[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-posthog-signals-scout-general":3,"mdc--lqly5g-key":37,"related-repo-posthog-signals-scout-general":467,"related-org-posthog-signals-scout-general":576},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":35,"mdContent":36},"signals-scout-general","analyze PostHog projects for high-confidence findings","General Signals scout for PostHog projects. Cross-product explorer that scans a team's project and emits findings into the Signals inbox. Sibling signals-scout-* specialists each watch a single product surface in depth; this scout looks for cross-product correlations and explores the surfaces no specialist covers. Each scout runs on its own schedule (default hourly), so general fires independently of the specialists over time.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"posthog","PostHog","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fposthog.png",[12,16,17,20,23],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Reporting","reporting",{"name":21,"slug":22,"type":15},"Data Analysis","data-analysis",{"name":24,"slug":25,"type":15},"Analytics","analytics",56,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fskills","2026-06-01T07:49:44.43013",null,4,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"PostHog skills (under construction)","https:\u002F\u002Fgithub.com\u002FPostHog\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fomnibus\u002Fsignals-scout-general","---\nname: signals-scout-general\ndescription: >\n  General Signals scout for PostHog projects. Cross-product explorer that scans a\n  team's project and emits findings into the Signals inbox. Sibling signals-scout-*\n  specialists each watch a single product surface in depth; this scout looks for\n  cross-product correlations and explores the surfaces no specialist covers. Each\n  scout runs on its own schedule (default hourly), so general fires independently\n  of the specialists over time.\ncompatibility: >\n  Runs as the PostHog Signals scout in a Claude sandbox with PostHog MCP scopes: signal_scout:read + signal_scout_internal:write (for\n  scratchpad-remember\u002Fforget and emit-signal), llm_skill:read, plus standard analytics reads. Uses the\n  signals-scout MCP family: project-profile-get, runs-list, runs-retrieve,\n  scratchpad-search, scratchpad-remember, scratchpad-forget, emit-signal.\nmetadata:\n  owner_team: signals\n---\n\n# Signals scout\n\nYou are a Signals scout. Look at this PostHog project, find what's actually worth\nsurfacing, and emit it as a finding. Skip what's noise. An empty findings list is\na real outcome — re-emitting a known issue is worse than emitting nothing.\n\n## Orient\n\nThree cheap reads cold-start a run:\n\n- `signals-scout-project-profile-get` — deterministic snapshot of products in use,\n  recent activity, integrations, top events with reach + burst metrics, inbox\n  report counts.\n- `signals-scout-scratchpad-search` — durable observations from past runs (the\n  team's history). Search with `text=\u003Ckeyword>` (ILIKE on key + content).\n- `signals-scout-runs-list` — recent summaries from this scout and siblings. Skim\n  the prose; pull `signals-scout-runs-retrieve` only when a summary mentions\n  something you're considering.\n\n## Explore\n\nPick what looks interesting and follow it. The profile names the products this\nteam uses; the scratchpad tells you what's normal; recent runs tell you what's\nalready covered. Validate hypotheses with concrete queries (`query-trends`,\n`query-funnel`, `query-error-tracking-issues-list`, `read-data-schema`,\n`inbox-reports-list`, `execute-sql`, etc.) before emitting.\n\nIf a sibling specialist already covers a surface in depth, leave the deep dive to it\non a future tick — the `skill_name`s on recent runs in `signals-scout-runs-list` show\nthe live roster (specialists exist for most product surfaces: error tracking, logs, AI\nobservability, experiments, feature flags, session replay, web analytics, surveys, and\nmore). Spend your time on **cross-product correlations** or on **surfaces no\nspecialist covers**.\n\n## Decide\n\nFor each candidate finding:\n\n- **Emit** via `signals-scout-emit-signal` if it clears the confidence\n  bar. The emit contract — schema, confidence rubric, severity, dedupe\n  keys, worked example — lives in [`references\u002Femit.md`](references\u002Femit.md).\n- **Remember** via `signals-scout-scratchpad-remember` if it's below the bar but\n  worth carrying forward, or to record what you ruled out and why.\n- **Skip** if the scratchpad already covers it.\n\nThe scratchpad has no tags or TTLs — entries are durable per-team prose keyed by\nstring, and re-using a key rewrites the entry in place. Encode the category in\nthe key prefix:\n\n| Prefix        | Use for                                                                          |\n| ------------- | -------------------------------------------------------------------------------- |\n| `pattern:`    | Durable observation about how this team's data normally shapes (baselines, etc). |\n| `noise:`      | Patterns to ignore (single-user, dev-only, recurring with no fix path).          |\n| `addressed:`  | Team-confirmed fix shipped or topic the team has moved on from.                  |\n| `dedupe:`     | Gates future emits on a specific issue \u002F fingerprint \u002F finding id.               |\n| `allowlist:`  | Vetted entities the scout should never re-surface.                               |\n| `not-in-use:` | Close-out memo for \"product not in use on this team\".                            |\n\nFull conventions (four-states classifier, cross-project noise patterns to\nrecognize) live in [`references\u002Fconventions.md`](references\u002Fconventions.md).\n\n## Avoid lens-lock\n\nIf the last few runs returned to the same lens, deliberately pick a different\none. Each scout runs on its own schedule, so you don't need to cover everything\nin one run — your job within a run is to follow what's interesting in the data,\nnot to ceremonially rotate lenses.\n\n## Close out\n\nIf you emitted findings, summarize in one paragraph: what + why. If you didn't,\none sentence is enough. The harness writes your summary to the run row;\n`signals-scout-runs-list` is how future runs and analysis read it.\n",{"data":38,"body":42},{"name":4,"description":6,"compatibility":39,"metadata":40},"Runs as the PostHog Signals scout in a Claude sandbox with PostHog MCP scopes: signal_scout:read + signal_scout_internal:write (for scratchpad-remember\u002Fforget and emit-signal), llm_skill:read, plus standard analytics reads. Uses the signals-scout MCP family: project-profile-get, runs-list, runs-retrieve, scratchpad-search, scratchpad-remember, scratchpad-forget, emit-signal.\n",{"owner_team":41},"signals",{"type":43,"children":44},"root",[45,54,60,67,72,127,133,183,218,224,229,288,293,423,438,444,449,455],{"type":46,"tag":47,"props":48,"children":50},"element","h1",{"id":49},"signals-scout",[51],{"type":52,"value":53},"text","Signals scout",{"type":46,"tag":55,"props":56,"children":57},"p",{},[58],{"type":52,"value":59},"You are a Signals scout. Look at this PostHog project, find what's actually worth\nsurfacing, and emit it as a finding. Skip what's noise. An empty findings list is\na real outcome — re-emitting a known issue is worse than emitting nothing.",{"type":46,"tag":61,"props":62,"children":64},"h2",{"id":63},"orient",[65],{"type":52,"value":66},"Orient",{"type":46,"tag":55,"props":68,"children":69},{},[70],{"type":52,"value":71},"Three cheap reads cold-start a run:",{"type":46,"tag":73,"props":74,"children":75},"ul",{},[76,89,108],{"type":46,"tag":77,"props":78,"children":79},"li",{},[80,87],{"type":46,"tag":81,"props":82,"children":84},"code",{"className":83},[],[85],{"type":52,"value":86},"signals-scout-project-profile-get",{"type":52,"value":88}," — deterministic snapshot of products in use,\nrecent activity, integrations, top events with reach + burst metrics, inbox\nreport counts.",{"type":46,"tag":77,"props":90,"children":91},{},[92,98,100,106],{"type":46,"tag":81,"props":93,"children":95},{"className":94},[],[96],{"type":52,"value":97},"signals-scout-scratchpad-search",{"type":52,"value":99}," — durable observations from past runs (the\nteam's history). Search with ",{"type":46,"tag":81,"props":101,"children":103},{"className":102},[],[104],{"type":52,"value":105},"text=\u003Ckeyword>",{"type":52,"value":107}," (ILIKE on key + content).",{"type":46,"tag":77,"props":109,"children":110},{},[111,117,119,125],{"type":46,"tag":81,"props":112,"children":114},{"className":113},[],[115],{"type":52,"value":116},"signals-scout-runs-list",{"type":52,"value":118}," — recent summaries from this scout and siblings. Skim\nthe prose; pull ",{"type":46,"tag":81,"props":120,"children":122},{"className":121},[],[123],{"type":52,"value":124},"signals-scout-runs-retrieve",{"type":52,"value":126}," only when a summary mentions\nsomething you're considering.",{"type":46,"tag":61,"props":128,"children":130},{"id":129},"explore",[131],{"type":52,"value":132},"Explore",{"type":46,"tag":55,"props":134,"children":135},{},[136,138,144,146,152,154,160,161,167,168,174,175,181],{"type":52,"value":137},"Pick what looks interesting and follow it. The profile names the products this\nteam uses; the scratchpad tells you what's normal; recent runs tell you what's\nalready covered. Validate hypotheses with concrete queries (",{"type":46,"tag":81,"props":139,"children":141},{"className":140},[],[142],{"type":52,"value":143},"query-trends",{"type":52,"value":145},",\n",{"type":46,"tag":81,"props":147,"children":149},{"className":148},[],[150],{"type":52,"value":151},"query-funnel",{"type":52,"value":153},", ",{"type":46,"tag":81,"props":155,"children":157},{"className":156},[],[158],{"type":52,"value":159},"query-error-tracking-issues-list",{"type":52,"value":153},{"type":46,"tag":81,"props":162,"children":164},{"className":163},[],[165],{"type":52,"value":166},"read-data-schema",{"type":52,"value":145},{"type":46,"tag":81,"props":169,"children":171},{"className":170},[],[172],{"type":52,"value":173},"inbox-reports-list",{"type":52,"value":153},{"type":46,"tag":81,"props":176,"children":178},{"className":177},[],[179],{"type":52,"value":180},"execute-sql",{"type":52,"value":182},", etc.) before emitting.",{"type":46,"tag":55,"props":184,"children":185},{},[186,188,194,196,201,203,209,211,216],{"type":52,"value":187},"If a sibling specialist already covers a surface in depth, leave the deep dive to it\non a future tick — the ",{"type":46,"tag":81,"props":189,"children":191},{"className":190},[],[192],{"type":52,"value":193},"skill_name",{"type":52,"value":195},"s on recent runs in ",{"type":46,"tag":81,"props":197,"children":199},{"className":198},[],[200],{"type":52,"value":116},{"type":52,"value":202}," show\nthe live roster (specialists exist for most product surfaces: error tracking, logs, AI\nobservability, experiments, feature flags, session replay, web analytics, surveys, and\nmore). Spend your time on ",{"type":46,"tag":204,"props":205,"children":206},"strong",{},[207],{"type":52,"value":208},"cross-product correlations",{"type":52,"value":210}," or on ",{"type":46,"tag":204,"props":212,"children":213},{},[214],{"type":52,"value":215},"surfaces no\nspecialist covers",{"type":52,"value":217},".",{"type":46,"tag":61,"props":219,"children":221},{"id":220},"decide",[222],{"type":52,"value":223},"Decide",{"type":46,"tag":55,"props":225,"children":226},{},[227],{"type":52,"value":228},"For each candidate finding:",{"type":46,"tag":73,"props":230,"children":231},{},[232,261,278],{"type":46,"tag":77,"props":233,"children":234},{},[235,240,242,248,250,260],{"type":46,"tag":204,"props":236,"children":237},{},[238],{"type":52,"value":239},"Emit",{"type":52,"value":241}," via ",{"type":46,"tag":81,"props":243,"children":245},{"className":244},[],[246],{"type":52,"value":247},"signals-scout-emit-signal",{"type":52,"value":249}," if it clears the confidence\nbar. The emit contract — schema, confidence rubric, severity, dedupe\nkeys, worked example — lives in ",{"type":46,"tag":251,"props":252,"children":254},"a",{"href":253},"references\u002Femit.md",[255],{"type":46,"tag":81,"props":256,"children":258},{"className":257},[],[259],{"type":52,"value":253},{"type":52,"value":217},{"type":46,"tag":77,"props":262,"children":263},{},[264,269,270,276],{"type":46,"tag":204,"props":265,"children":266},{},[267],{"type":52,"value":268},"Remember",{"type":52,"value":241},{"type":46,"tag":81,"props":271,"children":273},{"className":272},[],[274],{"type":52,"value":275},"signals-scout-scratchpad-remember",{"type":52,"value":277}," if it's below the bar but\nworth carrying forward, or to record what you ruled out and why.",{"type":46,"tag":77,"props":279,"children":280},{},[281,286],{"type":46,"tag":204,"props":282,"children":283},{},[284],{"type":52,"value":285},"Skip",{"type":52,"value":287}," if the scratchpad already covers it.",{"type":46,"tag":55,"props":289,"children":290},{},[291],{"type":52,"value":292},"The scratchpad has no tags or TTLs — entries are durable per-team prose keyed by\nstring, and re-using a key rewrites the entry in place. Encode the category in\nthe key prefix:",{"type":46,"tag":294,"props":295,"children":296},"table",{},[297,316],{"type":46,"tag":298,"props":299,"children":300},"thead",{},[301],{"type":46,"tag":302,"props":303,"children":304},"tr",{},[305,311],{"type":46,"tag":306,"props":307,"children":308},"th",{},[309],{"type":52,"value":310},"Prefix",{"type":46,"tag":306,"props":312,"children":313},{},[314],{"type":52,"value":315},"Use for",{"type":46,"tag":317,"props":318,"children":319},"tbody",{},[320,338,355,372,389,406],{"type":46,"tag":302,"props":321,"children":322},{},[323,333],{"type":46,"tag":324,"props":325,"children":326},"td",{},[327],{"type":46,"tag":81,"props":328,"children":330},{"className":329},[],[331],{"type":52,"value":332},"pattern:",{"type":46,"tag":324,"props":334,"children":335},{},[336],{"type":52,"value":337},"Durable observation about how this team's data normally shapes (baselines, etc).",{"type":46,"tag":302,"props":339,"children":340},{},[341,350],{"type":46,"tag":324,"props":342,"children":343},{},[344],{"type":46,"tag":81,"props":345,"children":347},{"className":346},[],[348],{"type":52,"value":349},"noise:",{"type":46,"tag":324,"props":351,"children":352},{},[353],{"type":52,"value":354},"Patterns to ignore (single-user, dev-only, recurring with no fix path).",{"type":46,"tag":302,"props":356,"children":357},{},[358,367],{"type":46,"tag":324,"props":359,"children":360},{},[361],{"type":46,"tag":81,"props":362,"children":364},{"className":363},[],[365],{"type":52,"value":366},"addressed:",{"type":46,"tag":324,"props":368,"children":369},{},[370],{"type":52,"value":371},"Team-confirmed fix shipped or topic the team has moved on from.",{"type":46,"tag":302,"props":373,"children":374},{},[375,384],{"type":46,"tag":324,"props":376,"children":377},{},[378],{"type":46,"tag":81,"props":379,"children":381},{"className":380},[],[382],{"type":52,"value":383},"dedupe:",{"type":46,"tag":324,"props":385,"children":386},{},[387],{"type":52,"value":388},"Gates future emits on a specific issue \u002F fingerprint \u002F finding id.",{"type":46,"tag":302,"props":390,"children":391},{},[392,401],{"type":46,"tag":324,"props":393,"children":394},{},[395],{"type":46,"tag":81,"props":396,"children":398},{"className":397},[],[399],{"type":52,"value":400},"allowlist:",{"type":46,"tag":324,"props":402,"children":403},{},[404],{"type":52,"value":405},"Vetted entities the scout should never re-surface.",{"type":46,"tag":302,"props":407,"children":408},{},[409,418],{"type":46,"tag":324,"props":410,"children":411},{},[412],{"type":46,"tag":81,"props":413,"children":415},{"className":414},[],[416],{"type":52,"value":417},"not-in-use:",{"type":46,"tag":324,"props":419,"children":420},{},[421],{"type":52,"value":422},"Close-out memo for \"product not in use on this team\".",{"type":46,"tag":55,"props":424,"children":425},{},[426,428,437],{"type":52,"value":427},"Full conventions (four-states classifier, cross-project noise patterns to\nrecognize) live in ",{"type":46,"tag":251,"props":429,"children":431},{"href":430},"references\u002Fconventions.md",[432],{"type":46,"tag":81,"props":433,"children":435},{"className":434},[],[436],{"type":52,"value":430},{"type":52,"value":217},{"type":46,"tag":61,"props":439,"children":441},{"id":440},"avoid-lens-lock",[442],{"type":52,"value":443},"Avoid lens-lock",{"type":46,"tag":55,"props":445,"children":446},{},[447],{"type":52,"value":448},"If the last few runs returned to the same lens, deliberately pick a different\none. Each scout runs on its own schedule, so you don't need to cover everything\nin one run — your job within a run is to follow what's interesting in the data,\nnot to ceremonially rotate lenses.",{"type":46,"tag":61,"props":450,"children":452},{"id":451},"close-out",[453],{"type":52,"value":454},"Close out",{"type":46,"tag":55,"props":456,"children":457},{},[458,460,465],{"type":52,"value":459},"If you emitted findings, summarize in one paragraph: what + why. If you didn't,\none sentence is enough. The harness writes your summary to the run row;\n",{"type":46,"tag":81,"props":461,"children":463},{"className":462},[],[464],{"type":52,"value":116},{"type":52,"value":466}," is how future runs and analysis read it.",{"items":468,"total":575},[469,486,504,518,534,548,559],{"slug":470,"name":470,"fn":471,"description":472,"org":473,"tags":474,"stars":26,"repoUrl":27,"updatedAt":485},"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},[475,478,481,482],{"name":476,"slug":477,"type":15},"Communications","communications",{"name":479,"slug":480,"type":15},"CRM","crm",{"name":9,"slug":8,"type":15},{"name":483,"slug":484,"type":15},"Sales","sales","2026-04-16T05:13:00.172732",{"slug":487,"name":487,"fn":488,"description":489,"org":490,"tags":491,"stars":26,"repoUrl":27,"updatedAt":503},"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},[492,495,498,501,502],{"name":493,"slug":494,"type":15},"Audit","audit",{"name":496,"slug":497,"type":15},"Data Engineering","data-engineering",{"name":499,"slug":500,"type":15},"Data Quality","data-quality",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-06-21T08:19:05.85849",{"slug":505,"name":505,"fn":506,"description":507,"org":508,"tags":509,"stars":26,"repoUrl":27,"updatedAt":517},"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},[510,513,516],{"name":511,"slug":512,"type":15},"Deployment","deployment",{"name":514,"slug":515,"type":15},"Feature Flags","feature-flags",{"name":9,"slug":8,"type":15},"2026-05-04T05:56:44.484909",{"slug":519,"name":519,"fn":520,"description":521,"org":522,"tags":523,"stars":26,"repoUrl":27,"updatedAt":533},"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},[524,527,528,529,532],{"name":525,"slug":526,"type":15},"A\u002FB Testing","a-b-testing",{"name":24,"slug":25,"type":15},{"name":21,"slug":22,"type":15},{"name":530,"slug":531,"type":15},"Debugging","debugging",{"name":9,"slug":8,"type":15},"2026-05-22T06:59:58.103867",{"slug":535,"name":535,"fn":536,"description":537,"org":538,"tags":539,"stars":26,"repoUrl":27,"updatedAt":547},"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},[540,541,542,545,546],{"name":24,"slug":25,"type":15},{"name":530,"slug":531,"type":15},{"name":543,"slug":544,"type":15},"Frontend","frontend",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-04-22T05:06:51.989772",{"slug":549,"name":549,"fn":550,"description":551,"org":552,"tags":553,"stars":26,"repoUrl":27,"updatedAt":558},"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},[554,555,556,557],{"name":24,"slug":25,"type":15},{"name":530,"slug":531,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-04-27T05:46:14.554016",{"slug":560,"name":560,"fn":561,"description":562,"org":563,"tags":564,"stars":26,"repoUrl":27,"updatedAt":574},"error-tracking-android","track Android errors with PostHog","PostHog error tracking for Android",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[565,568,569,572,573],{"name":566,"slug":567,"type":15},"Android","android",{"name":530,"slug":531,"type":15},{"name":570,"slug":571,"type":15},"Mobile","mobile",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-04-06T18:46:26.982494",110,{"items":577,"total":738},[578,593,603,616,629,642,658,675,687,702,712,728],{"slug":579,"name":579,"fn":580,"description":581,"org":582,"tags":583,"stars":590,"repoUrl":591,"updatedAt":592},"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},[584,585,588,589],{"name":24,"slug":25,"type":15},{"name":586,"slug":587,"type":15},"Cost Optimization","cost-optimization",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},35568,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog","2026-07-28T05:34:11.117757",{"slug":594,"name":594,"fn":595,"description":596,"org":597,"tags":598,"stars":590,"repoUrl":591,"updatedAt":602},"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},[599,600,601],{"name":24,"slug":25,"type":15},{"name":493,"slug":494,"type":15},{"name":9,"slug":8,"type":15},"2026-06-08T08:08:33.693989",{"slug":604,"name":604,"fn":605,"description":606,"org":607,"tags":608,"stars":590,"repoUrl":591,"updatedAt":615},"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},[609,610,613,614],{"name":493,"slug":494,"type":15},{"name":611,"slug":612,"type":15},"Data Warehouse","data-warehouse",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-06-18T08:22:57.67984",{"slug":617,"name":617,"fn":618,"description":619,"org":620,"tags":621,"stars":590,"repoUrl":591,"updatedAt":628},"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},[622,623,624,627],{"name":493,"slug":494,"type":15},{"name":611,"slug":612,"type":15},{"name":625,"slug":626,"type":15},"Performance","performance",{"name":9,"slug":8,"type":15},"2026-06-18T08:25:10.936787",{"slug":630,"name":630,"fn":631,"description":632,"org":633,"tags":634,"stars":590,"repoUrl":591,"updatedAt":641},"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},[635,638,639,640],{"name":636,"slug":637,"type":15},"Alerting","alerting",{"name":530,"slug":531,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-06-18T08:24:40.318583",{"slug":643,"name":643,"fn":644,"description":645,"org":646,"tags":647,"stars":590,"repoUrl":591,"updatedAt":657},"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},[648,649,652,653,656],{"name":24,"slug":25,"type":15},{"name":650,"slug":651,"type":15},"Monitoring","monitoring",{"name":13,"slug":14,"type":15},{"name":654,"slug":655,"type":15},"Operations","operations",{"name":9,"slug":8,"type":15},"2026-07-18T05:10:54.430898",{"slug":659,"name":659,"fn":660,"description":661,"org":662,"tags":663,"stars":590,"repoUrl":591,"updatedAt":674},"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},[664,667,670,671],{"name":665,"slug":666,"type":15},"Automation","automation",{"name":668,"slug":669,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},{"name":672,"slug":673,"type":15},"Workflow Automation","workflow-automation","2026-07-28T05:34:12.167015",{"slug":676,"name":676,"fn":677,"description":678,"org":679,"tags":680,"stars":590,"repoUrl":591,"updatedAt":686},"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},[681,682,683,684,685],{"name":24,"slug":25,"type":15},{"name":530,"slug":531,"type":15},{"name":543,"slug":544,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-05-07T05:56:19.828048",{"slug":688,"name":688,"fn":689,"description":690,"org":691,"tags":692,"stars":590,"repoUrl":591,"updatedAt":701},"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},[693,696,697,698],{"name":694,"slug":695,"type":15},"API Development","api-development",{"name":543,"slug":544,"type":15},{"name":9,"slug":8,"type":15},{"name":699,"slug":700,"type":15},"SDK","sdk","2026-06-08T08:08:34.929454",{"slug":703,"name":703,"fn":704,"description":705,"org":706,"tags":707,"stars":590,"repoUrl":591,"updatedAt":711},"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},[708,709,710],{"name":694,"slug":695,"type":15},{"name":654,"slug":655,"type":15},{"name":9,"slug":8,"type":15},"2026-07-15T05:29:58.442727",{"slug":713,"name":713,"fn":714,"description":715,"org":716,"tags":717,"stars":590,"repoUrl":591,"updatedAt":727},"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},[718,719,722,723,724],{"name":665,"slug":666,"type":15},{"name":720,"slug":721,"type":15},"Email","email",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},{"name":725,"slug":726,"type":15},"Slack","slack","2026-06-09T07:32:27.935712",{"slug":729,"name":729,"fn":730,"description":731,"org":732,"tags":733,"stars":590,"repoUrl":591,"updatedAt":737},"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},[734,735,736],{"name":24,"slug":25,"type":15},{"name":694,"slug":695,"type":15},{"name":9,"slug":8,"type":15},"2026-06-08T08:08:29.624498",231]