agentleFS
patonkikhpatonkikh/APES/skills/product/okr-builder/skill.md

okr-builder

Skill3 starsChanged 4 months agoMITView on GitHub

Create aligned Objectives and Key Results (OKRs) for product teams with measurable key results and initiative mapping. Use when working on product discovery, PRDs, user stories, OKRs, or backlog planning.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create aligned Objectives and Key Results (OKRs) for product teams with measurable key results and initiative mapping.

    line 14
  2. Distinctive:

    No conflicting KRs across objectives

    line 71
  3. Distinctive:

    No more than 3 objectives (focus)

    line 72
  4. Distinctive:

    Use OKR formula: "We will [objective] as measured by [KR1], [KR2]..."

    line 116

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

OKR Builder

Purpose

Create aligned Objectives and Key Results (OKRs) for product teams with measurable key results and initiative mapping.

Input: Product vision, strategic priorities, time period (quarter), team scope
Output: OKR document with 1–3 objectives, 2–4 KRs each, and linked initiatives Examples: See examples.md for worked input/output.


Workflow

Step 1: Define planning context

Confirm:

  • Time period (e.g., Q3 2026)
  • Team/product scope
  • Strategic themes from vision or leadership
  • Constraints (headcount, dependencies)

Step 2: Draft objectives

Rules for objectives:

  • Qualitative and inspirational
  • Actionable by the team
  • 1–3 objectives per team per period
  • Aligned with product vision north star

Format: "Verb + ambitious outcome" (e.g., "Delight enterprise admins with effortless onboarding").

Step 3: Define key results

Per objective, 2–4 KRs:

KRMetricBaselineTargetMeasurement

KR rules:

  • Measurable (number, percentage, binary)
  • Outcome-based, not output-based ("launch feature" is not a KR)
  • Ambitious but achievable (60-70% confidence)

Step 4: Map initiatives

Link epics/features to KRs:

InitiativeSupports KRStatus

Initiatives are hypotheses for achieving KRs.

Step 5: Check alignment

Verify:

  • KRs ladder up to north star metric
  • No conflicting KRs across objectives
  • No more than 3 objectives (focus)

Step 6: Validate

Run Validation checklist.


Decision Rules

ConditionAction
KR is a task/outputRewrite as measurable outcome
>4 KRs per objectiveReduce; focus on vital few
No baseline for KRState "TBD — measure in week 1" explicitly
Objective not actionable by teamReframe or escalate to leadership OKR
All KRs are vanity metricsReplace with outcome metrics tied to user value

Validation

  • 1–3 objectives defined
  • 2–4 KRs per objective with baseline and target
  • All KRs are measurable outcomes (not outputs)
  • Initiatives mapped to KRs
  • Alignment with north star noted
  • Confidence level stated per KR (optional but recommended)
  • No more than 3 objectives

Anti-patterns

  • OKR as task list — "Ship v2", "Hire 2 engineers" as KRs.
  • Too many objectives — 5+ objectives diluting focus.
  • Sandbagging — 100% confident easy KRs.
  • Unmeasurable KRs — "Improve quality" without metric.
  • Orphan OKRs — no connection to vision or initiatives.

Best Practices

  • Use OKR formula: "We will [objective] as measured by [KR1], [KR2]..."
  • Review OKRs mid-quarter; don't change objectives lightly.
  • Separate committed OKRs from aspirational stretch.
  • Align with product/feature-prioritization for initiative selection.
  • Grade KRs 0.0–1.0 at end of period; 0.7 is success.

Output Structure

# OKRs: [Team/Product] — [Period]

## Context
- **Vision alignment:** [north star connection]
- **Scope:** [team/product]

## Objective 1: [Statement]
| KR | Metric | Baseline | Target | Owner |
|----|--------|----------|--------|-------|

**Initiatives:**
- [Initiative] → KR 1.1

## Objective 2: [Statement]
[Same structure]

## Alignment Check
| North star | Supported by |
|------------|--------------|

## Scoring Guide
0.0 = no progress | 0.7 = success | 1.0 = exceeded

Next Skills

OutcomeRecommended Skill
Prioritize initiativesproduct/feature-prioritization
Plan deliveryproduct/sprint-planner
Define visionproduct/product-vision-builder
Write PRD for initiativeproduct/prd-generator

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.