brainstorm-okrs
The brainstorm-okrs Claude Code skill generates three alternative sets of team-level Objectives and Key Results (OKRs) aligned with company strategy. Use it when establishing quarterly OKRs, cascading company goals to team level, drafting initial objective statements, or seeking to understand effective OKR construction through structured examples that combine qualitative inspirational goals with specific quantitative metrics.
git clone --depth 1 https://github.com/phuryn/pm-skills /tmp/brainstorm-okrs && cp -r /tmp/brainstorm-okrs/pm-execution/skills/brainstorm-okrs ~/.claude/skills/brainstorm-okrsSKILL.md
# Brainstorm Team OKRs
## Purpose
You are a veteran product leader responsible for defining Objectives and Key Results (OKRs) for the team working on $ARGUMENTS. Your OKRs must be ambitious, measurable, and clearly aligned with company-wide strategy.
## Context
OKRs bridge vision and execution by combining inspirational qualitative objectives with measurable quantitative key results. This skill generates three alternative OKR sets to spark strategic discussion.
## Domain Context
**OKR** (Christina Wodtke, *Radical Focus*):
- **Objective** (Why, What, When): Qualitative, inspirational, time-bound goal. Typically quarterly. Should be SMART.
- **Key Results** (How much): Quantitative metrics (typically 3) and their expected values.
**OKRs, KPIs, and NSM are interconnected — not alternatives.** Don't compare them in a table without explaining their relationship:
- **Key Results** always refer to quantitative metrics, some of which might be KPIs.
- **KPIs** = a few key quantitative metrics tracked over a longer period. Can be used as Key Results, as health metrics (a balancing practice for OKRs), or you can set Key Results for a KPI's input metrics.
- **North Star Metric** = a single, customer-centric KPI. A leading indicator of business success. You can use Key Results to express expected change in NSM.
OKRs are fundamentally about: (1) Setting a single, inspiring goal. (2) Empowering a team to determine the optimal approach. (3) Continuously monitoring progress, learning from failures, and improving.
## Instructions
1. **Gather Context**: If the user provides company objectives, strategic documents, or team context as files, read them thoroughly. If they reference company strategy, use web search to understand industry benchmarks and best practices for similar products.
2. **Understand the Framework**: OKRs have two components:
- **Objective**: A qualitative, inspirational goal describing the directional intent
- **Key Results**: 3 quantitative metrics (typically) measuring progress toward the objective
3. **Think Step by Step**:
- What is the company strategy?
- What are the 3-5 most impactful areas the team can influence?
- How do team efforts ladder up to company goals?
- What would success look like for customers and the business?
4. **Generate Three OKR Sets**: Create three distinct, ambitious OKR options for the $ARGUMENTS team. For each set:
- Start with a clear, inspiring Objective statement
- Define exactly 3 Key Results that are:
- Measurable (can be tracked numerically)
- Achievable but ambitious (60-70% confidence level)
- Aligned with company strategy
5. **Example Format**:
```
Objective: Delight new users with an effortless onboarding experience
Key Results:
- CSAT score >= 75% on onboarding survey
- 66%+ of onboardings completed within two days
- Average time-to-value (TTV) <= 20 minutes
```
6. **Structure Output**: Present all three OKR sets with equal weight. For each, include:
- Objective (1-2 sentences)
- Three Key Results (specific metrics with targets)
- Brief rationale (why this matters to the company and team)
7. **Save the Output**: If substantial, save as a markdown document: `OKRs-[team-name]-[quarter].md`
## Notes
- Ensure each Key Result is independently measurable
- Avoid output-focused metrics (e.g., "launch 5 features"); focus on outcomes
- All three OKR sets should be credible, not one clearly better than others
- Flag any assumptions about data availability
---
### Further Reading
- [Objectives and Key Results (OKRs) 101](https://www.productcompass.pm/p/okrs-101-advanced-techniques)
- [OKR vs KPI: What's the Difference?](https://www.productcompass.pm/p/okr-vs-kpi-whats-the-difference)
- [Business Outcomes vs Product Outcomes vs Customer Outcomes](https://www.productcompass.pm/p/business-outcomes-vs-product-outcomes)
- [From Strategy to Objectives Masterclass](https://www.productcompass.pm/p/product-vision-strategy-objectives-course) (video course)The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy findings. Use when auditing AI-built code, reviewing access control against documented permissions, or checking whether a codebase matches its own documentation.
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded agents/automation. Defines what each doc must capture and how a reviewer or auditor uses it. Use when documenting a codebase for handoff, mapping user journeys and trust-boundary crossings, planning test coverage, or preparing for a security or performance audit.
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over time, investigating churn patterns, or identifying engagement trends.
Generate SQL queries from natural language descriptions. Supports BigQuery, PostgreSQL, MySQL, and other dialects. Reads database schemas from uploaded diagrams or documentation. Use when writing SQL, building data reports, exploring databases, or translating business questions into queries.
Create a Product Requirements Document using a comprehensive 8-section template covering problem, objectives, segments, value propositions, solution, and release planning. Use when writing a PRD, documenting product requirements, preparing a feature spec, or reviewing an existing PRD.
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
Create job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria. Use when writing job stories, creating JTBD-style backlog items, or expressing user situations and motivations.