[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-posthog-signals-scout-your-scout":3,"mdc-gpvnue-key":39,"related-org-posthog-signals-scout-your-scout":249,"related-repo-posthog-signals-scout-your-scout":427},{"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":34,"sourceUrl":37,"mdContent":38},"signals-scout-your-scout","configure PostHog signal scouts","What this scout watches and the condition under which it files a report.\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],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Monitoring","monitoring",{"name":21,"slug":22,"type":15},"Automation","automation",1091,"https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog.com","2026-08-10T04:45:49.295902",null,856,[29,30,31,32,8,33],"design","docs","gatsby","handbook","tailwindcss",{"repoUrl":24,"stars":23,"forks":27,"topics":35,"description":36},[29,30,31,32,8,33],"Official docs, website, and handbook for PostHog.","https:\u002F\u002Fgithub.com\u002FPostHog\u002Fposthog.com\u002Ftree\u002FHEAD\u002Fcontents\u002Fpocket-guides\u002Fself-driving\u002F_starter","---\n# The scout itself. This is a real SKILL.md – the same shape as the canonical scouts in\n# the monorepo under `products\u002Fsignals\u002Fskills\u002Fsignals-scout-*\u002FSKILL.md`, so you can paste\n# one in here or lift this one out without reformatting anything.\n#\n# `name` MUST match `signals-scout-\u003Ckebab-case>` or the harness never runs it.\nname: signals-scout-your-scout\n\n# Doubles as the description on the scout config API, and prefills the deep link. One\n# or two lines: what it watches, and what makes it file.\ndescription: >\n  What this scout watches and the condition under which it files a report.\n\n# What puts the scout on the report channel. Every scout needs both – without them it\n# falls back to a deprecated legacy signal-emitting channel and can't write reports.\nallowed_tools:\n  - emit_report\n  - edit_report\n---\n\n# Your scout's title\n\nOne line on what it watches. Everything below is the agent's instructions, executed on\nevery run, so write it in the second person to the agent – not to the reader.\n\nSay how this relates to the canonical fleet. Most scouts you write will be a narrower\nversion of an existing one, and saying which saves a reader from running both. Check\n`products\u002Fsignals\u002Fskills\u002F` in the monorepo before you assume yours is new.\n\nIf your `schedule` in index.mdx isn't the fleet default of daily, justify it here in one\nline.\n\n## Discriminator\n\nThe rule that decides whether a run files a report or writes nothing. Be specific enough\nthat two different agents would reach the same verdict on the same data.\n\nPrefer a **rate** over a raw count. A threshold on a count always needs a human to ask\n\"but did traffic move?\", which is why those alerts get muted. A threshold on a normalized\nrate answers that question itself – which is what lets the agent decide alone. Pick your\ndenominator before you pick your threshold.\n\n### The bar\n\nGive a concrete starting threshold, and say it's meant to be tuned:\n\n- the numeric condition, on a **complete** bucket – a partial bucket reads as a spike\n  every time, and\n- a **volume floor**, below which the number is noise.\n\nThe volume floor usually matters more than the threshold.\n\n## Explore\n\nNumbered steps the agent works through. Order them by likelihood, cheapest first.\n\n1. **Rule out the instrumentation.** Broken tracking looks identical to a broken product\n   in almost every scout. Check this before anything else.\n2. **Rule out the innocent explanation.** Whatever your discriminator's quiet case is,\n   this is where the agent confirms it doesn't apply.\n3. **Find the cause.** A report that says a number moved, with no cause attached, is\n   something the reader still has to go investigate themselves.\n4. **Tie it to a deploy** where one sits in the window, and include the commit range.\n\n## Disqualifiers\n\nThe explicit list of \"don't file for this\". Every false positive you can think of goes\nhere – this list is what keeps the inbox worth reading.\n\n- The innocent explanation from your discriminator's quiet case.\n- Anything deliberate and announced.\n- Anything below the volume floor.\n- Not enough history to have a stable norm yet.\n",{"data":40,"body":44},{"name":4,"description":6,"allowed_tools":41},[42,43],"emit_report","edit_report",{"type":45,"children":46},"root",[47,56,62,76,89,96,101,114,121,126,155,160,166,171,215,221,226],{"type":48,"tag":49,"props":50,"children":52},"element","h1",{"id":51},"your-scouts-title",[53],{"type":54,"value":55},"text","Your scout's title",{"type":48,"tag":57,"props":58,"children":59},"p",{},[60],{"type":54,"value":61},"One line on what it watches. Everything below is the agent's instructions, executed on\nevery run, so write it in the second person to the agent – not to the reader.",{"type":48,"tag":57,"props":63,"children":64},{},[65,67,74],{"type":54,"value":66},"Say how this relates to the canonical fleet. Most scouts you write will be a narrower\nversion of an existing one, and saying which saves a reader from running both. Check\n",{"type":48,"tag":68,"props":69,"children":71},"code",{"className":70},[],[72],{"type":54,"value":73},"products\u002Fsignals\u002Fskills\u002F",{"type":54,"value":75}," in the monorepo before you assume yours is new.",{"type":48,"tag":57,"props":77,"children":78},{},[79,81,87],{"type":54,"value":80},"If your ",{"type":48,"tag":68,"props":82,"children":84},{"className":83},[],[85],{"type":54,"value":86},"schedule",{"type":54,"value":88}," in index.mdx isn't the fleet default of daily, justify it here in one\nline.",{"type":48,"tag":90,"props":91,"children":93},"h2",{"id":92},"discriminator",[94],{"type":54,"value":95},"Discriminator",{"type":48,"tag":57,"props":97,"children":98},{},[99],{"type":54,"value":100},"The rule that decides whether a run files a report or writes nothing. Be specific enough\nthat two different agents would reach the same verdict on the same data.",{"type":48,"tag":57,"props":102,"children":103},{},[104,106,112],{"type":54,"value":105},"Prefer a ",{"type":48,"tag":107,"props":108,"children":109},"strong",{},[110],{"type":54,"value":111},"rate",{"type":54,"value":113}," over a raw count. A threshold on a count always needs a human to ask\n\"but did traffic move?\", which is why those alerts get muted. A threshold on a normalized\nrate answers that question itself – which is what lets the agent decide alone. Pick your\ndenominator before you pick your threshold.",{"type":48,"tag":115,"props":116,"children":118},"h3",{"id":117},"the-bar",[119],{"type":54,"value":120},"The bar",{"type":48,"tag":57,"props":122,"children":123},{},[124],{"type":54,"value":125},"Give a concrete starting threshold, and say it's meant to be tuned:",{"type":48,"tag":127,"props":128,"children":129},"ul",{},[130,143],{"type":48,"tag":131,"props":132,"children":133},"li",{},[134,136,141],{"type":54,"value":135},"the numeric condition, on a ",{"type":48,"tag":107,"props":137,"children":138},{},[139],{"type":54,"value":140},"complete",{"type":54,"value":142}," bucket – a partial bucket reads as a spike\nevery time, and",{"type":48,"tag":131,"props":144,"children":145},{},[146,148,153],{"type":54,"value":147},"a ",{"type":48,"tag":107,"props":149,"children":150},{},[151],{"type":54,"value":152},"volume floor",{"type":54,"value":154},", below which the number is noise.",{"type":48,"tag":57,"props":156,"children":157},{},[158],{"type":54,"value":159},"The volume floor usually matters more than the threshold.",{"type":48,"tag":90,"props":161,"children":163},{"id":162},"explore",[164],{"type":54,"value":165},"Explore",{"type":48,"tag":57,"props":167,"children":168},{},[169],{"type":54,"value":170},"Numbered steps the agent works through. Order them by likelihood, cheapest first.",{"type":48,"tag":172,"props":173,"children":174},"ol",{},[175,185,195,205],{"type":48,"tag":131,"props":176,"children":177},{},[178,183],{"type":48,"tag":107,"props":179,"children":180},{},[181],{"type":54,"value":182},"Rule out the instrumentation.",{"type":54,"value":184}," Broken tracking looks identical to a broken product\nin almost every scout. Check this before anything else.",{"type":48,"tag":131,"props":186,"children":187},{},[188,193],{"type":48,"tag":107,"props":189,"children":190},{},[191],{"type":54,"value":192},"Rule out the innocent explanation.",{"type":54,"value":194}," Whatever your discriminator's quiet case is,\nthis is where the agent confirms it doesn't apply.",{"type":48,"tag":131,"props":196,"children":197},{},[198,203],{"type":48,"tag":107,"props":199,"children":200},{},[201],{"type":54,"value":202},"Find the cause.",{"type":54,"value":204}," A report that says a number moved, with no cause attached, is\nsomething the reader still has to go investigate themselves.",{"type":48,"tag":131,"props":206,"children":207},{},[208,213],{"type":48,"tag":107,"props":209,"children":210},{},[211],{"type":54,"value":212},"Tie it to a deploy",{"type":54,"value":214}," where one sits in the window, and include the commit range.",{"type":48,"tag":90,"props":216,"children":218},{"id":217},"disqualifiers",[219],{"type":54,"value":220},"Disqualifiers",{"type":48,"tag":57,"props":222,"children":223},{},[224],{"type":54,"value":225},"The explicit list of \"don't file for this\". Every false positive you can think of goes\nhere – this list is what keeps the inbox worth reading.",{"type":48,"tag":127,"props":227,"children":228},{},[229,234,239,244],{"type":48,"tag":131,"props":230,"children":231},{},[232],{"type":54,"value":233},"The innocent explanation from your discriminator's quiet case.",{"type":48,"tag":131,"props":235,"children":236},{},[237],{"type":54,"value":238},"Anything deliberate and announced.",{"type":48,"tag":131,"props":240,"children":241},{},[242],{"type":54,"value":243},"Anything below the volume floor.",{"type":48,"tag":131,"props":245,"children":246},{},[247],{"type":54,"value":248},"Not enough history to have a stable norm yet.",{"items":250,"total":426},[251,268,280,293,306,321,335,349,367,384,399,411],{"slug":252,"name":252,"fn":253,"description":254,"org":255,"tags":256,"stars":265,"repoUrl":266,"updatedAt":267},"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},[257,260,263,264],{"name":258,"slug":259,"type":15},"Analytics","analytics",{"name":261,"slug":262,"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","2026-08-10T04:16:25.279222",{"slug":269,"name":269,"fn":270,"description":271,"org":272,"tags":273,"stars":265,"repoUrl":266,"updatedAt":279},"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},[274,275,278],{"name":258,"slug":259,"type":15},{"name":276,"slug":277,"type":15},"Audit","audit",{"name":9,"slug":8,"type":15},"2026-06-08T08:08:33.693989",{"slug":281,"name":281,"fn":282,"description":283,"org":284,"tags":285,"stars":265,"repoUrl":266,"updatedAt":292},"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},[286,287,290,291],{"name":276,"slug":277,"type":15},{"name":288,"slug":289,"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":294,"name":294,"fn":295,"description":296,"org":297,"tags":298,"stars":265,"repoUrl":266,"updatedAt":305},"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},[299,300,301,304],{"name":276,"slug":277,"type":15},{"name":288,"slug":289,"type":15},{"name":302,"slug":303,"type":15},"Performance","performance",{"name":9,"slug":8,"type":15},"2026-06-18T08:25:10.936787",{"slug":307,"name":307,"fn":308,"description":309,"org":310,"tags":311,"stars":265,"repoUrl":266,"updatedAt":320},"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},[312,315,318,319],{"name":313,"slug":314,"type":15},"Alerting","alerting",{"name":316,"slug":317,"type":15},"Debugging","debugging",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-06-18T08:24:40.318583",{"slug":322,"name":322,"fn":323,"description":324,"org":325,"tags":326,"stars":265,"repoUrl":266,"updatedAt":334},"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},[327,328,329,330,333],{"name":258,"slug":259,"type":15},{"name":18,"slug":19,"type":15},{"name":13,"slug":14,"type":15},{"name":331,"slug":332,"type":15},"Operations","operations",{"name":9,"slug":8,"type":15},"2026-07-18T05:10:54.430898",{"slug":336,"name":336,"fn":337,"description":338,"org":339,"tags":340,"stars":265,"repoUrl":266,"updatedAt":348},"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},[341,342,344,345],{"name":21,"slug":22,"type":15},{"name":343,"slug":29,"type":15},"Design",{"name":9,"slug":8,"type":15},{"name":346,"slug":347,"type":15},"Prototyping","prototyping","2026-08-06T06:09:29.946969",{"slug":350,"name":350,"fn":351,"description":352,"org":353,"tags":354,"stars":265,"repoUrl":266,"updatedAt":366},"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},[355,358,359,362,365],{"name":356,"slug":357,"type":15},"CSS","css",{"name":343,"slug":29,"type":15},{"name":360,"slug":361,"type":15},"Graphics","graphics",{"name":363,"slug":364,"type":15},"HTML","html",{"name":9,"slug":8,"type":15},"2026-08-06T06:09:30.313848",{"slug":368,"name":368,"fn":369,"description":370,"org":371,"tags":372,"stars":265,"repoUrl":266,"updatedAt":383},"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},[373,374,377,380],{"name":343,"slug":29,"type":15},{"name":375,"slug":376,"type":15},"Frontend","frontend",{"name":378,"slug":379,"type":15},"React","react",{"name":381,"slug":382,"type":15},"UI Components","ui-components","2026-08-06T06:09:18.633724",{"slug":385,"name":385,"fn":386,"description":387,"org":388,"tags":389,"stars":265,"repoUrl":266,"updatedAt":398},"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},[390,391,394,395],{"name":21,"slug":22,"type":15},{"name":392,"slug":393,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},{"name":396,"slug":397,"type":15},"Workflow Automation","workflow-automation","2026-08-10T04:16:26.294119",{"slug":400,"name":400,"fn":401,"description":402,"org":403,"tags":404,"stars":265,"repoUrl":266,"updatedAt":410},"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},[405,406,407,408,409],{"name":258,"slug":259,"type":15},{"name":316,"slug":317,"type":15},{"name":375,"slug":376,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-05-07T05:56:19.828048",{"slug":412,"name":412,"fn":413,"description":414,"org":415,"tags":416,"stars":265,"repoUrl":266,"updatedAt":425},"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},[417,420,421,422],{"name":418,"slug":419,"type":15},"API Development","api-development",{"name":375,"slug":376,"type":15},{"name":9,"slug":8,"type":15},{"name":423,"slug":424,"type":15},"SDK","sdk","2026-06-08T08:08:34.929454",248,{"items":428,"total":476},[429,443,458,469],{"slug":430,"name":430,"fn":431,"description":432,"org":433,"tags":434,"stars":23,"repoUrl":24,"updatedAt":442},"signals-scout-ai-cost","monitor AI feature costs and performance","Watches cost per conversation for AI features and reports when it breaks from its recent norm while volume holds steady, attributing the change to a model, prompt, cache, or retry cause.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[435,436,439,440,441],{"name":261,"slug":262,"type":15},{"name":437,"slug":438,"type":15},"LLM","llm",{"name":18,"slug":19,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-08-10T04:45:48.936016",{"slug":444,"name":444,"fn":445,"description":446,"org":447,"tags":448,"stars":23,"repoUrl":24,"updatedAt":457},"signals-scout-flag-debt","identify and remove stale feature flags","Finds feature flags whose decision is over but which are still evaluated in production – terminal rollouts left in place, or keys that no longer appear in any connected repo.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[449,452,453,454],{"name":450,"slug":451,"type":15},"Feature Flags","feature-flags",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":455,"slug":456,"type":15},"Tech Debt","tech-debt","2026-08-10T04:45:50.019808",{"slug":459,"name":459,"fn":460,"description":461,"org":462,"tags":463,"stars":23,"repoUrl":24,"updatedAt":468},"signals-scout-silent-failure","detect and diagnose silent application failures","Watches the completion rate of one named core action for breaks from its own norm, and reports the likely cause – with swallowed exceptions as the first thing it looks for.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[464,465,466,467],{"name":316,"slug":317,"type":15},{"name":18,"slug":19,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-08-10T04:45:56.482808",{"slug":4,"name":4,"fn":5,"description":6,"org":470,"tags":471,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[472,473,474,475],{"name":21,"slug":22,"type":15},{"name":18,"slug":19,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},4]