okr-writer
Skill22 starsChanged 3 months agoMITView on GitHub
Writes strong OKRs (Objectives and Key Results) with outcome-focused, inspiring objectives and measurable, ambitious, time-bound key results. Use this skill when the user asks to write, draft, review, critique, or improve OKRs, goals, or quarterly/annual objectives, when they mention "objectives and key results", "set goals for the team", "turn this strategy into OKRs", "are these good key results", or when distinguishing outcomes from outputs/tasks for planning and performance.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- Bellistri-Nick/pm-skillstheir own version, first seen Nov 15, 2026
- JayRHa/agent-skillsword for word, first seen Oct 15, 2026
- JayRHa/AgentSkillsword for word, first seen Jun 9, 2026
- hamzafarooq/claude-code-startertheir own version, first seen May 8, 2026
- Mehdibargach/claude-code-pm-skillstheir own version, first seen Mar 18, 2026
Other versions5 projects use a version of this.
Word for word · 2
- JayRHa/agent-skills★ 12100% same
- JayRHa/AgentSkills★ 12100% same
Edited · 0
None found.
Wrote their own version · 3
- hamzafarooq/claude-code-starter★ 145same name
- Mehdibargach/claude-code-pm-skills★ 97same name
- Bellistri-Nick/pm-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository194 other files it gives its agents.
- 0-templateSkill
- ab-test-analyzerSkill
- academy-guideSkill
- add-to-my-skillsSkill
- adr-authorSkill
- ai-tools-setupSkill
- algorithmic-artSkill
- api-and-interface-designSkill
- api-designerSkill
- api-docs-writerSkill
- apple-store-submitSkill
- aws-cost-optimizerSkill
- bash-script-hardeningSkill
- blog-post-writerSkill
- book-summarizerSkill
- branch-cleanupSkill
- brand-copy-landingSkill
- brand-copySkill
- brand-designSkill
- brand-guidelinesSkill
- browser-testing-with-devtoolsSkill
- canvas-designSkill
- changelog-generatorSkill
- changelog-keeperSkill
- chart-chooserSkill
- ci-cd-and-automationSkill
- ci-fix-loopSkill
- claude-apiSkill
- cloudflare-block-countriesSkill
- coderabbitloopSkill
- code-review-and-qualitySkill
- code-reviewerSkill
- code-simplificationSkill
- codexloopSkill
- comms-notionSkill
- comms-slackSkill
- comms-whatsappSkill
- competitive-analysisSkill
- concept-explainerSkill
- constraint-driven-developmentSkill
- context-engineeringSkill
- context-repoSkill
- cover-letter-writerSkill
- crash-courseSkill
- cron-schedulerSkill
- data-digestSkill
- data-pipeline-architectSkill
- debug-detectiveSkill
- debugging-and-error-recoverySkill
- decision-matrixSkill
- dependabot-triageSkill
- dependency-upgraderSkill
- deprecation-and-migrationSkill
- dev-instantdbSkill
- discernment-nudgeSkill
- doc-coauthoringSkill
- dockerfile-proSkill
- docs-index-keeperSkill
- documentation-and-adrsSkill
- docxSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use this skill to: draft new OKRs from a vague goal or strategy, rewrite weak/task-based OKRs into outcome-based ones, review and score a …
- Distinctive: line 27
Follow these steps in order.
- Very specific: line 33
Draft the Objective: Write one short, qualitative, inspiring sentence.
- Very specific: line 39
Self-review with the rubric: Run every OKR through references/review-rubric.md (or scripts/okr_lint.py for automated checks).
- Distinctive: line 45
Every key result should be reducible to:
- Distinctive: line 54
If you can write "Done / Not done" instead of a number, it is probably a task, not a key result.
- Distinctive: line 58
Task vs Key Result test: Ask "Could we do this perfectly and still fail the objective?" If yes, it's an output/initiative, not a KR.
- Distinctive: line 83
Always record a baseline and a deadline within the OKR period.
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
OKR Writer
Overview
OKRs (Objectives and Key Results) are a goal-setting framework that links an inspiring qualitative Objective ("what we want to achieve") to 2-5 quantitative Key Results ("how we measure progress"). This skill produces OKRs that are outcome-focused (changes in behavior, value, or state — not task lists), measurable (a number anyone can verify), and appropriately ambitious.
Keywords: OKR, objective, key result, goal setting, KPI vs OKR, outcome vs output, stretch goal, quarterly planning, north star, measurable goals, scoring, grading.
Use this skill to: draft new OKRs from a vague goal or strategy, rewrite weak/task-based OKRs into outcome-based ones, review and score a draft set, or cascade company OKRs to teams.
Core Definitions
- Objective — A memorable, qualitative, inspirational statement of WHAT you want to accomplish in the period. No numbers. Answers "where do we want to go?"
- Key Result — A quantitative measure of HOW you'll know you got there. Has a metric, a baseline, and a target. Answers "how do we know we arrived?"
- Output — Something you produce or do (ship a feature, run 3 campaigns). NOT a key result on its own.
- Outcome — A change that results from outputs (activation rate rises from 40% to 55%). This is what good key results measure.
- Initiative / Task — The work you do to move a key result. Tracked separately, never as the OKR itself.
Workflow
Follow these steps in order. Do not skip the diagnosis step — most weak OKRs come from skipping it.
- Clarify intent and scope. Ask (or infer) four things: the team/owner, the time horizon (quarter, year), the strategic theme or problem this serves, and the current baseline for any metric mentioned. If a baseline is unknown, flag it — a key result without a baseline is unscoreable.
- Find the outcome. Restate the user's goal as "If we succeed, what will be measurably different about the world / customer / business?" If they hand you a task ("rebuild onboarding"), ask "so that what happens?" until you reach a metric. See
references/outcome-vs-output.md. - Draft the Objective. Write one short, qualitative, inspiring sentence. No metrics, no jargon, no "and" stitching two goals together. It should be repeatable from memory. Use the patterns in
references/objective-patterns.md. - Draft 2-5 Key Results. Each must follow the metric formula:
<verb> <metric> from <baseline> to <target> by <date>. Cover the outcome from multiple angles and include at least one counter-balancing / quality KR so the team can't game the headline number. Seereferences/key-result-formulas.md. - Calibrate ambition. Decide committed vs aspirational (stretch). For aspirational OKRs, target ~70% confidence — hitting 100% means it was sandbagged. State the confidence level explicitly.
- Self-review with the rubric. Run every OKR through
references/review-rubric.md(orscripts/okr_lint.pyfor automated checks). Fix any KR that is a task, lacks a number, lacks a baseline, or just measures activity. - Present. Output using
templates/okr-template.md. Include owner, period, confidence, and the initiatives separately from the KRs.
The Key Result Formula
Every key result should be reducible to:
{Direction verb} {metric} from {baseline} to {target} by {deadline}.
Examples:
- "Increase 30-day user retention from 42% to 55% by end of Q3."
- "Reduce average support first-response time from 9h to under 2h by Sept 30."
- "Grow ARR from $4.2M to $5.0M by year end."
If you can write "Done / Not done" instead of a number, it is probably a task, not a key result. Binary milestones are allowed sparingly (e.g., "Achieve SOC 2 Type II certification") but prefer graded metrics.
Decision Heuristics
- Task vs Key Result test: Ask "Could we do this perfectly and still fail the objective?" If yes, it's an output/initiative, not a KR. Demote it.
- Vanity vs value test: Would the metric impress a board slide but not reflect real value (e.g., "signups" with no activation)? Pair it with an activation/retention KR or replace it.
- Gaming test: "How would a lazy/clever team hit this number without delivering the intent?" Add a counter-metric to close the loophole.
- Memorability test: Can a team member recite the Objective without reading it? If not, shorten.
- Quantity test: More than 5 KRs per Objective dilutes focus; more than 3-5 Objectives per team scatters effort. Cut.
Worked Example (compressed)
Weak input: "Improve our mobile app and ship the redesign."
Diagnosis: This is an output. The implied outcome is usage/satisfaction. Baseline needed.
Strong OKR:
- Objective: Make the mobile app the channel customers love most.
- KR1: Raise mobile App Store rating from 3.6 to 4.5 by end of Q4.
- KR2: Increase share of weekly active users on mobile from 31% to 50%.
- KR3: Cut mobile crash-free-session rate gaps: improve from 98.1% to 99.5% (counter-balance for shipping fast).
- Initiatives (not KRs): ship redesign, add biometric login, fix top 10 crashes.
See examples/saas-growth-okrs.md and examples/rewrite-weak-okrs.md for full examples.
Best Practices
- Limit to 3-5 Objectives per team, 2-5 Key Results per Objective.
- Objectives are qualitative and inspiring; Key Results are quantitative and boring-precise.
- Always record a baseline and a deadline within the OKR period.
- Separate Initiatives (the work) from Key Results (the result). Track both, grade only KRs.
- Mark each set as committed (must hit 100%) or aspirational (target ~70%).
- Make OKRs public across the org; cascade by alignment, not literal copy-paste.
- Set, then grade at period end on a 0.0-1.0 scale; reflect, don't punish stretch misses.
Common Pitfalls
- Task lists masquerading as KRs ("Launch v2", "Hire 3 engineers") — these are initiatives.
- No baseline — "Increase revenue" with no start point can't be scored.
- Sandbagging — targets the team already knows they'll hit; nothing learned.
- Too many OKRs — everything is a priority, so nothing is.
- Vanity metrics — page views, raw signups, lines of code.
- Objectives with numbers — that's a key result wearing an objective's hat.
- Stitched objectives — "Grow revenue AND improve quality AND hire" — split them.
- Set-and-forget — no mid-period check-ins or end-period grading.
Supporting Files
references/outcome-vs-output.md— how to convert outputs into outcomes, the "so that" laddering technique, and a large lookup table.references/objective-patterns.md— sentence patterns and a bank of strong/weak objective examples.references/key-result-formulas.md— KR metric types, the formula, counter-metrics, and verb lists.references/review-rubric.md— the scoring rubric to grade any draft OKR set.templates/okr-template.md— fill-in template for presenting a final OKR set.examples/saas-growth-okrs.md— a complete company → team cascade example.examples/rewrite-weak-okrs.md— before/after rewrites of common bad OKRs.scripts/okr_lint.py— runnable linter that flags task-like, baseline-less, or number-less key results.
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
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.

