Skip to main content
skill CX Codex

okr-design · yonatangross — Claude Code skill: OKRs and installation

okr-design is a Claude Code skill for setting goals and defining success metrics. It helps structure OKRs, KPI trees, and experiment measures.

MIT 140 installs ★ 305 updated 2026-11-07

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add yonatangross/orchestkit --skill okr-design -a claude-code
Open on GitHub

What okr-design does

okr-design turns goals into OKRs, breaks top-level metrics into KPI trees, and helps select a North Star metric and leading indicators. For each lagging metric, it calls for 2–3 leading predictors.

The skill also helps define metrics before instrumentation and set experiment guardrails before launch. Its materials include templates for metric definitions, events, and experiment plans. Claude Code 2.1.277 or later is required.

What it helps with

  • write measurable key results for a goal
  • break revenue into a KPI tree
  • find leading indicators for a lagging metric
  • set experiment guardrails before launch

Example prompts for the agent

  • Draft OKRs for a goal to improve customer retention.
  • Break revenue into a KPI tree and suggest leading indicators.
  • Create an A/B test plan with guardrail metrics.

How to install okr-design

1Skills CLI (Vercel)

npx skills add yonatangross/orchestkit --skill okr-design -a claude-code

2Manually: put the files in place

~/.claude/skills/okr-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/okr-design/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about okr-design

How do I install okr-design in Claude Code?

Run npx skills add yonatangross/orchestkit --skill okr-design -a claude-code. The skill file is at ~/.claude/skills/okr-design/SKILL.md.

What does okr-design do?

It helps structure OKRs, build KPI trees, choose metrics, and define guardrails for experiments.

Which Claude Code version does okr-design require?

It requires Claude Code 2.1.277 or later.

Source text

SKILL.md · MIT
---
name: okr-design
compatibility: "Claude Code 2.1.277+"
description: "OKR trees, KPIs, North Star metric, leading and lagging indicators, experiment guardrails. Use when setting goals or success metrics."
user-invocable: false
disable-model-invocation: false
metadata:
  owner-agent: "product-strategist"
  category: document-asset-creation
  version: "1.0.0"
  author: "OrchestKit"
  complexity: "medium"
  tags: "okr, kpi, north-star, metrics, experiment, goal-setting, leading-lagging, instrumentation"
allowed-tools: "Read Glob Grep WebFetch WebSearch"
---

# OKR Design & Metrics Framework

Structure goals, decompose metrics into KPI trees, identify leading indicators, and design rigorous experiments.

## OKR Structure

Objectives are qualitative and inspiring. Key Results are quantitative and outcome-focused — never a list of outputs.

```
Objective: Qualitative, inspiring goal (70% achievable stretch)
+-- Key Result 1: [Verb] [metric] from [baseline] to [target]
+-- Key Result 2: [Verb] [metric] from [baseline] to [target]
+-- Key Result 3: [Verb] [metric] from [baseline] to [target]
```

```markdown
## Q1 OKRs

### Objective: Become the go-to platform for enterprise teams

Key Results:
- KR1: Increase enterprise NPS from 32 to 50
- KR2: Reduce time-to-value from 14 days to 3 days
- KR3: Achieve 95% feature adoption in first 30 days of onboarding
- KR4: Win 5 competitive displacements from [Competitor]
```

### OKR Quality Checks

| Check | Objective | Key Result |
|-------|-----------|------------|
| Has a number | NO | YES |
| Inspiring / energizing | YES | not required |
| Outcome-focused (not "ship X features") | YES | YES |
| 70% achievable (stretch, not sandbagged) | YES | YES |
| Aligned to higher-level goal | YES | YES |

See [references/okr-workshop-guide.md](references/okr-workshop-guide.md) for a full facilitation agenda (3-4 hours, dot voting, finalization template).
See [rules/metrics-okr.md](rules/metrics-okr.md) for pitfalls and alignment cascade patterns.

---

## KPI Tree & North Star

Decompose the top-level metric into components with clear cause-effect relationships.

```
Revenue (Lagging — root)
├── New Revenue = Leads × Conv Rate          (Leading)
├── Expansion   = Users × Upsell Rate        (Leading)
└── Retained    = Existing × (1 - Churn)     (Lagging)
```

### North Star + Input Metrics Template

```markdown
## Metrics Framework

North Star: [One metric that captures core value — e.g., Weekly Active Teams]

Input Metrics (leading, actionable by teams):
1. New signups — acquisition
2. Onboarding completion rate — activation
3. Features used per user/week — engagement
4. Invite rate — virality
5. Upgrade rate — monetization

Lagging Validation (confirm inputs translate to value):
- Revenue growth
- Net retention rate
- Customer lifetime value
```

### North Star Selection by Business Type

| Business | North Star Example | Why |
|----------|--------------------|-----|
| SaaS | Weekly Active Users | Indicates ongoing value delivery |
| Marketplace | Gross Merchandise Value | Captures both buyer and seller sides |
| Media | Time spent | Engagement signals content value |
| E-commerce | Purchase frequency | Repeat = satisfaction |

See [rules/metrics-kpi-trees.md](rules/metrics-kpi-trees.md) for the full revenue and product health KPI tree examples.

---

## Leading vs Lagging Indicators

Every lagging metric you want to improve needs 2-3 leading predictors.

```markdown
## Metric Pairs

Lagging: Customer Churn Rate
Leading:
  1. Product usage frequency (weekly)
  2. Support ticket severity (daily)
  3. NPS score trend (monthly)

Lagging: Revenue Growth
Leading:
  1. Pipeline value (weekly)
  2. Demo-to-trial conversion (weekly)
  3. Feature adoption rate (weekly)
```

| Indicator | Review Cadence | Action Timeline |
|-----------|----------------|-----------------|
| Leading | Daily / Weekly | Immediate course correction |
| Lagging | Monthly / Quarterly | Strategic adjustments |

See [rules/metrics-leading-lagging.md](rules/metrics-leading-lagging.md) for a balanced dashboard template.

---

## Metric Instrumentation

Every metric needs a formal definition before instrumentation.

```markdown
## Metric: Feature Adoption Rate

Definition: % of active users who used [feature] at least once in their first 30 days.
Formula: (Users who triggered feature_activated in first 30 days) / (Users who signed up)
Data Source: Analytics — feature_activated event
Segments: By plan tier, by signup cohort
Calculation: Daily
Review: Weekly

Events:
  user_signed_up  { user_id, plan_tier, signup_source }
  feature_activated { user_id, feature_name, activation_method }
```

Event naming: `object_action` in snake_case — `user_signed_up`, `feature_activated`, `subscription_upgraded`.

See [rules/metrics-instrumentation.md](rules/metrics-instrumentation.md) for the full metric definition template, alerting thresholds, and dashboard design principles.

---

## Experiment Design

Every experiment must define guardrail metrics before launch. Guardrails prevent shipping a "win" that causes hidden damage.

```markdown
## Experiment: [Name]

### Hypothesis
If we [change], then [primary metric] will [direction] by [amount]
because [reasoning based on evidence].

### Metrics
- Primary: [The metric you are trying to move]
- Secondary: [Supporting context metrics]
- Guardrails: [Metrics that MUST NOT degrade — define thresholds]

### Design
- Type: A/B test | multivariate | feature flag rollout
- Sample size: [N per variant — calculated for statistical power]
- Duration: [Minimum weeks to reach significance]

### Rollout Plan
1. 10% — 1 week canary, monitor guardrails daily
2. 50% — 2 weeks, confirm statistical significance
3. 100% — full rollout with continued monitoring

### Kill Criteria
Any guardrail degrades > [threshold]% relative to baseline.
```

### Pre-Launch Checklist

- [ ] Hypothesis documented with expected effect size
- [ ] Primary, secondary, and guardrail metrics defined
- [ ] Sample size calculated for minimum detectable effect
- [ ] Dashboard or alerts configured for guardrail metrics
- [ ] Staged rollout plan with kill criteria at each stage
- [ ] Rollback procedure documented

See [rules/metrics-experiment-design.md](rules/metrics-experiment-design.md) for guardrail thresholds, performance and business guardrail tables, and alert SLAs.

---

## Common Pitfalls

| Pitfall | Mitigation |
|---------|------------|
| KRs are outputs ("ship 5 features") | Rewrite as outcomes ("increase conversion by 20%") |
| Tracking only lagging indicators | Pair every lagging metric with 2-3 leading predictors |
| No baseline before setting targets | Instrument and measure for 2 weeks before setting OKRs |
| Launching experiments without guardrails | Define guardrails before any code is shipped |
| Too many OKRs (>5 per team) | Limit to 3-5 objectives, 3-5 KRs each |
| Metrics without owners | Every metric needs a team owner |

---

## Related Skills

- `prioritization` — RICE, WSJF, ICE, MoSCoW scoring; OKRs define which KPIs drive RICE impact
- `product-frameworks` — Full PM toolkit: value prop, competitive analysis, user research, business case
- `product-analytics` — Instrument and query the metrics defined in OKR trees
- `write-prd` — Embed success metrics and experiment hypotheses into product requirements
- `market-sizing` — TAM/SAM/SOM that anchors North Star Metric targets
- `competitive-analysis` — Competitor benchmarks that inform KR targets

---

**Version:** 1.0.0

© OrchestKit · MIT · yonatangross/orchestkit

Similar skills

All skills for Notes, tasks and projects →

okr-design by other authors comes first.

okr-design rampstackco okr-design — a skill for writing outcome-based OKRs, choosing useful key results, and correcting weak scoring habits. Use it for quarterly planning or an OKR reset. CX Codex +1 293installs okr-goal-setting-wasp-drone Legion Code Inc. okr-goal-setting-wasp-drone — a subagent for writing, auditing, and scoring OKRs grounded in Grove and Doerr methodology. CX Codex ★ 96repo stars okr-generator OneWave-AI okr-generator builds a structured okr-plan.md file using the Google and Intel framework from your company targets and team baselines. CX Codex +1 250installs measure-okr-grader product-on-purpose measure-okr-grader scores each KR at the end of an OKR cycle, checks how solid the evidence is, and turns the results into input for the next cycle. Useful when the team argues over whether a score is good. CX Codex +1 768installs revenue-kpi-framework Maya-Beth Finotti revenue-kpi-framework is a Claude Code skill for designing company-wide revenue metrics. It activates around KPI trees, North Star metrics, or questions about what each team level should track. CX Codex +1 27,700installs kpi-dashboard-design Seth Hobson The kpi-dashboard-design skill helps design KPI dashboards, choose useful metrics, and trace conflicting calculations. Use it for SaaS, operations, and cohort analysis views. CX Codex +1 16,141installs brainstorm-okrs borghei brainstorm-okrs — a skill for AI-powered code editors that drafts and validates quarterly OKRs using the Radical Focus method: one objective, three measurable key results, and counter-metrics. CX Codex +1 111installs

From the same set86

The whole set →
business-case business-case is a Claude Code skill that calculates ROI, NPV, IRR, payback period and TCO. It runs when an agent builds a financial case or compares build vs buy. CX Codex +1 162installs testing-e2e testing-e2e provides Playwright E2E standards, page object patterns, and axe-core accessibility checks. Activates when editing tests or playwright.config.*. CX Codex +1 160installs interaction-patterns interaction-patterns — a skill for Claude Code supplies UI interaction rules for loading, pagination, overlays and notifications. It comes into play while building these interface behaviors. CX Codex +1 160installs documentation-patterns The documentation-patterns skill provides patterns for READMEs, ADRs, OpenAPI docs, changelogs, and technical writing. Use it when drafting project docs or recording an architecture choice. CX Codex +1 150installs figma-design-handoff The figma-design-handoff Claude Code skill guides Figma-to-code handoff, from design tokens to component details. It comes into play when translating layouts, inspecting Dev Mode, or checking a built UI against a Figma frame. CX Codex +1 136installs user-research Skill for structured user research: personas, journey maps, interviews, usability testing, and card sorting. Learn what users actually need and build products grounded in evidence. CX Codex +1 134installs brainstorm The brainstorm skill explores a design question with parallel agents, filters ideas for feasibility, and compares trade-offs. It does not build or fix code. CX Codex +1 133installs setup Scans a project, identifies its stack, suggests skills and MCP servers, then rates readiness. It also supports rescans and focused setup modes. CX Codex +1 133installs

Project sponsors

Companies that keep this analytics open