197},".",{"type":49,"value":199}," The disambiguation wording, recommendations, and post-answer branches live there — do not formulate rollout questions yourself, and do not assume an example you remember covers the user's path.",{"type":44,"tag":52,"props":201,"children":202},{},[203,205,210],{"type":49,"value":204},"Key decision points (covered in detail by ",{"type":44,"tag":88,"props":206,"children":208},{"className":207},[],[209],{"type":49,"value":195},{"type":49,"value":211},"):",{"type":44,"tag":97,"props":213,"children":214},{},[215,220,225],{"type":44,"tag":101,"props":216,"children":217},{},[218],{"type":49,"value":219},"Variant split (how many variants, what percentage each)",{"type":44,"tag":101,"props":221,"children":222},{},[223],{"type":49,"value":224},"Overall rollout percentage (what % of all users enter the experiment)",{"type":44,"tag":101,"props":226,"children":227},{},[228],{"type":49,"value":229},"Whether to persist the flag across authentication steps",{"type":44,"tag":52,"props":231,"children":232},{},[233],{"type":49,"value":234},"If the user doesn't mention rollout specifics, use defaults: 50\u002F50 control\u002Ftest, 100% rollout.",{"type":44,"tag":76,"props":236,"children":238},{"id":237},"step-3-how-to-measure-impact",[239],{"type":49,"value":240},"Step 3: How to measure impact?",{"type":44,"tag":52,"props":242,"children":243},{},[244,246,259,261,266],{"type":49,"value":245},"This is about analytics and metrics. ",{"type":44,"tag":105,"props":247,"children":248},{},[249,251,257],{"type":49,"value":250},"Load the ",{"type":44,"tag":88,"props":252,"children":254},{"className":253},[],[255],{"type":49,"value":256},"configuring-experiment-analytics",{"type":49,"value":258}," skill",{"type":49,"value":260}," for guidance.\nThat skill's first step checks for an existing ",{"type":44,"tag":105,"props":262,"children":263},{},[264],{"type":49,"value":265},"shared metric",{"type":49,"value":267}," to reuse before building a new one —\ndon't duplicate a metric the project already has set up.",{"type":44,"tag":52,"props":269,"children":270},{},[271,276,278,283,285,291],{"type":44,"tag":105,"props":272,"children":273},{},[274],{"type":49,"value":275},"Do NOT configure metrics on creation.",{"type":49,"value":277}," Metrics are not passed to ",{"type":44,"tag":88,"props":279,"children":281},{"className":280},[],[282],{"type":49,"value":93},{"type":49,"value":284}," — they are added\nafterwards via ",{"type":44,"tag":88,"props":286,"children":288},{"className":287},[],[289],{"type":49,"value":290},"experiment-update",{"type":49,"value":292},". This keeps the creation call lightweight.",{"type":44,"tag":52,"props":294,"children":295},{},[296],{"type":49,"value":297},"When the user specifies metrics upfront, acknowledge them and add them immediately after creation.\nWhen they don't, create the draft and then guide them through metric setup as a follow-up.",{"type":44,"tag":58,"props":299,"children":301},{"id":300},"how-to-create",[302],{"type":49,"value":303},"How to create",{"type":44,"tag":52,"props":305,"children":306},{},[307,309,314],{"type":49,"value":308},"Call ",{"type":44,"tag":88,"props":310,"children":312},{"className":311},[],[313],{"type":49,"value":93},{"type":49,"value":315}," with:",{"type":44,"tag":317,"props":318,"children":323},"pre",{"className":319,"code":320,"language":321,"meta":322,"style":322},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","{\n  \"name\": \"Descriptive experiment name\",\n  \"feature_flag_key\": \"kebab-case-key\",\n  \"description\": \"Hypothesis: [what you expect to happen]\",\n  \"feature_flag\": {\n    \"filters\": {\n      \"multivariate\": {\n        \"variants\": [\n          { \"key\": \"control\", \"name\": \"Control\", \"rollout_percentage\": 50 },\n          { \"key\": \"test\", \"name\": \"Test\", \"rollout_percentage\": 50 }\n        ]\n      },\n      \"groups\": [{ \"properties\": [], \"rollout_percentage\": 100 }]\n    },\n    \"ensure_experience_continuity\": false\n  }\n}\n","json","",[324],{"type":44,"tag":88,"props":325,"children":326},{"__ignoreMap":322},[327,339,383,421,458,484,511,538,566,671,770,778,787,861,870,896,905],{"type":44,"tag":328,"props":329,"children":332},"span",{"class":330,"line":331},"line",1,[333],{"type":44,"tag":328,"props":334,"children":336},{"style":335},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[337],{"type":49,"value":338},"{\n",{"type":44,"tag":328,"props":340,"children":342},{"class":330,"line":341},2,[343,348,354,359,363,368,374,378],{"type":44,"tag":328,"props":344,"children":345},{"style":335},[346],{"type":49,"value":347},"  \"",{"type":44,"tag":328,"props":349,"children":351},{"style":350},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[352],{"type":49,"value":353},"name",{"type":44,"tag":328,"props":355,"children":356},{"style":335},[357],{"type":49,"value":358},"\"",{"type":44,"tag":328,"props":360,"children":361},{"style":335},[362],{"type":49,"value":95},{"type":44,"tag":328,"props":364,"children":365},{"style":335},[366],{"type":49,"value":367}," \"",{"type":44,"tag":328,"props":369,"children":371},{"style":370},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[372],{"type":49,"value":373},"Descriptive experiment name",{"type":44,"tag":328,"props":375,"children":376},{"style":335},[377],{"type":49,"value":358},{"type":44,"tag":328,"props":379,"children":380},{"style":335},[381],{"type":49,"value":382},",\n",{"type":44,"tag":328,"props":384,"children":386},{"class":330,"line":385},3,[387,391,396,400,404,408,413,417],{"type":44,"tag":328,"props":388,"children":389},{"style":335},[390],{"type":49,"value":347},{"type":44,"tag":328,"props":392,"children":393},{"style":350},[394],{"type":49,"value":395},"feature_flag_key",{"type":44,"tag":328,"props":397,"children":398},{"style":335},[399],{"type":49,"value":358},{"type":44,"tag":328,"props":401,"children":402},{"style":335},[403],{"type":49,"value":95},{"type":44,"tag":328,"props":405,"children":406},{"style":335},[407],{"type":49,"value":367},{"type":44,"tag":328,"props":409,"children":410},{"style":370},[411],{"type":49,"value":412},"kebab-case-key",{"type":44,"tag":328,"props":414,"children":415},{"style":335},[416],{"type":49,"value":358},{"type":44,"tag":328,"props":418,"children":419},{"style":335},[420],{"type":49,"value":382},{"type":44,"tag":328,"props":422,"children":424},{"class":330,"line":423},4,[425,429,433,437,441,445,450,454],{"type":44,"tag":328,"props":426,"children":427},{"style":335},[428],{"type":49,"value":347},{"type":44,"tag":328,"props":430,"children":431},{"style":350},[432],{"type":49,"value":127},{"type":44,"tag":328,"props":434,"children":435},{"style":335},[436],{"type":49,"value":358},{"type":44,"tag":328,"props":438,"children":439},{"style":335},[440],{"type":49,"value":95},{"type":44,"tag":328,"props":442,"children":443},{"style":335},[444],{"type":49,"value":367},{"type":44,"tag":328,"props":446,"children":447},{"style":370},[448],{"type":49,"value":449},"Hypothesis: [what you expect to happen]",{"type":44,"tag":328,"props":451,"children":452},{"style":335},[453],{"type":49,"value":358},{"type":44,"tag":328,"props":455,"children":456},{"style":335},[457],{"type":49,"value":382},{"type":44,"tag":328,"props":459,"children":461},{"class":330,"line":460},5,[462,466,471,475,479],{"type":44,"tag":328,"props":463,"children":464},{"style":335},[465],{"type":49,"value":347},{"type":44,"tag":328,"props":467,"children":468},{"style":350},[469],{"type":49,"value":470},"feature_flag",{"type":44,"tag":328,"props":472,"children":473},{"style":335},[474],{"type":49,"value":358},{"type":44,"tag":328,"props":476,"children":477},{"style":335},[478],{"type":49,"value":95},{"type":44,"tag":328,"props":480,"children":481},{"style":335},[482],{"type":49,"value":483}," {\n",{"type":44,"tag":328,"props":485,"children":487},{"class":330,"line":486},6,[488,493,499,503,507],{"type":44,"tag":328,"props":489,"children":490},{"style":335},[491],{"type":49,"value":492},"    \"",{"type":44,"tag":328,"props":494,"children":496},{"style":495},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[497],{"type":49,"value":498},"filters",{"type":44,"tag":328,"props":500,"children":501},{"style":335},[502],{"type":49,"value":358},{"type":44,"tag":328,"props":504,"children":505},{"style":335},[506],{"type":49,"value":95},{"type":44,"tag":328,"props":508,"children":509},{"style":335},[510],{"type":49,"value":483},{"type":44,"tag":328,"props":512,"children":514},{"class":330,"line":513},7,[515,520,526,530,534],{"type":44,"tag":328,"props":516,"children":517},{"style":335},[518],{"type":49,"value":519},"      \"",{"type":44,"tag":328,"props":521,"children":523},{"style":522},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[524],{"type":49,"value":525},"multivariate",{"type":44,"tag":328,"props":527,"children":528},{"style":335},[529],{"type":49,"value":358},{"type":44,"tag":328,"props":531,"children":532},{"style":335},[533],{"type":49,"value":95},{"type":44,"tag":328,"props":535,"children":536},{"style":335},[537],{"type":49,"value":483},{"type":44,"tag":328,"props":539,"children":541},{"class":330,"line":540},8,[542,547,553,557,561],{"type":44,"tag":328,"props":543,"children":544},{"style":335},[545],{"type":49,"value":546},"        \"",{"type":44,"tag":328,"props":548,"children":550},{"style":549},"--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178",[551],{"type":49,"value":552},"variants",{"type":44,"tag":328,"props":554,"children":555},{"style":335},[556],{"type":49,"value":358},{"type":44,"tag":328,"props":558,"children":559},{"style":335},[560],{"type":49,"value":95},{"type":44,"tag":328,"props":562,"children":563},{"style":335},[564],{"type":49,"value":565}," [\n",{"type":44,"tag":328,"props":567,"children":569},{"class":330,"line":568},9,[570,575,579,585,589,593,597,602,606,611,615,619,623,627,631,636,640,644,648,653,657,661,666],{"type":44,"tag":328,"props":571,"children":572},{"style":335},[573],{"type":49,"value":574},"          {",{"type":44,"tag":328,"props":576,"children":577},{"style":335},[578],{"type":49,"value":367},{"type":44,"tag":328,"props":580,"children":582},{"style":581},"--shiki-light:#916B53;--shiki-default:#916B53;--shiki-dark:#916B53",[583],{"type":49,"value":584},"key",{"type":44,"tag":328,"props":586,"children":587},{"style":335},[588],{"type":49,"value":358},{"type":44,"tag":328,"props":590,"children":591},{"style":335},[592],{"type":49,"value":95},{"type":44,"tag":328,"props":594,"children":595},{"style":335},[596],{"type":49,"value":367},{"type":44,"tag":328,"props":598,"children":599},{"style":370},[600],{"type":49,"value":601},"control",{"type":44,"tag":328,"props":603,"children":604},{"style":335},[605],{"type":49,"value":358},{"type":44,"tag":328,"props":607,"children":608},{"style":335},[609],{"type":49,"value":610},",",{"type":44,"tag":328,"props":612,"children":613},{"style":335},[614],{"type":49,"value":367},{"type":44,"tag":328,"props":616,"children":617},{"style":581},[618],{"type":49,"value":353},{"type":44,"tag":328,"props":620,"children":621},{"style":335},[622],{"type":49,"value":358},{"type":44,"tag":328,"props":624,"children":625},{"style":335},[626],{"type":49,"value":95},{"type":44,"tag":328,"props":628,"children":629},{"style":335},[630],{"type":49,"value":367},{"type":44,"tag":328,"props":632,"children":633},{"style":370},[634],{"type":49,"value":635},"Control",{"type":44,"tag":328,"props":637,"children":638},{"style":335},[639],{"type":49,"value":358},{"type":44,"tag":328,"props":641,"children":642},{"style":335},[643],{"type":49,"value":610},{"type":44,"tag":328,"props":645,"children":646},{"style":335},[647],{"type":49,"value":367},{"type":44,"tag":328,"props":649,"children":650},{"style":581},[651],{"type":49,"value":652},"rollout_percentage",{"type":44,"tag":328,"props":654,"children":655},{"style":335},[656],{"type":49,"value":358},{"type":44,"tag":328,"props":658,"children":659},{"style":335},[660],{"type":49,"value":95},{"type":44,"tag":328,"props":662,"children":663},{"style":522},[664],{"type":49,"value":665}," 50",{"type":44,"tag":328,"props":667,"children":668},{"style":335},[669],{"type":49,"value":670}," },\n",{"type":44,"tag":328,"props":672,"children":674},{"class":330,"line":673},10,[675,679,683,687,691,695,699,704,708,712,716,720,724,728,732,737,741,745,749,753,757,761,765],{"type":44,"tag":328,"props":676,"children":677},{"style":335},[678],{"type":49,"value":574},{"type":44,"tag":328,"props":680,"children":681},{"style":335},[682],{"type":49,"value":367},{"type":44,"tag":328,"props":684,"children":685},{"style":581},[686],{"type":49,"value":584},{"type":44,"tag":328,"props":688,"children":689},{"style":335},[690],{"type":49,"value":358},{"type":44,"tag":328,"props":692,"children":693},{"style":335},[694],{"type":49,"value":95},{"type":44,"tag":328,"props":696,"children":697},{"style":335},[698],{"type":49,"value":367},{"type":44,"tag":328,"props":700,"children":701},{"style":370},[702],{"type":49,"value":703},"test",{"type":44,"tag":328,"props":705,"children":706},{"style":335},[707],{"type":49,"value":358},{"type":44,"tag":328,"props":709,"children":710},{"style":335},[711],{"type":49,"value":610},{"type":44,"tag":328,"props":713,"children":714},{"style":335},[715],{"type":49,"value":367},{"type":44,"tag":328,"props":717,"children":718},{"style":581},[719],{"type":49,"value":353},{"type":44,"tag":328,"props":721,"children":722},{"style":335},[723],{"type":49,"value":358},{"type":44,"tag":328,"props":725,"children":726},{"style":335},[727],{"type":49,"value":95},{"type":44,"tag":328,"props":729,"children":730},{"style":335},[731],{"type":49,"value":367},{"type":44,"tag":328,"props":733,"children":734},{"style":370},[735],{"type":49,"value":736},"Test",{"type":44,"tag":328,"props":738,"children":739},{"style":335},[740],{"type":49,"value":358},{"type":44,"tag":328,"props":742,"children":743},{"style":335},[744],{"type":49,"value":610},{"type":44,"tag":328,"props":746,"children":747},{"style":335},[748],{"type":49,"value":367},{"type":44,"tag":328,"props":750,"children":751},{"style":581},[752],{"type":49,"value":652},{"type":44,"tag":328,"props":754,"children":755},{"style":335},[756],{"type":49,"value":358},{"type":44,"tag":328,"props":758,"children":759},{"style":335},[760],{"type":49,"value":95},{"type":44,"tag":328,"props":762,"children":763},{"style":522},[764],{"type":49,"value":665},{"type":44,"tag":328,"props":766,"children":767},{"style":335},[768],{"type":49,"value":769}," }\n",{"type":44,"tag":328,"props":771,"children":772},{"class":330,"line":27},[773],{"type":44,"tag":328,"props":774,"children":775},{"style":335},[776],{"type":49,"value":777},"        ]\n",{"type":44,"tag":328,"props":779,"children":781},{"class":330,"line":780},12,[782],{"type":44,"tag":328,"props":783,"children":784},{"style":335},[785],{"type":49,"value":786},"      },\n",{"type":44,"tag":328,"props":788,"children":790},{"class":330,"line":789},13,[791,795,800,804,808,813,817,822,826,830,835,839,843,847,851,856],{"type":44,"tag":328,"props":792,"children":793},{"style":335},[794],{"type":49,"value":519},{"type":44,"tag":328,"props":796,"children":797},{"style":522},[798],{"type":49,"value":799},"groups",{"type":44,"tag":328,"props":801,"children":802},{"style":335},[803],{"type":49,"value":358},{"type":44,"tag":328,"props":805,"children":806},{"style":335},[807],{"type":49,"value":95},{"type":44,"tag":328,"props":809,"children":810},{"style":335},[811],{"type":49,"value":812}," [{",{"type":44,"tag":328,"props":814,"children":815},{"style":335},[816],{"type":49,"value":367},{"type":44,"tag":328,"props":818,"children":819},{"style":549},[820],{"type":49,"value":821},"properties",{"type":44,"tag":328,"props":823,"children":824},{"style":335},[825],{"type":49,"value":358},{"type":44,"tag":328,"props":827,"children":828},{"style":335},[829],{"type":49,"value":95},{"type":44,"tag":328,"props":831,"children":832},{"style":335},[833],{"type":49,"value":834}," [],",{"type":44,"tag":328,"props":836,"children":837},{"style":335},[838],{"type":49,"value":367},{"type":44,"tag":328,"props":840,"children":841},{"style":549},[842],{"type":49,"value":652},{"type":44,"tag":328,"props":844,"children":845},{"style":335},[846],{"type":49,"value":358},{"type":44,"tag":328,"props":848,"children":849},{"style":335},[850],{"type":49,"value":95},{"type":44,"tag":328,"props":852,"children":853},{"style":522},[854],{"type":49,"value":855}," 100",{"type":44,"tag":328,"props":857,"children":858},{"style":335},[859],{"type":49,"value":860}," }]\n",{"type":44,"tag":328,"props":862,"children":864},{"class":330,"line":863},14,[865],{"type":44,"tag":328,"props":866,"children":867},{"style":335},[868],{"type":49,"value":869},"    },\n",{"type":44,"tag":328,"props":871,"children":873},{"class":330,"line":872},15,[874,878,883,887,891],{"type":44,"tag":328,"props":875,"children":876},{"style":335},[877],{"type":49,"value":492},{"type":44,"tag":328,"props":879,"children":880},{"style":495},[881],{"type":49,"value":882},"ensure_experience_continuity",{"type":44,"tag":328,"props":884,"children":885},{"style":335},[886],{"type":49,"value":358},{"type":44,"tag":328,"props":888,"children":889},{"style":335},[890],{"type":49,"value":95},{"type":44,"tag":328,"props":892,"children":893},{"style":335},[894],{"type":49,"value":895}," false\n",{"type":44,"tag":328,"props":897,"children":899},{"class":330,"line":898},16,[900],{"type":44,"tag":328,"props":901,"children":902},{"style":335},[903],{"type":49,"value":904},"  }\n",{"type":44,"tag":328,"props":906,"children":908},{"class":330,"line":907},17,[909],{"type":44,"tag":328,"props":910,"children":911},{"style":335},[912],{"type":49,"value":913},"}\n",{"type":44,"tag":52,"props":915,"children":916},{},[917,919,924,926,932],{"type":49,"value":918},"Flag config goes in the ",{"type":44,"tag":88,"props":920,"children":922},{"className":921},[],[923],{"type":49,"value":470},{"type":49,"value":925}," object, in the flag's own filters shape (not the deprecated ",{"type":44,"tag":88,"props":927,"children":929},{"className":928},[],[930],{"type":49,"value":931},"parameters",{"type":49,"value":933}," keys).\nTwo different percentages live in there, do NOT mix them up:",{"type":44,"tag":97,"props":935,"children":936},{},[937,955],{"type":44,"tag":101,"props":938,"children":939},{},[940,946,948,953],{"type":44,"tag":88,"props":941,"children":943},{"className":942},[],[944],{"type":49,"value":945},"filters.multivariate.variants[].rollout_percentage",{"type":49,"value":947}," is how users ",{"type":44,"tag":105,"props":949,"children":950},{},[951],{"type":49,"value":952},"inside",{"type":49,"value":954}," the experiment are split across variants (must sum to 100, recommended to have an even split).",{"type":44,"tag":101,"props":956,"children":957},{},[958,964,966,971],{"type":44,"tag":88,"props":959,"children":961},{"className":960},[],[962],{"type":49,"value":963},"filters.groups[0].rollout_percentage",{"type":49,"value":965}," is the overall gate: what fraction of ",{"type":44,"tag":105,"props":967,"children":968},{},[969],{"type":49,"value":970},"all",{"type":49,"value":972}," users enter the experiment at all (0-100, defaults to 100).",{"type":44,"tag":52,"props":974,"children":975},{},[976],{"type":49,"value":977},"Key details:",{"type":44,"tag":97,"props":979,"children":980},{},[981,1009,1019,1044],{"type":44,"tag":101,"props":982,"children":983},{},[984,986,992,994,1000,1002,1007],{"type":49,"value":985},"Minimum 2, maximum 20 variants. No specific variant key is required — the analysis baseline defaults to the variant keyed ",{"type":44,"tag":88,"props":987,"children":989},{"className":988},[],[990],{"type":49,"value":991},"\"control\"",{"type":49,"value":993}," when present, else the first variant (override with ",{"type":44,"tag":88,"props":995,"children":997},{"className":996},[],[998],{"type":49,"value":999},"stats_config.baseline_variant_key",{"type":49,"value":1001},"). Convention: key the baseline ",{"type":44,"tag":88,"props":1003,"children":1005},{"className":1004},[],[1006],{"type":49,"value":991},{"type":49,"value":1008}," unless the user asks for specific keys.",{"type":44,"tag":101,"props":1010,"children":1011},{},[1012,1017],{"type":44,"tag":88,"props":1013,"children":1015},{"className":1014},[],[1016],{"type":49,"value":963},{"type":49,"value":1018}," defaults to 100 if omitted.",{"type":44,"tag":101,"props":1020,"children":1021},{},[1022,1027,1029,1035,1037,1042],{"type":44,"tag":88,"props":1023,"children":1025},{"className":1024},[],[1026],{"type":49,"value":882},{"type":49,"value":1028}," persists a user's variant across authentication steps; leave it ",{"type":44,"tag":88,"props":1030,"children":1032},{"className":1031},[],[1033],{"type":49,"value":1034},"false",{"type":49,"value":1036}," unless the flag is shown to both logged-out and logged-in users (see ",{"type":44,"tag":88,"props":1038,"children":1040},{"className":1039},[],[1041],{"type":49,"value":195},{"type":49,"value":1043},").",{"type":44,"tag":101,"props":1045,"children":1046},{},[1047,1049,1055],{"type":49,"value":1048},"Stats default to Bayesian. Only set ",{"type":44,"tag":88,"props":1050,"children":1052},{"className":1051},[],[1053],{"type":49,"value":1054},"stats_config",{"type":49,"value":1056}," if the user requests Frequentist.",{"type":44,"tag":58,"props":1058,"children":1060},{"id":1059},"after-creation",[1061],{"type":49,"value":1062},"After creation",{"type":44,"tag":1064,"props":1065,"children":1066},"ol",{},[1067,1092,1102,1119],{"type":44,"tag":101,"props":1068,"children":1069},{},[1070,1075,1077,1082,1084,1090],{"type":44,"tag":105,"props":1071,"children":1072},{},[1073],{"type":49,"value":1074},"Always show the experiment URL.",{"type":49,"value":1076}," The ",{"type":44,"tag":88,"props":1078,"children":1080},{"className":1079},[],[1081],{"type":49,"value":93},{"type":49,"value":1083}," response includes ",{"type":44,"tag":88,"props":1085,"children":1087},{"className":1086},[],[1088],{"type":49,"value":1089},"_posthogUrl",{"type":49,"value":1091}," — always display this link so the user can view and configure the experiment in the UI.",{"type":44,"tag":101,"props":1093,"children":1094},{},[1095,1100],{"type":44,"tag":105,"props":1096,"children":1097},{},[1098],{"type":49,"value":1099},"Remind the user to implement the feature flag in code.",{"type":49,"value":1101}," Link to the experiment page and say \"implement the flag as shown here\" — the experiment detail page shows implementation snippets for the user's SDK.",{"type":44,"tag":101,"props":1103,"children":1104},{},[1105,1110,1112,1117],{"type":44,"tag":105,"props":1106,"children":1107},{},[1108],{"type":49,"value":1109},"Guide through metrics",{"type":49,"value":1111}," if not yet configured — load the ",{"type":44,"tag":88,"props":1113,"children":1115},{"className":1114},[],[1116],{"type":49,"value":256},{"type":49,"value":1118}," skill.",{"type":44,"tag":101,"props":1120,"children":1121},{},[1122,1127,1129,1135],{"type":44,"tag":105,"props":1123,"children":1124},{},[1125],{"type":49,"value":1126},"Launch",{"type":49,"value":1128}," when ready — use the ",{"type":44,"tag":88,"props":1130,"children":1132},{"className":1131},[],[1133],{"type":49,"value":1134},"experiment-launch",{"type":49,"value":1136}," tool.",{"type":44,"tag":1138,"props":1139,"children":1140},"style",{},[1141],{"type":49,"value":1142},"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":1144,"total":1315},[1145,1162,1174,1187,1200,1215,1231,1248,1262,1277,1287,1305],{"slug":1146,"name":1146,"fn":1147,"description":1148,"org":1149,"tags":1150,"stars":1159,"repoUrl":1160,"updatedAt":1161},"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},[1151,1152,1155,1158],{"name":18,"slug":19,"type":13},{"name":1153,"slug":1154,"type":13},"Cost Optimization","cost-optimization",{"name":1156,"slug":1157,"type":13},"Observability","observability",{"name":9,"slug":8,"type":13},35568,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog","2026-07-28T05:34:11.117757",{"slug":1163,"name":1163,"fn":1164,"description":1165,"org":1166,"tags":1167,"stars":1159,"repoUrl":1160,"updatedAt":1173},"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},[1168,1169,1172],{"name":18,"slug":19,"type":13},{"name":1170,"slug":1171,"type":13},"Audit","audit",{"name":9,"slug":8,"type":13},"2026-06-08T08:08:33.693989",{"slug":1175,"name":1175,"fn":1176,"description":1177,"org":1178,"tags":1179,"stars":1159,"repoUrl":1160,"updatedAt":1186},"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},[1180,1181,1184,1185],{"name":1170,"slug":1171,"type":13},{"name":1182,"slug":1183,"type":13},"Data Warehouse","data-warehouse",{"name":1156,"slug":1157,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:22:57.67984",{"slug":1188,"name":1188,"fn":1189,"description":1190,"org":1191,"tags":1192,"stars":1159,"repoUrl":1160,"updatedAt":1199},"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},[1193,1194,1195,1198],{"name":1170,"slug":1171,"type":13},{"name":1182,"slug":1183,"type":13},{"name":1196,"slug":1197,"type":13},"Performance","performance",{"name":9,"slug":8,"type":13},"2026-06-18T08:25:10.936787",{"slug":1201,"name":1201,"fn":1202,"description":1203,"org":1204,"tags":1205,"stars":1159,"repoUrl":1160,"updatedAt":1214},"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},[1206,1209,1212,1213],{"name":1207,"slug":1208,"type":13},"Alerting","alerting",{"name":1210,"slug":1211,"type":13},"Debugging","debugging",{"name":1156,"slug":1157,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:24:40.318583",{"slug":1216,"name":1216,"fn":1217,"description":1218,"org":1219,"tags":1220,"stars":1159,"repoUrl":1160,"updatedAt":1230},"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},[1221,1222,1225,1226,1229],{"name":18,"slug":19,"type":13},{"name":1223,"slug":1224,"type":13},"Monitoring","monitoring",{"name":1156,"slug":1157,"type":13},{"name":1227,"slug":1228,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-18T05:10:54.430898",{"slug":1232,"name":1232,"fn":1233,"description":1234,"org":1235,"tags":1236,"stars":1159,"repoUrl":1160,"updatedAt":1247},"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},[1237,1240,1243,1244],{"name":1238,"slug":1239,"type":13},"Automation","automation",{"name":1241,"slug":1242,"type":13},"MCP","mcp",{"name":9,"slug":8,"type":13},{"name":1245,"slug":1246,"type":13},"Workflow Automation","workflow-automation","2026-07-28T05:34:12.167015",{"slug":1249,"name":1249,"fn":1250,"description":1251,"org":1252,"tags":1253,"stars":1159,"repoUrl":1160,"updatedAt":1261},"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},[1254,1255,1256,1259,1260],{"name":18,"slug":19,"type":13},{"name":1210,"slug":1211,"type":13},{"name":1257,"slug":1258,"type":13},"Frontend","frontend",{"name":1156,"slug":1157,"type":13},{"name":9,"slug":8,"type":13},"2026-05-07T05:56:19.828048",{"slug":1263,"name":1263,"fn":1264,"description":1265,"org":1266,"tags":1267,"stars":1159,"repoUrl":1160,"updatedAt":1276},"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},[1268,1271,1272,1273],{"name":1269,"slug":1270,"type":13},"API Development","api-development",{"name":1257,"slug":1258,"type":13},{"name":9,"slug":8,"type":13},{"name":1274,"slug":1275,"type":13},"SDK","sdk","2026-06-08T08:08:34.929454",{"slug":1278,"name":1278,"fn":1279,"description":1280,"org":1281,"tags":1282,"stars":1159,"repoUrl":1160,"updatedAt":1286},"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},[1283,1284,1285],{"name":1269,"slug":1270,"type":13},{"name":1227,"slug":1228,"type":13},{"name":9,"slug":8,"type":13},"2026-07-15T05:29:58.442727",{"slug":1288,"name":1288,"fn":1289,"description":1290,"org":1291,"tags":1292,"stars":1159,"repoUrl":1160,"updatedAt":1304},"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},[1293,1294,1297,1298,1301],{"name":1238,"slug":1239,"type":13},{"name":1295,"slug":1296,"type":13},"Email","email",{"name":9,"slug":8,"type":13},{"name":1299,"slug":1300,"type":13},"Reporting","reporting",{"name":1302,"slug":1303,"type":13},"Slack","slack","2026-06-09T07:32:27.935712",{"slug":1306,"name":1306,"fn":1307,"description":1308,"org":1309,"tags":1310,"stars":1159,"repoUrl":1160,"updatedAt":1314},"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},[1311,1312,1313],{"name":18,"slug":19,"type":13},{"name":1269,"slug":1270,"type":13},{"name":9,"slug":8,"type":13},"2026-06-08T08:08:29.624498",231,{"items":1317,"total":1421},[1318,1333,1347,1362,1375,1387,1405],{"slug":1319,"name":1319,"fn":1320,"description":1321,"org":1322,"tags":1323,"stars":23,"repoUrl":24,"updatedAt":1332},"analyzing-experiment-session-replays","analyze session replays for PostHog experiments","Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with different experiment variants, identify usability issues, compare behavior patterns between control and test groups, or get qualitative insights to complement quantitative experiment results.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1324,1325,1328,1329],{"name":18,"slug":19,"type":13},{"name":1326,"slug":1327,"type":13},"Design","design",{"name":9,"slug":8,"type":13},{"name":1330,"slug":1331,"type":13},"User Research","user-research","2026-04-06T18:44:38.291781",{"slug":1334,"name":1334,"fn":1335,"description":1336,"org":1337,"tags":1338,"stars":23,"repoUrl":24,"updatedAt":1346},"assessing-heatmaps","analyze page heatmaps and suggest improvements","Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click \u002F rageclick \u002F scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements.\nTRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heatmap\u002Fclick data, or to 'analyze\u002Fassess\u002Freview the heatmap' for a URL.\nDO NOT TRIGGER when: the user only wants to create a saved heatmap screenshot with no analysis (use heatmaps-saved-create directly), or is asking about session replay in general (use investigating-replay).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1339,1340,1341,1342,1343],{"name":18,"slug":19,"type":13},{"name":1257,"slug":1258,"type":13},{"name":9,"slug":8,"type":13},{"name":15,"slug":16,"type":13},{"name":1344,"slug":1345,"type":13},"UX Design","ux-design","2026-06-05T07:40:43.37798",{"slug":1348,"name":1348,"fn":1349,"description":1350,"org":1351,"tags":1352,"stars":23,"repoUrl":24,"updatedAt":1361},"auditing-experiments-flags","audit PostHog experiments and feature flags","Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1353,1354,1357,1358],{"name":1170,"slug":1171,"type":13},{"name":1355,"slug":1356,"type":13},"Feature Flags","feature-flags",{"name":9,"slug":8,"type":13},{"name":1359,"slug":1360,"type":13},"QA","qa","2026-04-06T18:44:30.657553",{"slug":1363,"name":1363,"fn":1364,"description":1365,"org":1366,"tags":1367,"stars":23,"repoUrl":24,"updatedAt":1374},"authoring-scouts","author and edit PostHog Signals scouts","How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to customize a canonical scout for their own setup (narrow its scope, retune its thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, or write a brand-new scout from scratch for a specific use case (a custom event, a product surface no canonical scout covers), or steer a scout without editing it at all by leaving it a note. Covers the scout SKILL.md anatomy, the report contract, the dedupe + scratchpad-memory conventions, the scout-notes steering channel, the per-team skills-store path vs the canonical in-repo path, and the write-and-inspect test loop (with dry-run as an optional safety net). Trigger on \"write\u002Fedit\u002Fcustomize a signals scout\", \"new scout for X\", \"tune my scout schedule\", \"make a scout that watches \u003Cevent>\", \"leave a note for \u002F give feedback to a scout\", \"tell the scouts about X\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1368,1371,1372,1373],{"name":1369,"slug":1370,"type":13},"Agents","agents",{"name":1238,"slug":1239,"type":13},{"name":1156,"slug":1157,"type":13},{"name":9,"slug":8,"type":13},"2026-07-28T05:33:45.509154",{"slug":1376,"name":1376,"fn":1377,"description":1378,"org":1379,"tags":1380,"stars":23,"repoUrl":24,"updatedAt":1386},"building-a-dashboard","build and update PostHog dashboards","Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP. Use when a user asks to create a dashboard, put several metrics\u002Fcharts together on one page, assemble a dashboard for a topic (product analytics, retention, revenue, activation, etc.), or add\u002Fremove\u002Freplace insights on a dashboard they already have. Covers deciding create vs update, reusing existing insights vs creating new ones, and using PostHog's vetted dashboard templates as reference for what a strong dashboard on a topic looks like.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1381,1382,1385],{"name":18,"slug":19,"type":13},{"name":1383,"slug":1384,"type":13},"Dashboards","dashboards",{"name":1241,"slug":1242,"type":13},"2026-07-21T06:07:38.060598",{"slug":1388,"name":1388,"fn":1389,"description":1390,"org":1391,"tags":1392,"stars":23,"repoUrl":24,"updatedAt":1404},"checking-deploy-timing","correlate PostHog deployments with GitHub commits","Determine when a PostHog code change reached a given environment by reading the hidden GIT deploy annotations in the project and correlating them with the merge commit on GitHub. Use when PostHog staff ask \"when was X deployed\", \"is my change live in the US\u002FEU yet\", \"has my PR shipped\", \"did the fix roll out to prod-us\", or otherwise want to know whether\u002Fwhen a commit, PR, or feature went out to a region. Do not answer deploy-timing questions from event\u002Fdata volume alone — that only shows when data changed, not when code shipped.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1393,1396,1399,1402,1403],{"name":1394,"slug":1395,"type":13},"Deployment","deployment",{"name":1397,"slug":1398,"type":13},"Git","git",{"name":1400,"slug":1401,"type":13},"GitHub","github",{"name":1156,"slug":1157,"type":13},{"name":9,"slug":8,"type":13},"2026-06-28T07:46:59.53536",{"slug":1406,"name":1406,"fn":1407,"description":1408,"org":1409,"tags":1410,"stars":23,"repoUrl":24,"updatedAt":1420},"choosing-trend-or-slope-view","visualize trends and growth over time","Clarify how to visualize change over a time range before building a trend. Use whenever the user asks how much something changed, grew, dropped, improved, or regressed between two points or periods — \"how much did X change from A to B\", \"before vs after\", \"start vs end\", \"week over week\", \"compare this month to last\", \"change over time\" — or mentions a \"slope chart\" \u002F \"slopegraph\". Two readings of \"change\" need different charts: the whole trend (a line, every interval) versus just the two endpoints (a slope, start vs end). Ask which they want, then render it. Not for choosing a saved insight ChartDisplayType in the insight editor.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1411,1412,1415,1418,1419],{"name":18,"slug":19,"type":13},{"name":1413,"slug":1414,"type":13},"Charts","charts",{"name":1416,"slug":1417,"type":13},"Data Visualization","data-visualization",{"name":9,"slug":8,"type":13},{"name":1299,"slug":1300,"type":13},"2026-06-18T08:18:57.960157",56]