--- name: posthog-shipped-but-unused description: "On the 1st: every feature shipped last month in Linear or Jira, the share of active accounts in PostHog that used it, and the support tickets it caused. Use when the user asks for this, or when it runs on a schedule." --- # Shipped but unused: Linear releases, PostHog usage and support On the 1st: every feature shipped last month in Linear or Jira, the share of active accounts in PostHog that used it, and the support tickets it caused. Linear shows the project marked complete. PostHog has an event for it somewhere. Support has a few tickets that mention it. A month later nobody can say whether the feature was worth building, because the answer sits in three tools that never meet in the same meeting. This skill is for the product manager who writes the monthly product review. On the 1st the agent lists the features shipped last month, looks up each one's event in PostHog using a map you set once, works out the share of active accounts that used it, and counts the Zendesk or Intercom tickets that name it. The card puts adoption and support load side by side per feature, so the review starts with "this one landed, this one did not, this one hurts". ## Two ways to get the data Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used. ## Route A: API or MCP server ### What you need - A one-time map from feature name to PostHog event or flag key, kept in the skill's settings: the join depends on it, and the event must fire when the feature is used, not when its page loads. - A PostHog personal API key with `query:read` (or the PostHog MCP server), and group analytics if adoption should count accounts rather than people. - Read access to Linear (MCP server or `LINEAR_API_KEY`) or Jira, and to Zendesk or Intercom tickets. If something is missing, say what and stop; do not invent numbers. ### Steps 1. **List what shipped last month** (Linear): Whichever you plan in. Linear: `projects(filter: { completedAt: { gte: "", lt: "" } })` for name, `completedAt` and `url`, plus `issues` with your feature label whose `completedAt` falls in the month. Jira: `GET /rest/api/3/project/{key}/versions`, keep versions with `released: true` and a `releaseDate` in the month, then `fixVersion = ""` for the features in each. 2. **Map each feature to its PostHog event**: The key is the feature name, lowercased and trimmed, looked up in the map the person set once in the skill's settings (`bulk export = export_completed`, or a flag key such as `flag:saved-views`). A feature with no entry is listed as "not mapped" and asks for one; never guess an event from its name. 3. **Work out adoption among active accounts** (PostHog): Through the query API, run HogQL for the month: active accounts are `SELECT count(DISTINCT $group_0) FROM events WHERE timestamp >= '' AND timestamp < '' AND $group_0 != ''`, and feature accounts the same with `event = ''` and `timestamp >= ''`. Use the group index for your account group type, or `person_id` without group analytics. For a flag, count `$feature_flag_called` with `properties.$feature_flag = ''` and label it exposure, not use. 4. **Count the tickets that name each feature** (Intercom): Whichever you use. Zendesk: `GET /api/v2/search.json?query=type:ticket created>= ""`, or `tags:` if you tag by feature. Intercom: `POST /conversations/search` with `source.body` `~` the feature name and `created_at` in the month. A ticket that names two features counts for the one with the longer name. 5. **Give each feature a verdict**: Adopted: 20% of active accounts or more. Low: under 5% after at least 14 days live. Painful: 5 or more tickets, whatever the adoption. Features live under 14 days are marked early. Post the card with days live, accounts using it, adoption and tickets per feature. ## Route B: the browser ### What you need - Signed in to Linear or Jira, to PostHog with access to the project, and to Zendesk or Intercom as an agent who can search all tickets. If something is missing, say what and stop; do not invent numbers. ### Steps Start at https://linear.app/. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears. 1. **List last month's shipped features**: In Linear, open **Projects**, filter by status Completed and read the completion dates for last month; then filter issues by your feature label and Completed in the same month. Jira users open the project's **Releases** page and read versions released in the month. 2. **Count active and adopting accounts in PostHog**: Open `https://us.posthog.com/` (or `eu.posthog.com`), **Product analytics**, new **Trends** insight. Set the date range to last month, series **All events**, and aggregate by unique organizations (or unique users) to get active accounts. Then switch the series to the feature's mapped event, from its ship date, for the accounts that used it. 3. **Count the tickets**: In Zendesk search `type:ticket created>` with last month's first day and the feature name in quotes, or in Intercom search conversations for the feature name with last month as the date range. Count tickets per feature. 4. **Give each feature a verdict**: Adoption is adopting accounts over active accounts. Adopted at 20% or more, low under 5% after 14 days live, painful at 5 or more tickets, early under 14 days. Report the table and the one thing to do first. Note: Aggregating by organizations needs PostHog group analytics; without it the browser route counts people. Ticket search in both support tools matches the words anywhere in the ticket, so a common feature name can overcount; read a few results to check. For more than 5 features a month the API route is faster. ## The report - **Features shipped** last month and the active accounts in the month. - **Per feature**: ship date, days live, accounts using it, adoption, tickets, and a verdict (adopted, low, painful, early). - **Not mapped**: shipped features with no PostHog event yet. - The first thing to do, for example "Read the 9 Slack alerts tickets before announcing it wider". ## Post it to Briefkin When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on. ```bash [ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \ -H "authorization: Bearer $BRIEFKIN_TOKEN" \ -H "content-type: application/json" \ -d @- <<'JSON' { "v": 1, "event_id": "posthog-shipped-but-unused/", "item_key": "posthog-shipped-but-unused", "project": "Acme", "source": "Shipped but unused: Linear releases, PostHog usage and support skill", "kind": "update", "title": "3 features shipped in October: one at 34% of accounts, one at 2%, one causing 9 tickets", "summary": "Of **1,240 active accounts** in October, **34%** used Bulk export and **2%** used Saved views. Slack alerts reached 15% in 9 days and drew **9 support tickets**.", "widget": [ { "type": "Table", "props": { "columns": [ "Feature", "Shipped", "Accounts", "Adoption", "Tickets", "Verdict" ], "align": [ "left", "left", "right", "right", "right", "left" ], "rows": [ [ "Bulk export", "Oct 6", 422, "34%", 1, "Adopted" ], [ "Saved views", "Oct 14", 25, "2%", 0, "Low" ], [ "Slack alerts", "Oct 22", 186, "15%", 9, "Painful" ] ] } }, { "type": "Bars", "props": { "unit": "%", "items": [ { "label": "Bulk export", "value": 34 }, { "label": "Slack alerts", "value": 15 }, { "label": "Saved views", "value": 2 } ] } }, { "type": "Callout", "props": { "text": "Read the 9 Slack alerts tickets before announcing it wider: 7 of them say the alert arrived twice.", "tone": "warn" } } ] } JSON ``` Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report. ## Run it on a schedule Suggested: 1st of the month at 9:00 (`0 9 1 * *`). From cron, with the agent signed in on that machine: ```bash 0 9 1 * * claude -p "Run the posthog-shipped-but-unused skill" # Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run ``` Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/posthog-shipped-but-unused#schedule Source: https://briefkin.dev/skills/posthog-shipped-but-unused