# Dstack Metric Brief

> KPI deep dive report. Given a metric name, produces a structured brief: current value, WoW and MoM trend, top contributing segments, and notable outliers. Outputs a shareable summary for Slack, docs, or stakeholder updates. Trigger phrases: "summarize this metric", "metric brief", "what's happening with X", "give me a KPI summary", "how is [metric] doing?", "weekly metric update".

- Skill: `upsolve-labs/dstack-metric-brief` (Agent Skill)
- Install (CLI): `npx skillmds@latest add upsolve-labs/dstack-metric-brief`
- Raw SKILL.md: https://api.skillmd.com/api/skills/upsolve-labs/dstack-metric-brief/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- License: MIT
- Author: Upsolve-Labs (https://skillmd.com/u/upsolve-labs)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/upsolve-labs/dstack-metric-brief

---


## Update Check (run first)

```bash
_UPD=$(~/.claude/skills/data-stack/bin/data-stack-update-check 2>/dev/null || .claude/skills/data-stack/bin/data-stack-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
```

If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/data-stack/skills/dstack-upgrade/SKILL.md` and follow the "Inline upgrade flow". If `JUST_UPGRADED <from> <to>`: tell user "Running data-stack v{to} (just updated!)" and continue.

# /metric-brief

You are producing a shareable KPI brief for a specific metric.

## Before Starting

If the user hasn't specified a metric, AskUserQuestion: "Which metric do you want a brief for? (e.g. 'daily active users', 'revenue', 'conversion rate')"

## Phase 1: Current Value & Trend

Open an Upsolve thread:

```
analyze_data("Show me <metric> for: the most recent full period, WoW change, MoM change, and the 30-day daily trend.")
```

## Phase 2: Segment Breakdown

```
analyze_data("Break down <metric> by the top 3 most impactful dimensions. For each segment show the current value and WoW change.", thread_id=<id>)
```

## Phase 3: Outliers & Notable Events

```
analyze_data("In the last 30 days of <metric> data, flag any single-day spikes, drops, or unusual patterns worth calling out.", thread_id=<id>)
```

## Phase 4: Output Brief

Format for easy copy-paste into Slack or a doc:

```
METRIC BRIEF: <Metric Name>
As of <date>
────────────────────────────────────────
Current:   <value>
WoW:       <+/- X%>
MoM:       <+/- X%>
Trend:     <upward / downward / flat>

TOP SEGMENTS:
  <segment 1>:  <value>  (<+/- X%> WoW)
  <segment 2>:  <value>  (<+/- X%> WoW)
  <segment 3>:  <value>  (<+/- X%> WoW)

NOTABLE:
  <any spikes, drops, or anomalies worth flagging — or "Nothing unusual">

SUMMARY:
  <2–3 sentence plain-language interpretation>
```

## Rules

- Keep the brief scannable. Never include raw SQL or query details in the output.
- If the metric has a known target, include % to target if the user mentions it.
- Always include WoW — it's the most actionable trend signal.
- If data is incomplete, note it explicitly rather than extrapolating.