creating-box-plot-insights

Draws a box plot in PostHog — a chart showing how a number is spread out, from lowest through typical to highest, rather than just its average.

WHEN TO USE

SCOPE

USE FOR

Chart how a tracked numeric value is spread out across each day or week of a date range.
Build a box plot from custom SQL when you need joins, derived values or your own grouping.
Show one box per group side by side so their spreads can be compared.
Save the chart as an insight and confirm it reads back with the right value and grouping.

This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.

In this document (6)

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

Identify the event or action and its numeric property. Confirm the property is numeric before saving.
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.
Run the query with posthog:query-trends.
If it returns distribution rows, save it with posthog:insight-create.
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:

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:

{
  "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

Read the saved insight with posthog:insight-get.
Run it with posthog:insight-query.
Confirm the result still has the expected columns and one row per box.
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.

This skill ships inside the PostHog AI Plugin. Listed package contents include 3 slash commands, 1 agent, hooks and an MCP server. Installed components and skill versions may vary by AI tool.

Install just this skill

Run this outside your AI tool, using Node.js 22.20.0 or newer. Skills CLI 1.7.2 skips skill selection; prompts cancel installation without an interactive terminal. If choosing Project when asked about installation scope, open your project's folder before running this.

Install checklist

Check selected tools if a picker appears; Claude Code may be unchecked under Additional agents. ↑/↓ moves, Space toggles selections, Enter confirms.
Without a tool picker, check Installing to: for your intended tool. Stop if it names a different tool.
If asked, choose Symlink (Recommended) for shared files or Copy to all agents for separate copies; review the summary before confirming installation.
Install the find-skills skill? defaults to Yes, adding another skill for all projects. Choose No if you don't want that extra installation.

Skills CLI 1.7.2 sends install data to skills.sh by default, including the source, skill names, target tools and file details; GitHub sources are reported only when GitHub confirms the repository is public, while other remote sources can also be reported. Confirmed-public GitHub sources also trigger a security-audit request. Before installing, set the environment variable DO_NOT_TRACK=1 or DISABLE_TELEMETRY=1 to disable both.

npx skills add posthog/ai-plugin --skill "creating-box-plot-insights" --full-depth

After installing for Claude Code, open it in the installation project if you chose Project; Global makes the skill available across projects on this computer. Once Claude Code loads the skill, its description helps Claude decide when to use it.

If installation created a top-level skills folder that did not exist when your Claude Code session started, run /reload-skills in that session. Run it again after later changes in that folder.

MCP server required

The skill's steps call for tools from the PostHog MCP server. Installing just this skill doesn't add that connection; set it up in your AI tool if it isn't there yet: PostHog MCP setup. Installing the whole plugin instead includes the connection settings.

Requirements for the PostHog MCP server

Connecting is free; sign in with your PostHog account.
Some tools use AI internally and may incur PostHog AI charges. Those tools require AI data processing to be enabled in your organization settings.

Install the whole plugin

This route installs the posthog plugin package selected for your AI tool.

Claude Code

Add PostHog's marketplace, then install the plugin

Run both lines in a terminal. They install PostHog's posthog plugin: this skill, PostHog's other skills, and a connection to PostHog's hosted MCP server.

claude plugin marketplace add PostHog/ai-plugin

02
```
claude plugin install posthog@posthog
```

Installation and loading

The plugin installs for you in every project and loads the next time you start Claude Code, or after /reload-plugins in an open session.
To connect your PostHog account, start claude, type /mcp, select plugin:posthog:posthog and follow the browser prompts.

Good to know

The plugin includes PostHog's session-capture hook; PostHog's README says it sends sessions to LLM Analytics only when POSTHOG_LLMA_CC_ENABLED=true and POSTHOG_API_KEY are both set.
If you use the separate posthog-telemetry plugin, PostHog says to keep only one of the two, because both register the same hook.
On a self-hosted PostHog, this route's MCP connection won't reach your instance: the plugin's config is fixed to https://mcp.posthog.com/mcp, which routes to PostHog's US or EU region. POSTHOG_MCP_URL works only for the Gemini CLI extension.

View on GitHub

Same repository

adding-warehouse-person-properties
Sync columns from a synced data warehouse table onto PostHog person or group properties, so warehouse data becomes usable anywhere person and group properties already work: feature flag targeting, cohorts, insight filters and breakdowns, surveys, session replay filters, workflows, and the person profile. Use when the user wants to "add a person property from my warehouse", "enrich people with Stripe/Postgres/Salesforce data", "put ARR or plan tier on my persons", "target a feature flag by a warehouse column", "sync warehouse columns onto groups or organizations", or wants to inspect, backfill, disable, or debug an existing warehouse-backed person or group property.Read full description
analyzing-expensive-users
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.Read full description
analyzing-experiment-session-replays
Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with different experiment variants, identify usability issues, compare behavior patterns between control and test groups, or get qualitative insights to complement quantitative experiment results. Also covers pairing the observed behavior with a linked survey when the user wants qualitative feedback beyond what recordings show.Read full description
assessing-heatmaps
Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements. TRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heatmap/click data, or to 'analyze/assess/review the heatmap' for a URL. DO NOT TRIGGER when: the user only wants to create a saved heatmap screenshot with no analysis (use heatmaps-saved-create directly), or is asking about session replay in general (use investigating-replay).Read full description
auditing-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.Read full description
auditing-experiments-flags
Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.Read full description

Creating box plot insights

Choose the query type

Standard product analytics box plot

SQL box plot

Verify the saved insight

Related skills

MCP connection required

Install just this skill

Install the whole plugin

Add PostHog's marketplace, then install the plugin

More skills

adding-warehouse-person-properties

analyzing-expensive-users

analyzing-experiment-session-replays

assessing-heatmaps

auditing-endpoints

auditing-experiments-flags