Files
skills/commands/setup-metrics.md
zeekayandHanzo Dev 65c3b27843 160 marketing, growth and PM skills, on our own connectors
Four MIT collections ported — growthOS, openclaw-marketing-skills,
Marketing-Skills and pm-skills — as 160 skills, 12 agents and 45
commands, each naming its origin in its own frontmatter so the tree can
be checked against THIRD_PARTY_NOTICES rather than trusted. Sixteen names
appeared in more than one collection and none of the copies were
identical; the longest wins, which lands on the more developed text where
they genuinely diverge.

A fifth collection is deliberately absent. awesome-growth-hacking-skills
carries NO licence, which leaves its author every right by default — and
it is a list of links rather than a collection of skills, so there is
nothing in it to port and no permission to port it with. It is cited as a
directory to read.

THE CONNECTOR SKILLS ARE REWRITTEN, not ported. They arrived installing
vendor SDKs, running OAuth flows of their own, and ending with long-lived
credentials in JSON files under .agents/ and ~/.growthos/ at mode 600.
That is a secret on a disk with no rotation path, protected from other
users and not from the agent — and one auth implementation per skill.
Hanzo holds these connectors in Go, per user, sealed in KMS, so `connect`
is the one home for the flow and the platform skills defer to it by
provider id: google_ads, meta_ads, x. It is reachable as HTTP or as MCP
tools at api.hanzo.ai/v1/mcp — the same routes, typed once in Go, so a
tool and a curl cannot disagree.

Two had nothing real behind them and now say so. There is no
search_console provider, so that skill names what does answer the same
questions (google_analytics, google_bigquery) and states that the remedy
is a provider in hanzoai/cloud rather than a vendor SDK here. And
getxapi-connect was a wrapper around a paid reseller of X's public data
with the vendor's key in an env var; it is `listen` now, on our own x
connector — a skill named after a vendor makes the vendor the capability
and dies with it.

The skills referenced paths that only existed inside the source repo, so
the shared material they read is ported to reference/ and the paths
rewritten. Three skills need the growthOS APPLICATION rather than its
data; per the estate's own split an application belongs in hanzoai/ads,
social, email or sms as a cloud plugin, so those three say what they need
instead of carrying an import that resolves to nothing.

Third-party product names are out of our prose and kept in the notices,
which is where the licence requires them and the only place they belong.
A skill's persona names a role, not somebody else's product.


Co-authored-by: Hanzo Dev <[email protected]>
2026-09-15 01:27:26 -07:00

4.4 KiB

description, argument-hint, source
description argument-hint source
Design a product metrics dashboard with North Star metric, input metrics, health metrics, and alert thresholds <product or feature area> phuryn/pm-skills

/setup-metrics -- Product Metrics Dashboard Design

Design a comprehensive metrics framework for your product or feature — from selecting the right North Star to defining alert thresholds that catch problems early.

Invocation

/setup-metrics SaaS project management tool
/setup-metrics New checkout flow we just launched
/setup-metrics             # asks what you're measuring

Workflow

Step 1: Understand What to Measure

Ask the user:

  • What product or feature area are you setting up metrics for?
  • What stage is it in? (pre-launch, recently launched, mature)
  • What are the current business goals or OKRs?
  • Do you have existing metrics? What's missing or broken?
  • What analytics tools are you using? (helps tailor implementation advice)

Step 2: Define the Metrics Framework

Apply the metrics-dashboard skill:

North Star Metric:

  • Identify the single metric that best captures the value your product delivers to users
  • Validate against criteria: measures value delivery, is a leading indicator, is actionable
  • Define the metric precisely (formula, data source, time window)

Input Metrics (3-5):

  • Identify the levers that drive the North Star
  • Each input metric should be directly actionable by a team
  • Map the causal chain: Input → North Star → Business Outcome

Health Metrics (3-5):

  • Metrics that should stay stable — if they degrade, something is wrong
  • Examples: error rates, latency, support ticket volume, NPS, churn rate
  • Define "healthy" ranges and degradation thresholds

Counter-Metrics (1-2):

  • Metrics that could indicate you're optimizing the wrong way
  • Example: if North Star is "daily active users", counter-metric is "session quality" to prevent empty engagement

Step 3: Design Alert Thresholds

For each metric:

Metric Green Yellow Red Check Frequency
[metric] [healthy range] [warning] [critical] [daily/weekly]
  • Yellow: Investigate — something may be off
  • Red: Act immediately — page someone or escalate

Step 4: Create Dashboard Spec

## Metrics Dashboard: [Product/Feature]

**North Star**: [metric name]
**Definition**: [precise formula]
**Current value**: [if known]
**Target**: [goal]

### Input Metrics
| Metric | Definition | Owner | Target | Current |
|--------|-----------|-------|--------|---------|

### Health Metrics
| Metric | Healthy Range | Yellow Threshold | Red Threshold |
|--------|-------------|-----------------|---------------|

### Counter-Metrics
| Metric | Why It Matters | Watch For |
|--------|---------------|-----------|

### Metrics Tree
North Star: [metric]
├── Input: [metric 1] → driven by [team/action]
├── Input: [metric 2] → driven by [team/action]
├── Input: [metric 3] → driven by [team/action]
└── Counter: [metric] → watch for [degradation signal]

### Implementation Notes
- Data sources: [where each metric comes from]
- Refresh frequency: [real-time / hourly / daily]
- Tool recommendations: [based on user's stack]

### Review Cadence
- **Daily**: Glance at North Star and health metrics
- **Weekly**: Review input metrics trends, discuss in team standup
- **Monthly**: Deep dive — are inputs driving the North Star as expected?
- **Quarterly**: Reassess the metrics framework itself

Save as a markdown file to the user's workspace.

Step 5: Offer Next Steps

  • "Want me to write SQL queries to compute these metrics?"
  • "Should I create OKRs based on this metrics framework?"
  • "Want me to build a cohort analysis to set realistic baselines?"
  • "Should I set up a weekly metrics review template?"

Notes

  • A good North Star is rare — most teams pick vanity metrics. Push for a metric that captures user value delivered, not just engagement
  • Input metrics should be MECE (mutually exclusive, collectively exhaustive) in explaining the North Star
  • If the product is pre-launch, define metrics now but note that baselines will need calibration after launch
  • Counter-metrics prevent Goodhart's Law — when a metric becomes a target, it ceases to be a good metric
  • Recommend starting with fewer metrics, well-instrumented, over a sprawling dashboard nobody checks