Terminal
Terminal/Skill
Explains an existing Mixpanel report or chart, showing what it displays and flagging notable patterns without digging into causes.
By Mixpanel
Works with
npx skills add mixpanel/ai-plugins --skill analyze-reportEngine required — resolve an engine per
ENGINE.md: one named in the conversation or loaded instructions is mandatory (not set up → offer/mixpanel:installfor it); otherwise use the Mixpanel MCP server, or offer/mixpanel:installif it's unavailable.
Take a Mixpanel report or chart that already exists (or just got built) and turn it into a one-screen summary the customer can act on. The skill is lean by default — it explains what the report shows and flags what's notable, but does not chase root causes unless the customer asks.
This skill is built for fast interpretation: flag what you see and stop. The boundary — when a "why" question turns this into a root-cause investigation — is defined in "Hybrid scope — when to stop" below.
Three input modes. Detect which one applies from the customer's message:
Most common. Mixpanel report URLs look like https://mixpanel.com/project/<project_id>/view/<board_id>/app/<chart> or include report_id=<id>. Extract the ID(s).
Fetch the report's saved configuration — the events, properties, filters, breakdowns, date range, and chart type — so you can ground the analysis without asking the customer to re-explain what they built.
If you can't resolve the URL/ID (404, permission error, malformed URL), say so plainly and ask if they meant a different report.
If the customer says "the DAU chart on my exec board" or "the funnel I built last week," they're pointing at an existing report but haven't given an ID. Search saved reports for candidates, show the top 3 matches with their titles and dates, and ask which one they mean.
If nothing useful comes back, escalate to Mode C:
"I can't find that report. Want to build it fresh and analyze that?"
The report has to be built before it can be analyzed. Build the chart first (or ask the customer to point you at the configuration they want), then come back to Step 2 and analyze the result. Once the chart is built you have a fresh result and a rendered widget; this skill picks up from there.
If the customer asks for both in one turn ("build me a DAU chart and tell me what it shows"), do them as one workflow: build → analyze → present together.
For Mode A or B (existing report), re-run the report against its saved configuration to get fresh data. Don't trust cached chart state — the customer may not have refreshed in days.
For Mode C, the chart was just built, so its result is already current — analyze that.
In all cases, you need:
Without configuration metadata, the analysis is shallow ("the line goes up") instead of grounded ("checkout volume rose 18% WoW, isolated to the iOS platform").
What to look for depends on chart type. Read the matching reference:
references/read-insights.mdreferences/read-funnels.mdreferences/read-retention.mdreferences/read-flows.mdThe references hold the specific patterns to look for in each chart type. The high-level rules across all types:
Output structure (always this shape, length scales with content):
**What this shows**
[1–2 sentences: report subject, time window, current value]
**The shape**
[1–3 sentences: trend direction, magnitude, key inflection points]
**Worth noting**
[Bullet list — only items that meet the "flag" bar above. Skip if
nothing notable.]
**Want to dig in?**
[Offer to either: (a) investigate why the movement happened, OR
(b) recut the report with a different breakdown, filter, or date range
if that would help]
Example output for a DAU chart that dipped:
**What this shows**
Daily Active Users over the last 30 days. Currently at 142K DAU.
**The shape**
Flat through most of the month, with a clear step-down on March 18th
— DAU dropped from ~150K to ~135K and hasn't recovered. The post-drop
baseline is roughly 9% below the pre-drop average.
**Worth noting**
- The drop is a step-change, not a gradual decline — typical of a
deploy, instrumentation change, or external event.
- Weekend dips are still present at the same magnitude — the issue
isn't a day-of-week shift.
**Want to dig in?**
The shape suggests a single trigger event around March 18th. Want me
to dig into which segments are driving the drop?
Keep it tight. A customer reading this on a phone needs to get the takeaway in the first paragraph.
Lean by default means: surface what's there, stop. The boundary is the "why" question. If the customer asks any of:
…that's a root-cause investigation, which is a deeper, multi-step workflow. Don't try to answer it inline here. Flag what the data shows and offer the deeper dig as an explicit next step:
"That's a root-cause question — it can take a few cuts to answer properly. Want me to dig into the segments driving this?"
Do not silently expand the analysis. An unbounded "why" question turns a 30-second summary into a 10-minute investigation. Better to make the boundary explicit and let the customer opt in.
For chart-type-specific reading patterns, see the matching file in references/.