[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-posthog-review-hog-authoring":3,"mdc--9zol08-key":46,"related-org-posthog-review-hog-authoring":534,"related-repo-posthog-review-hog-authoring":705},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":20,"repoUrl":21,"updatedAt":22,"license":23,"forks":24,"topics":25,"repo":41,"sourceUrl":44,"mdContent":45},"review-hog-authoring","author custom ReviewHog review skills","How to author custom ReviewHog skills — the review perspectives, blind-spot checks, and validation criteria that drive ReviewHog's automated PR reviews. Use when a user wants a new review perspective (a specialist lens on their PRs), a custom blind-spot sweep, or their own validation bar for which findings get published. Trigger on \"create a ReviewHog perspective\", \"custom review perspective\", \"my own blind-spot check\", \"custom validation criteria\", \"tune what ReviewHog publishes\".\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],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Code Review","code-review",{"name":18,"slug":19,"type":13},"Plugin Development","plugin-development",35568,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog","2026-07-15T05:30:15.513344",null,2977,[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"ab-testing","ai-analytics","analytics","cdp","data-warehouse","experiments","feature-flags","javascript","product-analytics","python","react","session-replay","surveys","typescript","web-analytics",{"repoUrl":21,"stars":20,"forks":24,"topics":42,"description":43},[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"🦔 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-authoring","---\nname: review-hog-authoring\ndescription: >\n  How to author custom ReviewHog skills — the review perspectives, blind-spot checks, and\n  validation criteria that drive ReviewHog's automated PR reviews. Use when a user wants a new\n  review perspective (a specialist lens on their PRs), a custom blind-spot sweep, or their own\n  validation bar for which findings get published. Trigger on \"create a ReviewHog perspective\",\n  \"custom review perspective\", \"my own blind-spot check\", \"custom validation criteria\", \"tune what\n  ReviewHog publishes\".\nmetadata:\n  owner_team: review_hog\n  skill_type: authoring\n---\n\n# Authoring ReviewHog skills\n\n**ReviewHog** is PostHog's automated PR reviewer. A review splits the PR into chunks, then for each\nchunk runs every enabled **perspective** in parallel (independent specialist lenses), a single\n**blind-spot check** afterwards (a final sweep conditioned on what the perspectives found), and\nfinally judges every surviving candidate finding against one **validation criteria** skill — only\nfindings that pass get published to the pull request.\n\nAll three kinds are team `LLMSkill` rows the review agents pull over MCP at run time. PostHog ships\ncanonicals; this skill is the guide for authoring **custom** ones. The skill itself is team-level;\nwhether it _runs_ is a per-user setting in **Inbox → Code review**.\n\n| Kind                | Name contract                   | Cardinality per user                | Canonical example                          |\n| ------------------- | ------------------------------- | ----------------------------------- | ------------------------------------------ |\n| Review perspective  | `review-hog-perspective-\u003Cslug>` | Multi-enable, at least one stays on | `review-hog-perspective-logic-correctness` |\n| Blind-spot check    | `review-hog-blind-spots-\u003Cslug>` | Exactly one active; selecting swaps | `review-hog-blind-spots-general`           |\n| Validation criteria | `review-hog-validation-\u003Cslug>`  | Exactly one active; selecting swaps | `review-hog-validation-criteria`           |\n\n## Authoring flow\n\n1. **Ground yourself.** Using the PostHog MCP skill tools, `skill-list` the team's `review-hog-*`\n   skills and `skill-get` the canonical of the kind you're authoring (see the table above) — it is\n   the reference for structure and tone. For a perspective, skim the descriptions of every existing\n   `review-hog-perspective-*` so the new lens doesn't re-cover ground an enabled one already owns\n   (overlap gets deduplicated later, but it wastes review passes).\n2. **Interview the user.** Ask what the skill should focus on, and offer a few concrete directions\n   the current set doesn't cover — grounded in what you saw in step 1 and, when useful, in the\n   project itself. Don't start writing until the direction is picked.\n3. **Draft the body** following the per-kind guidance below. Keep it a focused instruction set the\n   review agent can apply to one chunk in one pass — not an essay.\n4. **Create the skill yourself with `posthog:skill-create`** — actually create the team `LLMSkill`\n   row; never hand the user a body to copy-paste. Pass the exact name per the contract above\n   (lowercase slug), a one-paragraph `description` of what the lens\u002Fsweep\u002Fbar is, and the body.\n   **The name prefix is the whole identity** — it is how the Code review tab and the review runs\n   discover the skill. There is no `category` parameter on the skill tools and you don't need one:\n   the backend stamps the `review_hog` grouping category itself (it only affects grouping on the\n   Skills page) — do not spend turns trying to set or verify it. Iterate with\n   `posthog:skill-update` if the user wants changes. Author fresh — don't `skill-duplicate` a\n   canonical to edit: seeded metadata rides along with the copy, and the canonical sync may\n   overwrite or prune it.\n5. **Tell the user how to activate it.** A custom skill starts inactive for them:\n   - **Perspective** — toggle it on under Inbox → Code review → Perspectives (it appears disabled\n     until they enable it; at least one perspective must stay on).\n   - **Blind-spot check \u002F validation criteria** — select it under the matching section; exactly one\n     runs at a time, so selecting it swaps out the current one **for their reviews only**.\n     Reviews pin skill versions when a run starts, so an edit mid-review applies from the next run.\n\n## Writing a review perspective\n\nThe body instructs one specialist review pass over one PR chunk. Match the canonical\nlogic-correctness skill's shape:\n\n- **The lane** — one sentence on what this lens is responsible for; report everything in lane and\n  leave the rest to the other perspectives.\n- **Hunting grounds** — a numbered handful of concrete places to look, each a specific check the\n  agent can walk against the chunk (\"transaction boundaries that split writes that must land\n  together\"), not an abstract virtue (\"ensure correctness\").\n- **Lane boundary** — which perspective owns each adjacent concern this lens must leave alone.\n- **The finding bar** — a publishable finding names the concrete trigger and the concrete\n  consequence; close with a completion criterion (\"done when every changed file is flagged or\n  cleared against every hunting ground\").\n\nThe review harness already tells the agent the pipeline mechanics — parallel perspectives, later\ndeduplication, severity levels, the non-test-files rule — so the skill carries only the lens;\nrestating harness rules dilutes it.\n\n## Writing a blind-spot check\n\nThe body instructs the final sweep that runs after every enabled perspective finished a chunk. It\nis **conditioned on the covered findings** (the prompt lists which perspectives ran and what they\nfound), so the body should say how to use that: the covered findings map where attention already\nwent, and the sweep's value is the negative space — error paths, unhandled inputs, cross-file\ninteractions, assumptions. It is not scoped to one specialty, and an empty result beats padding. A\ncustom sweep narrows or re-weights this hunt (e.g. toward a domain the team keeps getting burned\nby).\n\n## Writing validation criteria\n\nThe body defines the keep\u002Fdrop bar every candidate finding is judged against before publishing.\nPrecision over recall is the house default — a reviewer that raises noise gets muted — so define:\nwhat makes a finding real and worth an author's attention (user-affecting correctness, security,\ndata loss, contract breaks, performance), what gets dropped (overengineering, speculation,\ndefensive paranoia, unreachable edges, style), and how to treat genuine uncertainty (default:\ndrop). A custom bar shifts strictness or re-weights concerns; it should still demand evidence from\nthe live codebase, not vibes.\n",{"data":47,"body":51},{"name":4,"description":6,"metadata":48},{"owner_team":49,"skill_type":50},"review_hog","authoring",{"type":52,"children":53},"root",[54,63,96,132,262,269,446,452,457,500,505,511,523,529],{"type":55,"tag":56,"props":57,"children":59},"element","h1",{"id":58},"authoring-reviewhog-skills",[60],{"type":61,"value":62},"text","Authoring ReviewHog skills",{"type":55,"tag":64,"props":65,"children":66},"p",{},[67,73,75,80,82,87,89,94],{"type":55,"tag":68,"props":69,"children":70},"strong",{},[71],{"type":61,"value":72},"ReviewHog",{"type":61,"value":74}," is PostHog's automated PR reviewer. A review splits the PR into chunks, then for each\nchunk runs every enabled ",{"type":55,"tag":68,"props":76,"children":77},{},[78],{"type":61,"value":79},"perspective",{"type":61,"value":81}," in parallel (independent specialist lenses), a single\n",{"type":55,"tag":68,"props":83,"children":84},{},[85],{"type":61,"value":86},"blind-spot check",{"type":61,"value":88}," afterwards (a final sweep conditioned on what the perspectives found), and\nfinally judges every surviving candidate finding against one ",{"type":55,"tag":68,"props":90,"children":91},{},[92],{"type":61,"value":93},"validation criteria",{"type":61,"value":95}," skill — only\nfindings that pass get published to the pull request.",{"type":55,"tag":64,"props":97,"children":98},{},[99,101,108,110,115,117,123,125,130],{"type":61,"value":100},"All three kinds are team ",{"type":55,"tag":102,"props":103,"children":105},"code",{"className":104},[],[106],{"type":61,"value":107},"LLMSkill",{"type":61,"value":109}," rows the review agents pull over MCP at run time. PostHog ships\ncanonicals; this skill is the guide for authoring ",{"type":55,"tag":68,"props":111,"children":112},{},[113],{"type":61,"value":114},"custom",{"type":61,"value":116}," ones. The skill itself is team-level;\nwhether it ",{"type":55,"tag":118,"props":119,"children":120},"em",{},[121],{"type":61,"value":122},"runs",{"type":61,"value":124}," is a per-user setting in ",{"type":55,"tag":68,"props":126,"children":127},{},[128],{"type":61,"value":129},"Inbox → Code review",{"type":61,"value":131},".",{"type":55,"tag":133,"props":134,"children":135},"table",{},[136,165],{"type":55,"tag":137,"props":138,"children":139},"thead",{},[140],{"type":55,"tag":141,"props":142,"children":143},"tr",{},[144,150,155,160],{"type":55,"tag":145,"props":146,"children":147},"th",{},[148],{"type":61,"value":149},"Kind",{"type":55,"tag":145,"props":151,"children":152},{},[153],{"type":61,"value":154},"Name contract",{"type":55,"tag":145,"props":156,"children":157},{},[158],{"type":61,"value":159},"Cardinality per user",{"type":55,"tag":145,"props":161,"children":162},{},[163],{"type":61,"value":164},"Canonical example",{"type":55,"tag":166,"props":167,"children":168},"tbody",{},[169,201,232],{"type":55,"tag":141,"props":170,"children":171},{},[172,178,187,192],{"type":55,"tag":173,"props":174,"children":175},"td",{},[176],{"type":61,"value":177},"Review perspective",{"type":55,"tag":173,"props":179,"children":180},{},[181],{"type":55,"tag":102,"props":182,"children":184},{"className":183},[],[185],{"type":61,"value":186},"review-hog-perspective-\u003Cslug>",{"type":55,"tag":173,"props":188,"children":189},{},[190],{"type":61,"value":191},"Multi-enable, at least one stays on",{"type":55,"tag":173,"props":193,"children":194},{},[195],{"type":55,"tag":102,"props":196,"children":198},{"className":197},[],[199],{"type":61,"value":200},"review-hog-perspective-logic-correctness",{"type":55,"tag":141,"props":202,"children":203},{},[204,209,218,223],{"type":55,"tag":173,"props":205,"children":206},{},[207],{"type":61,"value":208},"Blind-spot check",{"type":55,"tag":173,"props":210,"children":211},{},[212],{"type":55,"tag":102,"props":213,"children":215},{"className":214},[],[216],{"type":61,"value":217},"review-hog-blind-spots-\u003Cslug>",{"type":55,"tag":173,"props":219,"children":220},{},[221],{"type":61,"value":222},"Exactly one active; selecting swaps",{"type":55,"tag":173,"props":224,"children":225},{},[226],{"type":55,"tag":102,"props":227,"children":229},{"className":228},[],[230],{"type":61,"value":231},"review-hog-blind-spots-general",{"type":55,"tag":141,"props":233,"children":234},{},[235,240,249,253],{"type":55,"tag":173,"props":236,"children":237},{},[238],{"type":61,"value":239},"Validation criteria",{"type":55,"tag":173,"props":241,"children":242},{},[243],{"type":55,"tag":102,"props":244,"children":246},{"className":245},[],[247],{"type":61,"value":248},"review-hog-validation-\u003Cslug>",{"type":55,"tag":173,"props":250,"children":251},{},[252],{"type":61,"value":222},{"type":55,"tag":173,"props":254,"children":255},{},[256],{"type":55,"tag":102,"props":257,"children":259},{"className":258},[],[260],{"type":61,"value":261},"review-hog-validation-criteria",{"type":55,"tag":263,"props":264,"children":266},"h2",{"id":265},"authoring-flow",[267],{"type":61,"value":268},"Authoring flow",{"type":55,"tag":270,"props":271,"children":272},"ol",{},[273,316,326,336,405],{"type":55,"tag":274,"props":275,"children":276},"li",{},[277,282,284,290,292,298,300,306,308,314],{"type":55,"tag":68,"props":278,"children":279},{},[280],{"type":61,"value":281},"Ground yourself.",{"type":61,"value":283}," Using the PostHog MCP skill tools, ",{"type":55,"tag":102,"props":285,"children":287},{"className":286},[],[288],{"type":61,"value":289},"skill-list",{"type":61,"value":291}," the team's ",{"type":55,"tag":102,"props":293,"children":295},{"className":294},[],[296],{"type":61,"value":297},"review-hog-*",{"type":61,"value":299},"\nskills and ",{"type":55,"tag":102,"props":301,"children":303},{"className":302},[],[304],{"type":61,"value":305},"skill-get",{"type":61,"value":307}," the canonical of the kind you're authoring (see the table above) — it is\nthe reference for structure and tone. For a perspective, skim the descriptions of every existing\n",{"type":55,"tag":102,"props":309,"children":311},{"className":310},[],[312],{"type":61,"value":313},"review-hog-perspective-*",{"type":61,"value":315}," so the new lens doesn't re-cover ground an enabled one already owns\n(overlap gets deduplicated later, but it wastes review passes).",{"type":55,"tag":274,"props":317,"children":318},{},[319,324],{"type":55,"tag":68,"props":320,"children":321},{},[322],{"type":61,"value":323},"Interview the user.",{"type":61,"value":325}," Ask what the skill should focus on, and offer a few concrete directions\nthe current set doesn't cover — grounded in what you saw in step 1 and, when useful, in the\nproject itself. Don't start writing until the direction is picked.",{"type":55,"tag":274,"props":327,"children":328},{},[329,334],{"type":55,"tag":68,"props":330,"children":331},{},[332],{"type":61,"value":333},"Draft the body",{"type":61,"value":335}," following the per-kind guidance below. Keep it a focused instruction set the\nreview agent can apply to one chunk in one pass — not an essay.",{"type":55,"tag":274,"props":337,"children":338},{},[339,350,352,357,359,365,367,372,374,380,382,387,389,395,397,403],{"type":55,"tag":68,"props":340,"children":341},{},[342,344],{"type":61,"value":343},"Create the skill yourself with ",{"type":55,"tag":102,"props":345,"children":347},{"className":346},[],[348],{"type":61,"value":349},"posthog:skill-create",{"type":61,"value":351}," — actually create the team ",{"type":55,"tag":102,"props":353,"children":355},{"className":354},[],[356],{"type":61,"value":107},{"type":61,"value":358},"\nrow; never hand the user a body to copy-paste. Pass the exact name per the contract above\n(lowercase slug), a one-paragraph ",{"type":55,"tag":102,"props":360,"children":362},{"className":361},[],[363],{"type":61,"value":364},"description",{"type":61,"value":366}," of what the lens\u002Fsweep\u002Fbar is, and the body.\n",{"type":55,"tag":68,"props":368,"children":369},{},[370],{"type":61,"value":371},"The name prefix is the whole identity",{"type":61,"value":373}," — it is how the Code review tab and the review runs\ndiscover the skill. There is no ",{"type":55,"tag":102,"props":375,"children":377},{"className":376},[],[378],{"type":61,"value":379},"category",{"type":61,"value":381}," parameter on the skill tools and you don't need one:\nthe backend stamps the ",{"type":55,"tag":102,"props":383,"children":385},{"className":384},[],[386],{"type":61,"value":49},{"type":61,"value":388}," grouping category itself (it only affects grouping on the\nSkills page) — do not spend turns trying to set or verify it. Iterate with\n",{"type":55,"tag":102,"props":390,"children":392},{"className":391},[],[393],{"type":61,"value":394},"posthog:skill-update",{"type":61,"value":396}," if the user wants changes. Author fresh — don't ",{"type":55,"tag":102,"props":398,"children":400},{"className":399},[],[401],{"type":61,"value":402},"skill-duplicate",{"type":61,"value":404}," a\ncanonical to edit: seeded metadata rides along with the copy, and the canonical sync may\noverwrite or prune it.",{"type":55,"tag":274,"props":406,"children":407},{},[408,413,415],{"type":55,"tag":68,"props":409,"children":410},{},[411],{"type":61,"value":412},"Tell the user how to activate it.",{"type":61,"value":414}," A custom skill starts inactive for them:\n",{"type":55,"tag":416,"props":417,"children":418},"ul",{},[419,429],{"type":55,"tag":274,"props":420,"children":421},{},[422,427],{"type":55,"tag":68,"props":423,"children":424},{},[425],{"type":61,"value":426},"Perspective",{"type":61,"value":428}," — toggle it on under Inbox → Code review → Perspectives (it appears disabled\nuntil they enable it; at least one perspective must stay on).",{"type":55,"tag":274,"props":430,"children":431},{},[432,437,439,444],{"type":55,"tag":68,"props":433,"children":434},{},[435],{"type":61,"value":436},"Blind-spot check \u002F validation criteria",{"type":61,"value":438}," — select it under the matching section; exactly one\nruns at a time, so selecting it swaps out the current one ",{"type":55,"tag":68,"props":440,"children":441},{},[442],{"type":61,"value":443},"for their reviews only",{"type":61,"value":445},".\nReviews pin skill versions when a run starts, so an edit mid-review applies from the next run.",{"type":55,"tag":263,"props":447,"children":449},{"id":448},"writing-a-review-perspective",[450],{"type":61,"value":451},"Writing a review perspective",{"type":55,"tag":64,"props":453,"children":454},{},[455],{"type":61,"value":456},"The body instructs one specialist review pass over one PR chunk. Match the canonical\nlogic-correctness skill's shape:",{"type":55,"tag":416,"props":458,"children":459},{},[460,470,480,490],{"type":55,"tag":274,"props":461,"children":462},{},[463,468],{"type":55,"tag":68,"props":464,"children":465},{},[466],{"type":61,"value":467},"The lane",{"type":61,"value":469}," — one sentence on what this lens is responsible for; report everything in lane and\nleave the rest to the other perspectives.",{"type":55,"tag":274,"props":471,"children":472},{},[473,478],{"type":55,"tag":68,"props":474,"children":475},{},[476],{"type":61,"value":477},"Hunting grounds",{"type":61,"value":479}," — a numbered handful of concrete places to look, each a specific check the\nagent can walk against the chunk (\"transaction boundaries that split writes that must land\ntogether\"), not an abstract virtue (\"ensure correctness\").",{"type":55,"tag":274,"props":481,"children":482},{},[483,488],{"type":55,"tag":68,"props":484,"children":485},{},[486],{"type":61,"value":487},"Lane boundary",{"type":61,"value":489}," — which perspective owns each adjacent concern this lens must leave alone.",{"type":55,"tag":274,"props":491,"children":492},{},[493,498],{"type":55,"tag":68,"props":494,"children":495},{},[496],{"type":61,"value":497},"The finding bar",{"type":61,"value":499}," — a publishable finding names the concrete trigger and the concrete\nconsequence; close with a completion criterion (\"done when every changed file is flagged or\ncleared against every hunting ground\").",{"type":55,"tag":64,"props":501,"children":502},{},[503],{"type":61,"value":504},"The review harness already tells the agent the pipeline mechanics — parallel perspectives, later\ndeduplication, severity levels, the non-test-files rule — so the skill carries only the lens;\nrestating harness rules dilutes it.",{"type":55,"tag":263,"props":506,"children":508},{"id":507},"writing-a-blind-spot-check",[509],{"type":61,"value":510},"Writing a blind-spot check",{"type":55,"tag":64,"props":512,"children":513},{},[514,516,521],{"type":61,"value":515},"The body instructs the final sweep that runs after every enabled perspective finished a chunk. It\nis ",{"type":55,"tag":68,"props":517,"children":518},{},[519],{"type":61,"value":520},"conditioned on the covered findings",{"type":61,"value":522}," (the prompt lists which perspectives ran and what they\nfound), so the body should say how to use that: the covered findings map where attention already\nwent, and the sweep's value is the negative space — error paths, unhandled inputs, cross-file\ninteractions, assumptions. It is not scoped to one specialty, and an empty result beats padding. A\ncustom sweep narrows or re-weights this hunt (e.g. toward a domain the team keeps getting burned\nby).",{"type":55,"tag":263,"props":524,"children":526},{"id":525},"writing-validation-criteria",[527],{"type":61,"value":528},"Writing validation criteria",{"type":55,"tag":64,"props":530,"children":531},{},[532],{"type":61,"value":533},"The body defines the keep\u002Fdrop bar every candidate finding is judged against before publishing.\nPrecision over recall is the house default — a reviewer that raises noise gets muted — so define:\nwhat makes a finding real and worth an author's attention (user-affecting correctness, security,\ndata loss, contract breaks, performance), what gets dropped (overengineering, speculation,\ndefensive paranoia, unreachable edges, style), and how to treat genuine uncertainty (default:\ndrop). A custom bar shifts strictness or re-weights concerns; it should still demand evidence from\nthe live codebase, not vibes.",{"items":535,"total":704},[536,552,564,576,589,604,620,637,651,666,676,694],{"slug":537,"name":537,"fn":538,"description":539,"org":540,"tags":541,"stars":20,"repoUrl":21,"updatedAt":551},"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},[542,544,547,550],{"name":543,"slug":28,"type":13},"Analytics",{"name":545,"slug":546,"type":13},"Cost Optimization","cost-optimization",{"name":548,"slug":549,"type":13},"Observability","observability",{"name":9,"slug":8,"type":13},"2026-07-28T05:34:11.117757",{"slug":553,"name":553,"fn":554,"description":555,"org":556,"tags":557,"stars":20,"repoUrl":21,"updatedAt":563},"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},[558,559,562],{"name":543,"slug":28,"type":13},{"name":560,"slug":561,"type":13},"Audit","audit",{"name":9,"slug":8,"type":13},"2026-06-08T08:08:33.693989",{"slug":565,"name":565,"fn":566,"description":567,"org":568,"tags":569,"stars":20,"repoUrl":21,"updatedAt":575},"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},[570,571,573,574],{"name":560,"slug":561,"type":13},{"name":572,"slug":30,"type":13},"Data Warehouse",{"name":548,"slug":549,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:22:57.67984",{"slug":577,"name":577,"fn":578,"description":579,"org":580,"tags":581,"stars":20,"repoUrl":21,"updatedAt":588},"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},[582,583,584,587],{"name":560,"slug":561,"type":13},{"name":572,"slug":30,"type":13},{"name":585,"slug":586,"type":13},"Performance","performance",{"name":9,"slug":8,"type":13},"2026-06-18T08:25:10.936787",{"slug":590,"name":590,"fn":591,"description":592,"org":593,"tags":594,"stars":20,"repoUrl":21,"updatedAt":603},"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},[595,598,601,602],{"name":596,"slug":597,"type":13},"Alerting","alerting",{"name":599,"slug":600,"type":13},"Debugging","debugging",{"name":548,"slug":549,"type":13},{"name":9,"slug":8,"type":13},"2026-06-18T08:24:40.318583",{"slug":605,"name":605,"fn":606,"description":607,"org":608,"tags":609,"stars":20,"repoUrl":21,"updatedAt":619},"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},[610,611,614,615,618],{"name":543,"slug":28,"type":13},{"name":612,"slug":613,"type":13},"Monitoring","monitoring",{"name":548,"slug":549,"type":13},{"name":616,"slug":617,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-18T05:10:54.430898",{"slug":621,"name":621,"fn":622,"description":623,"org":624,"tags":625,"stars":20,"repoUrl":21,"updatedAt":636},"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},[626,629,632,633],{"name":627,"slug":628,"type":13},"Automation","automation",{"name":630,"slug":631,"type":13},"MCP","mcp",{"name":9,"slug":8,"type":13},{"name":634,"slug":635,"type":13},"Workflow Automation","workflow-automation","2026-07-28T05:34:12.167015",{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":20,"repoUrl":21,"updatedAt":650},"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},[643,644,645,648,649],{"name":543,"slug":28,"type":13},{"name":599,"slug":600,"type":13},{"name":646,"slug":647,"type":13},"Frontend","frontend",{"name":548,"slug":549,"type":13},{"name":9,"slug":8,"type":13},"2026-05-07T05:56:19.828048",{"slug":652,"name":652,"fn":653,"description":654,"org":655,"tags":656,"stars":20,"repoUrl":21,"updatedAt":665},"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},[657,660,661,662],{"name":658,"slug":659,"type":13},"API Development","api-development",{"name":646,"slug":647,"type":13},{"name":9,"slug":8,"type":13},{"name":663,"slug":664,"type":13},"SDK","sdk","2026-06-08T08:08:34.929454",{"slug":667,"name":667,"fn":668,"description":669,"org":670,"tags":671,"stars":20,"repoUrl":21,"updatedAt":675},"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},[672,673,674],{"name":658,"slug":659,"type":13},{"name":616,"slug":617,"type":13},{"name":9,"slug":8,"type":13},"2026-07-15T05:29:58.442727",{"slug":677,"name":677,"fn":678,"description":679,"org":680,"tags":681,"stars":20,"repoUrl":21,"updatedAt":693},"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},[682,683,686,687,690],{"name":627,"slug":628,"type":13},{"name":684,"slug":685,"type":13},"Email","email",{"name":9,"slug":8,"type":13},{"name":688,"slug":689,"type":13},"Reporting","reporting",{"name":691,"slug":692,"type":13},"Slack","slack","2026-06-09T07:32:27.935712",{"slug":695,"name":695,"fn":696,"description":697,"org":698,"tags":699,"stars":20,"repoUrl":21,"updatedAt":703},"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},[700,701,702],{"name":543,"slug":28,"type":13},{"name":658,"slug":659,"type":13},{"name":9,"slug":8,"type":13},"2026-06-08T08:08:29.624498",231,{"items":706,"total":756},[707,714,720,727,734,741,749],{"slug":537,"name":537,"fn":538,"description":539,"org":708,"tags":709,"stars":20,"repoUrl":21,"updatedAt":551},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[710,711,712,713],{"name":543,"slug":28,"type":13},{"name":545,"slug":546,"type":13},{"name":548,"slug":549,"type":13},{"name":9,"slug":8,"type":13},{"slug":553,"name":553,"fn":554,"description":555,"org":715,"tags":716,"stars":20,"repoUrl":21,"updatedAt":563},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[717,718,719],{"name":543,"slug":28,"type":13},{"name":560,"slug":561,"type":13},{"name":9,"slug":8,"type":13},{"slug":565,"name":565,"fn":566,"description":567,"org":721,"tags":722,"stars":20,"repoUrl":21,"updatedAt":575},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[723,724,725,726],{"name":560,"slug":561,"type":13},{"name":572,"slug":30,"type":13},{"name":548,"slug":549,"type":13},{"name":9,"slug":8,"type":13},{"slug":577,"name":577,"fn":578,"description":579,"org":728,"tags":729,"stars":20,"repoUrl":21,"updatedAt":588},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[730,731,732,733],{"name":560,"slug":561,"type":13},{"name":572,"slug":30,"type":13},{"name":585,"slug":586,"type":13},{"name":9,"slug":8,"type":13},{"slug":590,"name":590,"fn":591,"description":592,"org":735,"tags":736,"stars":20,"repoUrl":21,"updatedAt":603},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[737,738,739,740],{"name":596,"slug":597,"type":13},{"name":599,"slug":600,"type":13},{"name":548,"slug":549,"type":13},{"name":9,"slug":8,"type":13},{"slug":605,"name":605,"fn":606,"description":607,"org":742,"tags":743,"stars":20,"repoUrl":21,"updatedAt":619},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[744,745,746,747,748],{"name":543,"slug":28,"type":13},{"name":612,"slug":613,"type":13},{"name":548,"slug":549,"type":13},{"name":616,"slug":617,"type":13},{"name":9,"slug":8,"type":13},{"slug":621,"name":621,"fn":622,"description":623,"org":750,"tags":751,"stars":20,"repoUrl":21,"updatedAt":636},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[752,753,754,755],{"name":627,"slug":628,"type":13},{"name":630,"slug":631,"type":13},{"name":9,"slug":8,"type":13},{"name":634,"slug":635,"type":13},61]