Okr Design

What it does

When your agent uses it

• Setting team goals
• Defining success metrics
• Building measurement frameworks
• Designing A/B experiment guardrails

Example prompts

• “/okr-design”

Requirements

• Compatibility (from SKILL.md): Claude Code 2.1.277+
• Pre-approved tools (allowed-tools): Read, Glob, Grep, WebFetch, WebSearch

What it can do on your machine

Read from SKILL.md and the folder at commit e4ff8d9. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • WebFetch
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Claude Code 2.1.277+

  From compatibility in the SKILL.md frontmatter.

Context cost

Okr Design loads about 1.9k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 448 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~59

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yonatangross/orchestkit at commit e4ff8d9, republished under its MIT licence (© yonatangross). 448 words, ~1,901 tokens.

name

okr-design

description

OKR trees, KPI dashboards, North Star Metric, leading/lagging indicators, and experiment design. Use when setting team goals, defining success metrics, building measurement frameworks, or designing A/B experiment guardrails.

allowed-tools

Read, Glob, Grep, WebFetch, WebSearch

compatibility

Claude Code 2.1.277+

user-invocable

false

disable-model-invocation

false

metadata.owner-agent

product-strategist

metadata.category

document-asset-creation

metadata.version

1.0.0

metadata.author

OrchestKit

metadata.complexity

medium

metadata.tags

okr, kpi, north-star, metrics, experiment, goal-setting, leading-lagging, instrumentation

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]

## 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]

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

## 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

## 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)

## 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 }

## 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.

© yonatangross, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in src/skills/okr-design of yonatangross/orchestkit.

• SKILL.md
• references/okr-workshop-guide.md
• rules/_sections.md
• rules/metrics-experiment-design.md
• rules/metrics-instrumentation.md
• rules/metrics-kpi-trees.md
• rules/metrics-leading-lagging.md
• rules/metrics-okr.md
• test-cases.json

Open the folder on GitHubat commit e4ff8d9