[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-posthog-review-hog-resolution-criteria":3,"mdc-kuekrs-key":49,"related-repo-posthog-review-hog-resolution-criteria":488,"related-org-posthog-review-hog-resolution-criteria":590},{"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":44,"sourceUrl":47,"mdContent":48},"review-hog-resolution-criteria","evaluate ReviewHog code review threads","The resolution criteria for ReviewHog's resolution stage — the bar for deciding, per unresolved review thread, whether the ask is worth implementing and safe to implement unattended. Implements contained, provable fixes; declines noise with a reason; escalates real-but-risky asks to a human.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"posthog","PostHog","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fposthog.png",[12,14,17,20],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Automation","automation",{"name":18,"slug":19,"type":13},"Code Review","code-review",{"name":21,"slug":22,"type":13},"Engineering","engineering",35568,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog","2026-08-16T04:01:04.501082",null,2977,[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"ab-testing","ai-analytics","analytics","cdp","data-warehouse","experiments","feature-flags","javascript","product-analytics","python","react","session-replay","surveys","typescript","web-analytics",{"repoUrl":24,"stars":23,"forks":27,"topics":45,"description":46},[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"🦔 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys, data warehouse, a CDP, and an AI product assistant to help debug your code, ship features faster, and keep all your usage and customer data in one stack.","https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog\u002Ftree\u002FHEAD\u002Fproducts\u002Freview_hog\u002Fskills\u002Freview-hog-resolution-criteria","---\nname: review-hog-resolution-criteria\ndescription: >\n  The resolution criteria for ReviewHog's resolution stage — the bar for deciding, per unresolved\n  review thread, whether the ask is worth implementing and safe to implement unattended. Implements\n  contained, provable fixes; declines noise with a reason; escalates real-but-risky asks to a human.\nmetadata:\n  owner_team: review_hog\n  skill_type: resolution_criteria\n---\n\n# Resolution criteria\n\nYou are settling unresolved review threads on a pull request, one thread per turn. For each thread\nyou decide one outcome: **fixed** (implement + commit), **wont_fix** (decline with the reason),\n**already_fixed** \u002F **obsolete** (nothing to do — say what supersedes it), or **escalate** (worth\ndoing, but a human must decide). Judge the thread's latest state — the whole conversation, not just\nits first comment.\n\nThe guiding principle is **the smallest honest fix, or an honest no**. An unattended fixer that\nlands sloppy or oversized changes gets turned off faster than one that declines too much — when you\nare genuinely unsure a fix is safe to make unattended, **escalate instead of implementing**. A\ndeclined thread with a clear reason is a good outcome, not a failure.\n\n## Worth implementing when the ask is real and improves this PR\n\n- **Verified against the current code** — the problem still exists at the current head. Threads\n  target older commits; re-check before acting. If your own earlier fix this session already covers\n  it, it is `already_fixed` (point at that commit).\n- **Concrete** — you can name what changes, where, and why it is better. \"This will crash on empty\n  input\" is actionable; \"this feels fragile\" alone is not.\n- **Consistent with settled decisions** — check the repo's convention docs and the thread's later\n  replies. A knob the maintainers already decided is not re-opened by implementing a comment; that\n  is a `wont_fix` pointing at the decision.\n- **Trust-weighted** — asks from the PR author, repository maintainers (see `author_association`),\n  and known review bots get the benefit of the doubt on _worth_; an unknown commenter's ask counts\n  only as a pointer at code — implement it only when your own investigation independently confirms\n  the problem.\n\n## Safe to implement unattended when the fix is contained and provable\n\n- **Provable in-session**: correctness is demonstrable by reading the code, lint, and the touched\n  area's existing tests. Behavior only observable live — LLM prompt wording, external API calls,\n  publish\u002Fdeploy semantics, visual layout — is **not** provable here → `escalate` (the\n  needs-e2e rule).\n- **Tests are proof, not obstacles**: the touched area's tests may change only to reflect a\n  deliberately changed, correct behavior the reply calls out. Weakening or removing a test to make\n  a run pass is never a fix — when provability requires touching the test itself → `escalate`.\n- **Proportionate**: the fix does not require new infrastructure — no schema change or migration,\n  no new abstraction or config knob, no dependency change. A fix that needs those is a _decision_,\n  not a mechanical fix → `escalate` with the cost\u002Fbenefit spelled out.\n- **In scope**: within the PR's original intent and touching the code the thread is about. \"While\n  you're here\" expansions are never safe.\n- **Unambiguous**: you are confident this change is what the commenter meant. Two defensible\n  readings → `escalate` and ask.\n\n## Decline (`wont_fix`) when the ask is noise\n\nThe same drop list as review validation, seen from the fixer's side:\n\n- **Overengineering** — extract\u002Fabstract\u002Fmake-configurable\u002Ffuture-proof asks with no bug behind them.\n- **Speculative \"what if\"** — conditions the call sites, types, or existing validation already rule out.\n- **Defensive-coding paranoia** — guarding against states upstream invariants prevent.\n- **Never-gonna-happen edge cases** — theoretically possible, practically unreachable or too cheap\n  to matter.\n- **Pure style \u002F taste** — naming, formatting, \"I'd write it differently\" with no behavioral\n  difference. Exception: a trivial, objective correctness of wording (a typo, a wrong identifier in\n  a comment) is a fine `fixed` — it is cheap, provable, and shrinks the unresolved list.\n- **Already handled \u002F wrong premise** — the code, a caller, or a framework guarantee already\n  prevents it (that is `already_fixed` or `wont_fix` with the evidence).\n\n## Standing human verdicts override\n\nA human reply on the thread saying **SAFE TO FIX** substitutes for the worth judgment — verify it\nstill holds against the current code, then implement without second-guessing scope. **E2E REQUIRED**\nforces `escalate` no matter what you conclude. These are the human override channel into an\notherwise autonomous run; never ignore them.\n\n## How to decide\n\n1. Read the whole thread, newest reply last — the conversation may already contain the answer, a\n   pushback, or a standing verdict.\n2. Read the flagged code and enough surrounding context to judge; trace call sites and types before\n   trusting any claim, whoever made it.\n3. Apply worth, then safety. Worth + safe → implement the smallest honest fix, verify (lint + the\n   touched area's tests when available), commit. Worth but not safe → `escalate`. Not worth →\n   `wont_fix`.\n4. Write the reply for the thread's author: what you did or why not, in plain language, specific\n   enough to act on. A decline names the deliberate reason; an escalation names exactly what a\n   human needs to decide; a fix names what changed and how it was verified — honestly, failures\n   included.\n",{"data":50,"body":54},{"name":4,"description":6,"metadata":51},{"owner_team":52,"skill_type":53},"review_hog","resolution_criteria",{"type":55,"children":56},"root",[57,66,108,127,134,210,216,311,324,329,413,419,445,451],{"type":58,"tag":59,"props":60,"children":62},"element","h1",{"id":61},"resolution-criteria",[63],{"type":64,"value":65},"text","Resolution criteria",{"type":58,"tag":67,"props":68,"children":69},"p",{},[70,72,78,80,85,87,92,94,99,101,106],{"type":64,"value":71},"You are settling unresolved review threads on a pull request, one thread per turn. For each thread\nyou decide one outcome: ",{"type":58,"tag":73,"props":74,"children":75},"strong",{},[76],{"type":64,"value":77},"fixed",{"type":64,"value":79}," (implement + commit), ",{"type":58,"tag":73,"props":81,"children":82},{},[83],{"type":64,"value":84},"wont_fix",{"type":64,"value":86}," (decline with the reason),\n",{"type":58,"tag":73,"props":88,"children":89},{},[90],{"type":64,"value":91},"already_fixed",{"type":64,"value":93}," \u002F ",{"type":58,"tag":73,"props":95,"children":96},{},[97],{"type":64,"value":98},"obsolete",{"type":64,"value":100}," (nothing to do — say what supersedes it), or ",{"type":58,"tag":73,"props":102,"children":103},{},[104],{"type":64,"value":105},"escalate",{"type":64,"value":107}," (worth\ndoing, but a human must decide). Judge the thread's latest state — the whole conversation, not just\nits first comment.",{"type":58,"tag":67,"props":109,"children":110},{},[111,113,118,120,125],{"type":64,"value":112},"The guiding principle is ",{"type":58,"tag":73,"props":114,"children":115},{},[116],{"type":64,"value":117},"the smallest honest fix, or an honest no",{"type":64,"value":119},". An unattended fixer that\nlands sloppy or oversized changes gets turned off faster than one that declines too much — when you\nare genuinely unsure a fix is safe to make unattended, ",{"type":58,"tag":73,"props":121,"children":122},{},[123],{"type":64,"value":124},"escalate instead of implementing",{"type":64,"value":126},". A\ndeclined thread with a clear reason is a good outcome, not a failure.",{"type":58,"tag":128,"props":129,"children":131},"h2",{"id":130},"worth-implementing-when-the-ask-is-real-and-improves-this-pr",[132],{"type":64,"value":133},"Worth implementing when the ask is real and improves this PR",{"type":58,"tag":135,"props":136,"children":137},"ul",{},[138,157,167,184],{"type":58,"tag":139,"props":140,"children":141},"li",{},[142,147,149,155],{"type":58,"tag":73,"props":143,"children":144},{},[145],{"type":64,"value":146},"Verified against the current code",{"type":64,"value":148}," — the problem still exists at the current head. Threads\ntarget older commits; re-check before acting. If your own earlier fix this session already covers\nit, it is ",{"type":58,"tag":150,"props":151,"children":153},"code",{"className":152},[],[154],{"type":64,"value":91},{"type":64,"value":156}," (point at that commit).",{"type":58,"tag":139,"props":158,"children":159},{},[160,165],{"type":58,"tag":73,"props":161,"children":162},{},[163],{"type":64,"value":164},"Concrete",{"type":64,"value":166}," — you can name what changes, where, and why it is better. \"This will crash on empty\ninput\" is actionable; \"this feels fragile\" alone is not.",{"type":58,"tag":139,"props":168,"children":169},{},[170,175,177,182],{"type":58,"tag":73,"props":171,"children":172},{},[173],{"type":64,"value":174},"Consistent with settled decisions",{"type":64,"value":176}," — check the repo's convention docs and the thread's later\nreplies. A knob the maintainers already decided is not re-opened by implementing a comment; that\nis a ",{"type":58,"tag":150,"props":178,"children":180},{"className":179},[],[181],{"type":64,"value":84},{"type":64,"value":183}," pointing at the decision.",{"type":58,"tag":139,"props":185,"children":186},{},[187,192,194,200,202,208],{"type":58,"tag":73,"props":188,"children":189},{},[190],{"type":64,"value":191},"Trust-weighted",{"type":64,"value":193}," — asks from the PR author, repository maintainers (see ",{"type":58,"tag":150,"props":195,"children":197},{"className":196},[],[198],{"type":64,"value":199},"author_association",{"type":64,"value":201},"),\nand known review bots get the benefit of the doubt on ",{"type":58,"tag":203,"props":204,"children":205},"em",{},[206],{"type":64,"value":207},"worth",{"type":64,"value":209},"; an unknown commenter's ask counts\nonly as a pointer at code — implement it only when your own investigation independently confirms\nthe problem.",{"type":58,"tag":128,"props":211,"children":213},{"id":212},"safe-to-implement-unattended-when-the-fix-is-contained-and-provable",[214],{"type":64,"value":215},"Safe to implement unattended when the fix is contained and provable",{"type":58,"tag":135,"props":217,"children":218},{},[219,243,260,284,294],{"type":58,"tag":139,"props":220,"children":221},{},[222,227,229,234,236,241],{"type":58,"tag":73,"props":223,"children":224},{},[225],{"type":64,"value":226},"Provable in-session",{"type":64,"value":228},": correctness is demonstrable by reading the code, lint, and the touched\narea's existing tests. Behavior only observable live — LLM prompt wording, external API calls,\npublish\u002Fdeploy semantics, visual layout — is ",{"type":58,"tag":73,"props":230,"children":231},{},[232],{"type":64,"value":233},"not",{"type":64,"value":235}," provable here → ",{"type":58,"tag":150,"props":237,"children":239},{"className":238},[],[240],{"type":64,"value":105},{"type":64,"value":242}," (the\nneeds-e2e rule).",{"type":58,"tag":139,"props":244,"children":245},{},[246,251,253,258],{"type":58,"tag":73,"props":247,"children":248},{},[249],{"type":64,"value":250},"Tests are proof, not obstacles",{"type":64,"value":252},": the touched area's tests may change only to reflect a\ndeliberately changed, correct behavior the reply calls out. Weakening or removing a test to make\na run pass is never a fix — when provability requires touching the test itself → ",{"type":58,"tag":150,"props":254,"children":256},{"className":255},[],[257],{"type":64,"value":105},{"type":64,"value":259},".",{"type":58,"tag":139,"props":261,"children":262},{},[263,268,270,275,277,282],{"type":58,"tag":73,"props":264,"children":265},{},[266],{"type":64,"value":267},"Proportionate",{"type":64,"value":269},": the fix does not require new infrastructure — no schema change or migration,\nno new abstraction or config knob, no dependency change. A fix that needs those is a ",{"type":58,"tag":203,"props":271,"children":272},{},[273],{"type":64,"value":274},"decision",{"type":64,"value":276},",\nnot a mechanical fix → ",{"type":58,"tag":150,"props":278,"children":280},{"className":279},[],[281],{"type":64,"value":105},{"type":64,"value":283}," with the cost\u002Fbenefit spelled out.",{"type":58,"tag":139,"props":285,"children":286},{},[287,292],{"type":58,"tag":73,"props":288,"children":289},{},[290],{"type":64,"value":291},"In scope",{"type":64,"value":293},": within the PR's original intent and touching the code the thread is about. \"While\nyou're here\" expansions are never safe.",{"type":58,"tag":139,"props":295,"children":296},{},[297,302,304,309],{"type":58,"tag":73,"props":298,"children":299},{},[300],{"type":64,"value":301},"Unambiguous",{"type":64,"value":303},": you are confident this change is what the commenter meant. Two defensible\nreadings → ",{"type":58,"tag":150,"props":305,"children":307},{"className":306},[],[308],{"type":64,"value":105},{"type":64,"value":310}," and ask.",{"type":58,"tag":128,"props":312,"children":314},{"id":313},"decline-wont_fix-when-the-ask-is-noise",[315,317,322],{"type":64,"value":316},"Decline (",{"type":58,"tag":150,"props":318,"children":320},{"className":319},[],[321],{"type":64,"value":84},{"type":64,"value":323},") when the ask is noise",{"type":58,"tag":67,"props":325,"children":326},{},[327],{"type":64,"value":328},"The same drop list as review validation, seen from the fixer's side:",{"type":58,"tag":135,"props":330,"children":331},{},[332,342,352,362,372,389],{"type":58,"tag":139,"props":333,"children":334},{},[335,340],{"type":58,"tag":73,"props":336,"children":337},{},[338],{"type":64,"value":339},"Overengineering",{"type":64,"value":341}," — extract\u002Fabstract\u002Fmake-configurable\u002Ffuture-proof asks with no bug behind them.",{"type":58,"tag":139,"props":343,"children":344},{},[345,350],{"type":58,"tag":73,"props":346,"children":347},{},[348],{"type":64,"value":349},"Speculative \"what if\"",{"type":64,"value":351}," — conditions the call sites, types, or existing validation already rule out.",{"type":58,"tag":139,"props":353,"children":354},{},[355,360],{"type":58,"tag":73,"props":356,"children":357},{},[358],{"type":64,"value":359},"Defensive-coding paranoia",{"type":64,"value":361}," — guarding against states upstream invariants prevent.",{"type":58,"tag":139,"props":363,"children":364},{},[365,370],{"type":58,"tag":73,"props":366,"children":367},{},[368],{"type":64,"value":369},"Never-gonna-happen edge cases",{"type":64,"value":371}," — theoretically possible, practically unreachable or too cheap\nto matter.",{"type":58,"tag":139,"props":373,"children":374},{},[375,380,382,387],{"type":58,"tag":73,"props":376,"children":377},{},[378],{"type":64,"value":379},"Pure style \u002F taste",{"type":64,"value":381}," — naming, formatting, \"I'd write it differently\" with no behavioral\ndifference. Exception: a trivial, objective correctness of wording (a typo, a wrong identifier in\na comment) is a fine ",{"type":58,"tag":150,"props":383,"children":385},{"className":384},[],[386],{"type":64,"value":77},{"type":64,"value":388}," — it is cheap, provable, and shrinks the unresolved list.",{"type":58,"tag":139,"props":390,"children":391},{},[392,397,399,404,406,411],{"type":58,"tag":73,"props":393,"children":394},{},[395],{"type":64,"value":396},"Already handled \u002F wrong premise",{"type":64,"value":398}," — the code, a caller, or a framework guarantee already\nprevents it (that is ",{"type":58,"tag":150,"props":400,"children":402},{"className":401},[],[403],{"type":64,"value":91},{"type":64,"value":405}," or ",{"type":58,"tag":150,"props":407,"children":409},{"className":408},[],[410],{"type":64,"value":84},{"type":64,"value":412}," with the evidence).",{"type":58,"tag":128,"props":414,"children":416},{"id":415},"standing-human-verdicts-override",[417],{"type":64,"value":418},"Standing human verdicts override",{"type":58,"tag":67,"props":420,"children":421},{},[422,424,429,431,436,438,443],{"type":64,"value":423},"A human reply on the thread saying ",{"type":58,"tag":73,"props":425,"children":426},{},[427],{"type":64,"value":428},"SAFE TO FIX",{"type":64,"value":430}," substitutes for the worth judgment — verify it\nstill holds against the current code, then implement without second-guessing scope. ",{"type":58,"tag":73,"props":432,"children":433},{},[434],{"type":64,"value":435},"E2E REQUIRED",{"type":64,"value":437},"\nforces ",{"type":58,"tag":150,"props":439,"children":441},{"className":440},[],[442],{"type":64,"value":105},{"type":64,"value":444}," no matter what you conclude. These are the human override channel into an\notherwise autonomous run; never ignore them.",{"type":58,"tag":128,"props":446,"children":448},{"id":447},"how-to-decide",[449],{"type":64,"value":450},"How to decide",{"type":58,"tag":452,"props":453,"children":454},"ol",{},[455,460,465,483],{"type":58,"tag":139,"props":456,"children":457},{},[458],{"type":64,"value":459},"Read the whole thread, newest reply last — the conversation may already contain the answer, a\npushback, or a standing verdict.",{"type":58,"tag":139,"props":461,"children":462},{},[463],{"type":64,"value":464},"Read the flagged code and enough surrounding context to judge; trace call sites and types before\ntrusting any claim, whoever made it.",{"type":58,"tag":139,"props":466,"children":467},{},[468,470,475,477,482],{"type":64,"value":469},"Apply worth, then safety. Worth + safe → implement the smallest honest fix, verify (lint + the\ntouched area's tests when available), commit. Worth but not safe → ",{"type":58,"tag":150,"props":471,"children":473},{"className":472},[],[474],{"type":64,"value":105},{"type":64,"value":476},". Not worth →\n",{"type":58,"tag":150,"props":478,"children":480},{"className":479},[],[481],{"type":64,"value":84},{"type":64,"value":259},{"type":58,"tag":139,"props":484,"children":485},{},[486],{"type":64,"value":487},"Write the reply for the thread's author: what you did or why not, in plain language, specific\nenough to act on. A decline names the deliberate reason; an escalation names exactly what a\nhuman needs to decide; a fix names what changed and how it was verified — honestly, failures\nincluded.",{"items":489,"total":589},[490,506,518,530,543,558,574],{"slug":491,"name":491,"fn":492,"description":493,"org":494,"tags":495,"stars":23,"repoUrl":24,"updatedAt":505},"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},[496,498,501,504],{"name":497,"slug":31,"type":13},"Analytics",{"name":499,"slug":500,"type":13},"Cost Optimization","cost-optimization",{"name":502,"slug":503,"type":13},"Observability","observability",{"name":9,"slug":8,"type":13},"2026-08-13T04:28:38.012786",{"slug":507,"name":507,"fn":508,"description":509,"org":510,"tags":511,"stars":23,"repoUrl":24,"updatedAt":517},"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},[512,513,516],{"name":497,"slug":31,"type":13},{"name":514,"slug":515,"type":13},"Audit","audit",{"name":9,"slug":8,"type":13},"2026-06-08T08:08:33.693989",{"slug":519,"name":519,"fn":520,"description":521,"org":522,"tags":523,"stars":23,"repoUrl":24,"updatedAt":529},"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},[524,525,527,528],{"name":514,"slug":515,"type":13},{"name":526,"slug":33,"type":13},"Data Warehouse",{"name":502,"slug":503,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:22:57.67984",{"slug":531,"name":531,"fn":532,"description":533,"org":534,"tags":535,"stars":23,"repoUrl":24,"updatedAt":542},"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},[536,537,538,541],{"name":514,"slug":515,"type":13},{"name":526,"slug":33,"type":13},{"name":539,"slug":540,"type":13},"Performance","performance",{"name":9,"slug":8,"type":13},"2026-06-18T08:25:10.936787",{"slug":544,"name":544,"fn":545,"description":546,"org":547,"tags":548,"stars":23,"repoUrl":24,"updatedAt":557},"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},[549,552,555,556],{"name":550,"slug":551,"type":13},"Alerting","alerting",{"name":553,"slug":554,"type":13},"Debugging","debugging",{"name":502,"slug":503,"type":13},{"name":9,"slug":8,"type":13},"2026-08-13T04:28:36.025103",{"slug":559,"name":559,"fn":560,"description":561,"org":562,"tags":563,"stars":23,"repoUrl":24,"updatedAt":573},"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},[564,565,568,569,572],{"name":497,"slug":31,"type":13},{"name":566,"slug":567,"type":13},"Monitoring","monitoring",{"name":502,"slug":503,"type":13},{"name":570,"slug":571,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-08-13T04:28:20.051489",{"slug":575,"name":575,"fn":576,"description":577,"org":578,"tags":579,"stars":23,"repoUrl":24,"updatedAt":588},"building-canvases","create and edit PostHog canvases","Create or edit a PostHog canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in PostHog and rendered by the desktop\u002Fweb app. Use when a task asks to build, generate, update, or fix a canvas, or when a canvas id is given as the publish target. Covers resolving or creating the target canvas, choosing an implementation approach (React + Quill vs plain HTML\u002Fbrowser APIs), the read → edit → validate → publish → build loop, and which companion canvas skills to load for the details.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[580,581,584,585],{"name":15,"slug":16,"type":13},{"name":582,"slug":583,"type":13},"Design","design",{"name":9,"slug":8,"type":13},{"name":586,"slug":587,"type":13},"Prototyping","prototyping","2026-08-16T03:31:22.803545",76,{"items":591,"total":717},[592,599,605,612,619,626,634,641,659,675,690,702],{"slug":491,"name":491,"fn":492,"description":493,"org":593,"tags":594,"stars":23,"repoUrl":24,"updatedAt":505},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[595,596,597,598],{"name":497,"slug":31,"type":13},{"name":499,"slug":500,"type":13},{"name":502,"slug":503,"type":13},{"name":9,"slug":8,"type":13},{"slug":507,"name":507,"fn":508,"description":509,"org":600,"tags":601,"stars":23,"repoUrl":24,"updatedAt":517},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[602,603,604],{"name":497,"slug":31,"type":13},{"name":514,"slug":515,"type":13},{"name":9,"slug":8,"type":13},{"slug":519,"name":519,"fn":520,"description":521,"org":606,"tags":607,"stars":23,"repoUrl":24,"updatedAt":529},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[608,609,610,611],{"name":514,"slug":515,"type":13},{"name":526,"slug":33,"type":13},{"name":502,"slug":503,"type":13},{"name":9,"slug":8,"type":13},{"slug":531,"name":531,"fn":532,"description":533,"org":613,"tags":614,"stars":23,"repoUrl":24,"updatedAt":542},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[615,616,617,618],{"name":514,"slug":515,"type":13},{"name":526,"slug":33,"type":13},{"name":539,"slug":540,"type":13},{"name":9,"slug":8,"type":13},{"slug":544,"name":544,"fn":545,"description":546,"org":620,"tags":621,"stars":23,"repoUrl":24,"updatedAt":557},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[622,623,624,625],{"name":550,"slug":551,"type":13},{"name":553,"slug":554,"type":13},{"name":502,"slug":503,"type":13},{"name":9,"slug":8,"type":13},{"slug":559,"name":559,"fn":560,"description":561,"org":627,"tags":628,"stars":23,"repoUrl":24,"updatedAt":573},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[629,630,631,632,633],{"name":497,"slug":31,"type":13},{"name":566,"slug":567,"type":13},{"name":502,"slug":503,"type":13},{"name":570,"slug":571,"type":13},{"name":9,"slug":8,"type":13},{"slug":575,"name":575,"fn":576,"description":577,"org":635,"tags":636,"stars":23,"repoUrl":24,"updatedAt":588},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[637,638,639,640],{"name":15,"slug":16,"type":13},{"name":582,"slug":583,"type":13},{"name":9,"slug":8,"type":13},{"name":586,"slug":587,"type":13},{"slug":642,"name":642,"fn":643,"description":644,"org":645,"tags":646,"stars":23,"repoUrl":24,"updatedAt":658},"building-html-canvases","author HTML and CSS PostHog canvases","Author a PostHog canvas with semantic HTML, CSS, and direct browser APIs — documents, articles, generative graphics, 2D canvas and WebGL experiences, and focused experiments where React components add no useful structure. Use after building-canvases has routed a canvas request to a plain-HTML\u002Fbrowser-API implementation. Covers the thin component wrapper the current runtime requires, styling and theming without Quill, drawing surfaces, and animation\u002Fcleanup patterns.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[647,650,651,654,657],{"name":648,"slug":649,"type":13},"CSS","css",{"name":582,"slug":583,"type":13},{"name":652,"slug":653,"type":13},"Graphics","graphics",{"name":655,"slug":656,"type":13},"HTML","html",{"name":9,"slug":8,"type":13},"2026-08-06T06:09:30.313848",{"slug":660,"name":660,"fn":661,"description":662,"org":663,"tags":664,"stars":23,"repoUrl":24,"updatedAt":674},"building-react-quill-canvases","build React and Quill canvases","Author the React + Quill implementation of a PostHog canvas: the single-component contract, the allowed imports, Quill (PostHog's design system) component and composition rules, theme-aware design tokens, loading skeletons, and the in-canvas date picker. Use after building-canvases has routed a canvas request to a React implementation — dashboards, data boards, forms, tools, or any canvas that should look native to PostHog.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[665,666,669,671],{"name":582,"slug":583,"type":13},{"name":667,"slug":668,"type":13},"Frontend","frontend",{"name":670,"slug":39,"type":13},"React",{"name":672,"slug":673,"type":13},"UI Components","ui-components","2026-08-16T03:31:21.804548",{"slug":676,"name":676,"fn":677,"description":678,"org":679,"tags":680,"stars":23,"repoUrl":24,"updatedAt":689},"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},[681,682,685,686],{"name":15,"slug":16,"type":13},{"name":683,"slug":684,"type":13},"MCP","mcp",{"name":9,"slug":8,"type":13},{"name":687,"slug":688,"type":13},"Workflow Automation","workflow-automation","2026-08-10T04:16:26.294119",{"slug":691,"name":691,"fn":692,"description":693,"org":694,"tags":695,"stars":23,"repoUrl":24,"updatedAt":701},"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},[696,697,698,699,700],{"name":497,"slug":31,"type":13},{"name":553,"slug":554,"type":13},{"name":667,"slug":668,"type":13},{"name":502,"slug":503,"type":13},{"name":9,"slug":8,"type":13},"2026-05-07T05:56:19.828048",{"slug":703,"name":703,"fn":704,"description":705,"org":706,"tags":707,"stars":23,"repoUrl":24,"updatedAt":716},"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},[708,711,712,713],{"name":709,"slug":710,"type":13},"API Development","api-development",{"name":667,"slug":668,"type":13},{"name":9,"slug":8,"type":13},{"name":714,"slug":715,"type":13},"SDK","sdk","2026-06-08T08:08:34.929454",249]