posthog/ai-plugin

creating-box-plot-insights

- Creates product analytics or SQL-backed box plot insights in PostHog.

소스 보기

사용 방법

  1. 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
  2. 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
  3. 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/posthog/ai-plugin --skill creating-box-plot-insights

시작 전 확인

  • 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
  • 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Creating box plot insights

Box plots need distribution data, not an already-aggregated average or total. Choose the simplest query type that can express the user's question.

Choose the query type

Use a standard product analytics box plot when all of these are true:

  • The source is an event, action, or warehouse table supported by Trends.
  • One numeric property contains the values to distribute.
  • The user wants the distribution over a normal time interval.

Use a SQL box plot when the user needs custom grouping, joins, derived values, or bespoke SQL. Read querying-posthog-data before writing HogQL, then use references/sql-examples.md as a starting point.

Do not use SQL only to reproduce a standard Trends query.

Standard product analytics box plot

  1. Identify the event or action and its numeric property. Confirm the property is numeric before saving.
  2. Build an InsightVizNode whose source is a TrendsQuery:
  • Set the series event or action.
  • Set math_property to the numeric property.
  • Set trendsFilter.display to BoxPlot.
  • Choose the date range and interval that match the question.
  1. Run the query with posthog:query-trends.
  2. If it returns distribution rows, save it with posthog:insight-create.
  3. Read it back with posthog:insight-get and confirm the property, interval, and display.

A box plot without a numeric math_property is invalid. Do not substitute event counts unless counts are the values the user wants to distribute.

SQL box plot

The SQL must return one pre-aggregated row for each X-axis and series pair. Calculate the summary in the database. Never calculate percentiles from the limited result rows in the client.

Required numeric roles:

  • minimum
  • 25th percentile
  • median
  • mean
  • 75th percentile
  • maximum

The easiest result shape uses these aliases:

text
x, series, min, p25, median, mean, p75, max

x and series are optional:

  • Set xAxisColumn to null for one overall distribution or one box per series.
  • Set seriesColumn to null for one series.

Validate the HogQL with posthog:execute-sql before saving. Check that:

  • Every required statistic is numeric.
  • min <= p25 <= median <= p75 <= max for every row.
  • The mean is between the minimum and maximum.
  • Each X-axis and series pair appears once.
  • There are at most 200 series and 10,000 X-axis by series cells.

Then save this shape with posthog:insight-create:

json
{
  "query": {
    "kind": "DataVisualizationNode",
    "source": {
      "kind": "HogQLQuery",
      "query": "<validated HogQL>"
    },
    "display": "BoxPlot",
    "chartSettings": {
      "boxPlot": {
        "xAxisColumn": "x",
        "seriesColumn": "series",
        "minColumn": "min",
        "p25Column": "p25",
        "medianColumn": "median",
        "meanColumn": "mean",
        "p75Column": "p75",
        "maxColumn": "max",
        "excludeOutliers": true
      }
    }
  }
}

Use the actual aliases when the query uses different names. Do not map the six statistics as six Y-axis series.

Verify the saved insight

  1. Read the saved insight with posthog:insight-get.
  2. Run it with posthog:insight-query.
  3. Confirm the result still has the expected columns and one row per box.
  4. Report the insight link, the numeric value being distributed, and the grouping choices.

If an individual row has a missing or invalid summary, PostHog omits that box while keeping valid boxes visible. Fix the SQL when omitted boxes are not expected.

Related skills

  • querying-posthog-data - required before authoring or changing the HogQL for a SQL box plot.
  • formatting-insight-axes - use when the value axis needs currency, duration, percentage, or other formatting.
  • building-a-dashboard - use when the box plot should be placed with other insights on a dashboard.

관련 작업

같은 저장소의 Skills

더 많은 Skills

모든 Skills
posthog
공식

exploring-llm-costs

Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.

1시간 설치 수
2
GitHub Stars
98
업데이트
11월 6일
posthog
공식

exploring-llm-traces

Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/ or /ai-observability/sessions/ ), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against events.properties.$aiinput / $aioutputchoices returns empty — message

1시간 설치 수
2
GitHub Stars
98
업데이트
11월 6일
posthog
공식

instrument-integration

Add PostHog SDK integration to your application. Use when setting up PostHog for the first time or reviewing PRs that need PostHog initialization. Covers SDK installation, provider setup, and basic configuration for any framework.

1시간 설치 수
2
GitHub Stars
98
업데이트
11월 6일
posthog
공식

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (/error-tracking/ ) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next step should be. Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary in one pass.

1시간 설치 수
2
GitHub Stars
98
업데이트
11월 6일