[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-posthog-auditing-experiments-flags":3,"mdc-bn2lnb-key":38,"related-org-posthog-auditing-experiments-flags":563,"related-repo-posthog-auditing-experiments-flags":736},{"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},"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},"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},"Feature Flags","feature-flags",{"name":18,"slug":19,"type":13},"QA","qa",{"name":21,"slug":22,"type":13},"Audit","audit",59,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fai-plugin","2026-04-06T18:44:30.657553",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\u002Fauditing-experiments-flags","---\nname: auditing-experiments-flags\ndescription: '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.'\n---\n\n# Auditing experiments and feature flags\n\nThis skill teaches you how to run configuration audits on experiments and feature flags.\nAll checks use the experiment and feature flag read tools (`experiment-get`, `experiment-list`, `feature-flag-get-definition`, `feature-flag-get-all`) — no SQL queries are needed for Phase 1 checks.\n\n## Usage modes\n\n### Quick check (single entity)\n\nWhen the user asks about a specific experiment or flag:\n\n1. Fetch the entity via `experiment-get` (experiment ID) or `feature-flag-get-definition` (numeric flag ID).\n2. Apply the relevant checks from [experiment checks](.\u002Freferences\u002Fexperiment-checks.md) or [flag checks](.\u002Freferences\u002Fflag-checks.md).\n3. Report findings inline as markdown, grouped by severity (CRITICAL first, then WARNING, then INFO).\n4. Include entity links as `[Experiment: name](\u002Fexperiments\u002Fid)` or `[Flag: key](\u002Ffeature_flags\u002Fid)`.\n\n### Scoped audit (one domain)\n\nWhen the user asks to audit all experiments or all flags:\n\n1. Bulk-fetch via `experiment-list` or `feature-flag-get-all`.\n2. Run all checks for that domain against each entity.\n3. Group findings by severity, then by entity.\n4. Report as inline markdown.\n\n### Full audit (comprehensive)\n\nWhen the user asks for a comprehensive audit of both experiments and flags:\n\n1. Fetch all experiments via `experiment-list` and all flags via `feature-flag-get-all`.\n2. Run all experiment checks and all flag checks.\n3. Apply [recurring patterns](.\u002Freferences\u002Fsynthesis-patterns.md) to identify patterns across multiple findings.\n4. If there are more than 5 entities with findings, output as a notebook artifact via `notebooks-create` for easier navigation. Otherwise report inline.\n\n## Output format\n\nFor each finding, include:\n\n- **Severity badge**: `🔴 CRITICAL`, `🟡 WARNING`, or `🔵 INFO`\n- **Check name**: Which check produced this finding\n- **Entity link**: Markdown link to the entity\n- **What's wrong**: One-sentence description\n- **Action**: What to do about it (see [remediation actions](.\u002Freferences\u002Fremediation-actions.md))\n\nExample:\n\n> 🟡 **WARNING** — Flag integration · [Experiment: checkout-redesign](\u002Fexperiments\u002F42)\n> The linked feature flag is inactive (paused). Traffic is not being split.\n> **Action**: Re-enable the flag or end the experiment.\n\n## Handling unavailable data\n\nSome checks require activity logs (`feature-flags-activity-retrieve` for flags), which may not be available in every session.\nIf activity log data is unavailable:\n\n- Skip `checkActivityHistory` (experiment check) entirely.\n- Skip the \"toggle instability\" and \"never activated\" sub-checks in flag lifecycle checks.\n- In your report, note which checks were skipped and why:\n  > _Skipped: Activity history checks (activity logs not available via current tools)_\n\n## Partial failures\n\nIf a fetch call fails for some entities:\n\n- Continue with the entities you could fetch.\n- Report which entities could not be assessed and why.\n- Do not silently omit entities from the audit.\n\n## Reference files\n\n- [Experiment checks](.\u002Freferences\u002Fexperiment-checks.md) — experiment configuration checks\n- [Flag checks](.\u002Freferences\u002Fflag-checks.md) — feature flag checks\n- [Finding types](.\u002Freferences\u002Ffinding-taxonomy.md) — severity and category definitions\n- [Recurring patterns](.\u002Freferences\u002Fsynthesis-patterns.md) — patterns across multiple findings\n- [Remediation actions](.\u002Freferences\u002Fremediation-actions.md) — what to do about each finding\n",{"data":39,"body":40},{"name":4,"description":6},{"type":41,"children":42},"root",[43,52,89,96,103,108,178,184,189,224,230,235,287,293,298,382,387,417,423,436,474,480,485,503,509],{"type":44,"tag":45,"props":46,"children":48},"element","h1",{"id":47},"auditing-experiments-and-feature-flags",[49],{"type":50,"value":51},"text","Auditing experiments and feature flags",{"type":44,"tag":53,"props":54,"children":55},"p",{},[56,58,65,67,73,74,80,81,87],{"type":50,"value":57},"This skill teaches you how to run configuration audits on experiments and feature flags.\nAll checks use the experiment and feature flag read tools (",{"type":44,"tag":59,"props":60,"children":62},"code",{"className":61},[],[63],{"type":50,"value":64},"experiment-get",{"type":50,"value":66},", ",{"type":44,"tag":59,"props":68,"children":70},{"className":69},[],[71],{"type":50,"value":72},"experiment-list",{"type":50,"value":66},{"type":44,"tag":59,"props":75,"children":77},{"className":76},[],[78],{"type":50,"value":79},"feature-flag-get-definition",{"type":50,"value":66},{"type":44,"tag":59,"props":82,"children":84},{"className":83},[],[85],{"type":50,"value":86},"feature-flag-get-all",{"type":50,"value":88},") — no SQL queries are needed for Phase 1 checks.",{"type":44,"tag":90,"props":91,"children":93},"h2",{"id":92},"usage-modes",[94],{"type":50,"value":95},"Usage modes",{"type":44,"tag":97,"props":98,"children":100},"h3",{"id":99},"quick-check-single-entity",[101],{"type":50,"value":102},"Quick check (single entity)",{"type":44,"tag":53,"props":104,"children":105},{},[106],{"type":50,"value":107},"When the user asks about a specific experiment or flag:",{"type":44,"tag":109,"props":110,"children":111},"ol",{},[112,132,154,159],{"type":44,"tag":113,"props":114,"children":115},"li",{},[116,118,123,125,130],{"type":50,"value":117},"Fetch the entity via ",{"type":44,"tag":59,"props":119,"children":121},{"className":120},[],[122],{"type":50,"value":64},{"type":50,"value":124}," (experiment ID) or ",{"type":44,"tag":59,"props":126,"children":128},{"className":127},[],[129],{"type":50,"value":79},{"type":50,"value":131}," (numeric flag ID).",{"type":44,"tag":113,"props":133,"children":134},{},[135,137,144,146,152],{"type":50,"value":136},"Apply the relevant checks from ",{"type":44,"tag":138,"props":139,"children":141},"a",{"href":140},".\u002Freferences\u002Fexperiment-checks.md",[142],{"type":50,"value":143},"experiment checks",{"type":50,"value":145}," or ",{"type":44,"tag":138,"props":147,"children":149},{"href":148},".\u002Freferences\u002Fflag-checks.md",[150],{"type":50,"value":151},"flag checks",{"type":50,"value":153},".",{"type":44,"tag":113,"props":155,"children":156},{},[157],{"type":50,"value":158},"Report findings inline as markdown, grouped by severity (CRITICAL first, then WARNING, then INFO).",{"type":44,"tag":113,"props":160,"children":161},{},[162,164,170,171,177],{"type":50,"value":163},"Include entity links as ",{"type":44,"tag":59,"props":165,"children":167},{"className":166},[],[168],{"type":50,"value":169},"[Experiment: name](\u002Fexperiments\u002Fid)",{"type":50,"value":145},{"type":44,"tag":59,"props":172,"children":174},{"className":173},[],[175],{"type":50,"value":176},"[Flag: key](\u002Ffeature_flags\u002Fid)",{"type":50,"value":153},{"type":44,"tag":97,"props":179,"children":181},{"id":180},"scoped-audit-one-domain",[182],{"type":50,"value":183},"Scoped audit (one domain)",{"type":44,"tag":53,"props":185,"children":186},{},[187],{"type":50,"value":188},"When the user asks to audit all experiments or all flags:",{"type":44,"tag":109,"props":190,"children":191},{},[192,209,214,219],{"type":44,"tag":113,"props":193,"children":194},{},[195,197,202,203,208],{"type":50,"value":196},"Bulk-fetch via ",{"type":44,"tag":59,"props":198,"children":200},{"className":199},[],[201],{"type":50,"value":72},{"type":50,"value":145},{"type":44,"tag":59,"props":204,"children":206},{"className":205},[],[207],{"type":50,"value":86},{"type":50,"value":153},{"type":44,"tag":113,"props":210,"children":211},{},[212],{"type":50,"value":213},"Run all checks for that domain against each entity.",{"type":44,"tag":113,"props":215,"children":216},{},[217],{"type":50,"value":218},"Group findings by severity, then by entity.",{"type":44,"tag":113,"props":220,"children":221},{},[222],{"type":50,"value":223},"Report as inline markdown.",{"type":44,"tag":97,"props":225,"children":227},{"id":226},"full-audit-comprehensive",[228],{"type":50,"value":229},"Full audit (comprehensive)",{"type":44,"tag":53,"props":231,"children":232},{},[233],{"type":50,"value":234},"When the user asks for a comprehensive audit of both experiments and flags:",{"type":44,"tag":109,"props":236,"children":237},{},[238,256,261,274],{"type":44,"tag":113,"props":239,"children":240},{},[241,243,248,250,255],{"type":50,"value":242},"Fetch all experiments via ",{"type":44,"tag":59,"props":244,"children":246},{"className":245},[],[247],{"type":50,"value":72},{"type":50,"value":249}," and all flags via ",{"type":44,"tag":59,"props":251,"children":253},{"className":252},[],[254],{"type":50,"value":86},{"type":50,"value":153},{"type":44,"tag":113,"props":257,"children":258},{},[259],{"type":50,"value":260},"Run all experiment checks and all flag checks.",{"type":44,"tag":113,"props":262,"children":263},{},[264,266,272],{"type":50,"value":265},"Apply ",{"type":44,"tag":138,"props":267,"children":269},{"href":268},".\u002Freferences\u002Fsynthesis-patterns.md",[270],{"type":50,"value":271},"recurring patterns",{"type":50,"value":273}," to identify patterns across multiple findings.",{"type":44,"tag":113,"props":275,"children":276},{},[277,279,285],{"type":50,"value":278},"If there are more than 5 entities with findings, output as a notebook artifact via ",{"type":44,"tag":59,"props":280,"children":282},{"className":281},[],[283],{"type":50,"value":284},"notebooks-create",{"type":50,"value":286}," for easier navigation. Otherwise report inline.",{"type":44,"tag":90,"props":288,"children":290},{"id":289},"output-format",[291],{"type":50,"value":292},"Output format",{"type":44,"tag":53,"props":294,"children":295},{},[296],{"type":50,"value":297},"For each finding, include:",{"type":44,"tag":299,"props":300,"children":301},"ul",{},[302,334,344,354,364],{"type":44,"tag":113,"props":303,"children":304},{},[305,311,313,319,320,326,328],{"type":44,"tag":306,"props":307,"children":308},"strong",{},[309],{"type":50,"value":310},"Severity badge",{"type":50,"value":312},": ",{"type":44,"tag":59,"props":314,"children":316},{"className":315},[],[317],{"type":50,"value":318},"🔴 CRITICAL",{"type":50,"value":66},{"type":44,"tag":59,"props":321,"children":323},{"className":322},[],[324],{"type":50,"value":325},"🟡 WARNING",{"type":50,"value":327},", or ",{"type":44,"tag":59,"props":329,"children":331},{"className":330},[],[332],{"type":50,"value":333},"🔵 INFO",{"type":44,"tag":113,"props":335,"children":336},{},[337,342],{"type":44,"tag":306,"props":338,"children":339},{},[340],{"type":50,"value":341},"Check name",{"type":50,"value":343},": Which check produced this finding",{"type":44,"tag":113,"props":345,"children":346},{},[347,352],{"type":44,"tag":306,"props":348,"children":349},{},[350],{"type":50,"value":351},"Entity link",{"type":50,"value":353},": Markdown link to the entity",{"type":44,"tag":113,"props":355,"children":356},{},[357,362],{"type":44,"tag":306,"props":358,"children":359},{},[360],{"type":50,"value":361},"What's wrong",{"type":50,"value":363},": One-sentence description",{"type":44,"tag":113,"props":365,"children":366},{},[367,372,374,380],{"type":44,"tag":306,"props":368,"children":369},{},[370],{"type":50,"value":371},"Action",{"type":50,"value":373},": What to do about it (see ",{"type":44,"tag":138,"props":375,"children":377},{"href":376},".\u002Freferences\u002Fremediation-actions.md",[378],{"type":50,"value":379},"remediation actions",{"type":50,"value":381},")",{"type":44,"tag":53,"props":383,"children":384},{},[385],{"type":50,"value":386},"Example:",{"type":44,"tag":388,"props":389,"children":390},"blockquote",{},[391],{"type":44,"tag":53,"props":392,"children":393},{},[394,396,401,403,409,411,415],{"type":50,"value":395},"🟡 ",{"type":44,"tag":306,"props":397,"children":398},{},[399],{"type":50,"value":400},"WARNING",{"type":50,"value":402}," — Flag integration · ",{"type":44,"tag":138,"props":404,"children":406},{"href":405},"\u002Fexperiments\u002F42",[407],{"type":50,"value":408},"Experiment: checkout-redesign",{"type":50,"value":410},"\nThe linked feature flag is inactive (paused). Traffic is not being split.\n",{"type":44,"tag":306,"props":412,"children":413},{},[414],{"type":50,"value":371},{"type":50,"value":416},": Re-enable the flag or end the experiment.",{"type":44,"tag":90,"props":418,"children":420},{"id":419},"handling-unavailable-data",[421],{"type":50,"value":422},"Handling unavailable data",{"type":44,"tag":53,"props":424,"children":425},{},[426,428,434],{"type":50,"value":427},"Some checks require activity logs (",{"type":44,"tag":59,"props":429,"children":431},{"className":430},[],[432],{"type":50,"value":433},"feature-flags-activity-retrieve",{"type":50,"value":435}," for flags), which may not be available in every session.\nIf activity log data is unavailable:",{"type":44,"tag":299,"props":437,"children":438},{},[439,452,457],{"type":44,"tag":113,"props":440,"children":441},{},[442,444,450],{"type":50,"value":443},"Skip ",{"type":44,"tag":59,"props":445,"children":447},{"className":446},[],[448],{"type":50,"value":449},"checkActivityHistory",{"type":50,"value":451}," (experiment check) entirely.",{"type":44,"tag":113,"props":453,"children":454},{},[455],{"type":50,"value":456},"Skip the \"toggle instability\" and \"never activated\" sub-checks in flag lifecycle checks.",{"type":44,"tag":113,"props":458,"children":459},{},[460,462],{"type":50,"value":461},"In your report, note which checks were skipped and why:\n",{"type":44,"tag":388,"props":463,"children":464},{},[465],{"type":44,"tag":53,"props":466,"children":467},{},[468],{"type":44,"tag":469,"props":470,"children":471},"em",{},[472],{"type":50,"value":473},"Skipped: Activity history checks (activity logs not available via current tools)",{"type":44,"tag":90,"props":475,"children":477},{"id":476},"partial-failures",[478],{"type":50,"value":479},"Partial failures",{"type":44,"tag":53,"props":481,"children":482},{},[483],{"type":50,"value":484},"If a fetch call fails for some entities:",{"type":44,"tag":299,"props":486,"children":487},{},[488,493,498],{"type":44,"tag":113,"props":489,"children":490},{},[491],{"type":50,"value":492},"Continue with the entities you could fetch.",{"type":44,"tag":113,"props":494,"children":495},{},[496],{"type":50,"value":497},"Report which entities could not be assessed and why.",{"type":44,"tag":113,"props":499,"children":500},{},[501],{"type":50,"value":502},"Do not silently omit entities from the audit.",{"type":44,"tag":90,"props":504,"children":506},{"id":505},"reference-files",[507],{"type":50,"value":508},"Reference files",{"type":44,"tag":299,"props":510,"children":511},{},[512,522,532,543,553],{"type":44,"tag":113,"props":513,"children":514},{},[515,520],{"type":44,"tag":138,"props":516,"children":517},{"href":140},[518],{"type":50,"value":519},"Experiment checks",{"type":50,"value":521}," — experiment configuration checks",{"type":44,"tag":113,"props":523,"children":524},{},[525,530],{"type":44,"tag":138,"props":526,"children":527},{"href":148},[528],{"type":50,"value":529},"Flag checks",{"type":50,"value":531}," — feature flag checks",{"type":44,"tag":113,"props":533,"children":534},{},[535,541],{"type":44,"tag":138,"props":536,"children":538},{"href":537},".\u002Freferences\u002Ffinding-taxonomy.md",[539],{"type":50,"value":540},"Finding types",{"type":50,"value":542}," — severity and category definitions",{"type":44,"tag":113,"props":544,"children":545},{},[546,551],{"type":44,"tag":138,"props":547,"children":548},{"href":268},[549],{"type":50,"value":550},"Recurring patterns",{"type":50,"value":552}," — patterns across multiple findings",{"type":44,"tag":113,"props":554,"children":555},{},[556,561],{"type":44,"tag":138,"props":557,"children":558},{"href":376},[559],{"type":50,"value":560},"Remediation actions",{"type":50,"value":562}," — what to do about each finding",{"items":564,"total":735},[565,584,594,607,620,635,651,668,682,697,707,725],{"slug":566,"name":566,"fn":567,"description":568,"org":569,"tags":570,"stars":581,"repoUrl":582,"updatedAt":583},"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},[571,574,577,580],{"name":572,"slug":573,"type":13},"Analytics","analytics",{"name":575,"slug":576,"type":13},"Cost Optimization","cost-optimization",{"name":578,"slug":579,"type":13},"Observability","observability",{"name":9,"slug":8,"type":13},35568,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog","2026-07-28T05:34:11.117757",{"slug":585,"name":585,"fn":586,"description":587,"org":588,"tags":589,"stars":581,"repoUrl":582,"updatedAt":593},"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},[590,591,592],{"name":572,"slug":573,"type":13},{"name":21,"slug":22,"type":13},{"name":9,"slug":8,"type":13},"2026-06-08T08:08:33.693989",{"slug":595,"name":595,"fn":596,"description":597,"org":598,"tags":599,"stars":581,"repoUrl":582,"updatedAt":606},"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},[600,601,604,605],{"name":21,"slug":22,"type":13},{"name":602,"slug":603,"type":13},"Data Warehouse","data-warehouse",{"name":578,"slug":579,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:22:57.67984",{"slug":608,"name":608,"fn":609,"description":610,"org":611,"tags":612,"stars":581,"repoUrl":582,"updatedAt":619},"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},[613,614,615,618],{"name":21,"slug":22,"type":13},{"name":602,"slug":603,"type":13},{"name":616,"slug":617,"type":13},"Performance","performance",{"name":9,"slug":8,"type":13},"2026-06-18T08:25:10.936787",{"slug":621,"name":621,"fn":622,"description":623,"org":624,"tags":625,"stars":581,"repoUrl":582,"updatedAt":634},"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},[626,629,632,633],{"name":627,"slug":628,"type":13},"Alerting","alerting",{"name":630,"slug":631,"type":13},"Debugging","debugging",{"name":578,"slug":579,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:24:40.318583",{"slug":636,"name":636,"fn":637,"description":638,"org":639,"tags":640,"stars":581,"repoUrl":582,"updatedAt":650},"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},[641,642,645,646,649],{"name":572,"slug":573,"type":13},{"name":643,"slug":644,"type":13},"Monitoring","monitoring",{"name":578,"slug":579,"type":13},{"name":647,"slug":648,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-18T05:10:54.430898",{"slug":652,"name":652,"fn":653,"description":654,"org":655,"tags":656,"stars":581,"repoUrl":582,"updatedAt":667},"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},[657,660,663,664],{"name":658,"slug":659,"type":13},"Automation","automation",{"name":661,"slug":662,"type":13},"MCP","mcp",{"name":9,"slug":8,"type":13},{"name":665,"slug":666,"type":13},"Workflow Automation","workflow-automation","2026-07-28T05:34:12.167015",{"slug":669,"name":669,"fn":670,"description":671,"org":672,"tags":673,"stars":581,"repoUrl":582,"updatedAt":681},"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},[674,675,676,679,680],{"name":572,"slug":573,"type":13},{"name":630,"slug":631,"type":13},{"name":677,"slug":678,"type":13},"Frontend","frontend",{"name":578,"slug":579,"type":13},{"name":9,"slug":8,"type":13},"2026-05-07T05:56:19.828048",{"slug":683,"name":683,"fn":684,"description":685,"org":686,"tags":687,"stars":581,"repoUrl":582,"updatedAt":696},"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},[688,691,692,693],{"name":689,"slug":690,"type":13},"API Development","api-development",{"name":677,"slug":678,"type":13},{"name":9,"slug":8,"type":13},{"name":694,"slug":695,"type":13},"SDK","sdk","2026-06-08T08:08:34.929454",{"slug":698,"name":698,"fn":699,"description":700,"org":701,"tags":702,"stars":581,"repoUrl":582,"updatedAt":706},"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},[703,704,705],{"name":689,"slug":690,"type":13},{"name":647,"slug":648,"type":13},{"name":9,"slug":8,"type":13},"2026-07-15T05:29:58.442727",{"slug":708,"name":708,"fn":709,"description":710,"org":711,"tags":712,"stars":581,"repoUrl":582,"updatedAt":724},"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},[713,714,717,718,721],{"name":658,"slug":659,"type":13},{"name":715,"slug":716,"type":13},"Email","email",{"name":9,"slug":8,"type":13},{"name":719,"slug":720,"type":13},"Reporting","reporting",{"name":722,"slug":723,"type":13},"Slack","slack","2026-06-09T07:32:27.935712",{"slug":726,"name":726,"fn":727,"description":728,"org":729,"tags":730,"stars":581,"repoUrl":582,"updatedAt":734},"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},[731,732,733],{"name":572,"slug":573,"type":13},{"name":689,"slug":690,"type":13},{"name":9,"slug":8,"type":13},"2026-06-08T08:08:29.624498",231,{"items":737,"total":835},[738,753,769,776,789,801,819],{"slug":739,"name":739,"fn":740,"description":741,"org":742,"tags":743,"stars":23,"repoUrl":24,"updatedAt":752},"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},[744,745,748,749],{"name":572,"slug":573,"type":13},{"name":746,"slug":747,"type":13},"Design","design",{"name":9,"slug":8,"type":13},{"name":750,"slug":751,"type":13},"User Research","user-research","2026-04-06T18:44:38.291781",{"slug":754,"name":754,"fn":755,"description":756,"org":757,"tags":758,"stars":23,"repoUrl":24,"updatedAt":768},"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},[759,760,761,762,765],{"name":572,"slug":573,"type":13},{"name":677,"slug":678,"type":13},{"name":9,"slug":8,"type":13},{"name":763,"slug":764,"type":13},"Product Management","product-management",{"name":766,"slug":767,"type":13},"UX Design","ux-design","2026-06-05T07:40:43.37798",{"slug":4,"name":4,"fn":5,"description":6,"org":770,"tags":771,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[772,773,774,775],{"name":21,"slug":22,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"slug":777,"name":777,"fn":778,"description":779,"org":780,"tags":781,"stars":23,"repoUrl":24,"updatedAt":788},"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},[782,785,786,787],{"name":783,"slug":784,"type":13},"Agents","agents",{"name":658,"slug":659,"type":13},{"name":578,"slug":579,"type":13},{"name":9,"slug":8,"type":13},"2026-07-28T05:33:45.509154",{"slug":790,"name":790,"fn":791,"description":792,"org":793,"tags":794,"stars":23,"repoUrl":24,"updatedAt":800},"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},[795,796,799],{"name":572,"slug":573,"type":13},{"name":797,"slug":798,"type":13},"Dashboards","dashboards",{"name":661,"slug":662,"type":13},"2026-07-21T06:07:38.060598",{"slug":802,"name":802,"fn":803,"description":804,"org":805,"tags":806,"stars":23,"repoUrl":24,"updatedAt":818},"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},[807,810,813,816,817],{"name":808,"slug":809,"type":13},"Deployment","deployment",{"name":811,"slug":812,"type":13},"Git","git",{"name":814,"slug":815,"type":13},"GitHub","github",{"name":578,"slug":579,"type":13},{"name":9,"slug":8,"type":13},"2026-06-28T07:46:59.53536",{"slug":820,"name":820,"fn":821,"description":822,"org":823,"tags":824,"stars":23,"repoUrl":24,"updatedAt":834},"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},[825,826,829,832,833],{"name":572,"slug":573,"type":13},{"name":827,"slug":828,"type":13},"Charts","charts",{"name":830,"slug":831,"type":13},"Data Visualization","data-visualization",{"name":9,"slug":8,"type":13},{"name":719,"slug":720,"type":13},"2026-06-18T08:18:57.960157",56]