本文へ移動
cccskills
無料GitHub で公開

okr-writer

Write OKRs (Objectives and Key Results). Use when the user says "write OKRs", "help me set goals", "create objectives and key results", "quarterly goals", "team OKRs", "I need to define success for this quarter", "Doerr method", or wants to translate a strategic direction into measurable targets - even if they don't explicitly say "OKRs".

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.3 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Overview

Based on "Measure What Matters" by John Doerr, who brought OKRs from Intel to Google. Doerr's core distinction: Objectives are the "what" (inspirational, qualitative), Key Results are the "how we know" (measurable, binary at quarter end). CFRs - Conversations, Feedback, Recognition - are what make OKRs work in practice.

Two types of OKRs (Doerr):

  • Committed OKRs - Must be achieved 100%. Missing them requires explanation.
  • Aspirational OKRs - Stretch goals. 70% attainment is success. 100% means you aimed too low.

Workflow

Step 1: Identify the type

Ask: is this a committed OKR (must hit) or aspirational (stretch)? This changes how you write the Key Results.

Step 2: Write the Objective

  • Inspirational and qualitative
  • Memorable - a team should be able to recite it
  • Time-bound to the quarter
  • Answers: "What do we want to be true in 90 days?"

Doerr's test: "Does this objective make you uncomfortable in a good way?" If it's easy, it's not aspirational enough.

Step 3: Write 3-5 Key Results per Objective

Each KR must:

  • Be measurable with a specific number
  • Be outcome-based, not output-based ("30% reduction in churn" not "launch retention feature")
  • Have a baseline and a target
  • Be independently verifiable

Format: [Metric] from [baseline] to [target]

Step 4: Apply the Doerr CFR check

For each OKR set, identify:

  • Conversation: What weekly check-in question will track this?
  • Feedback: How will the team know mid-quarter if they're on track?
  • Recognition: What does hitting this KR mean for the team?

OKRs without CFRs become forgotten spreadsheets.

Step 5: Check vertical alignment

Doerr's "cascading" principle: team OKRs should visibly connect to company OKRs. Flag any team OKR that doesn't trace to a company-level objective.

Step 6: Flag missing baselines

"You'll need a baseline for this KR. Who owns this metric and can pull the current number?"

Anti-Patterns

1. Output-based Key Results Bad: "Launch new onboarding flow by March 31" Good: "Increase onboarding completion rate from 45% to 70%" Shipping is activity. Outcomes are results.

2. Treating aspirational OKRs as committed Bad: Team marks 70% attainment as failure because "we didn't hit it." Good: For aspirational OKRs, 70% = success. Recalibrate at quarter end, don't punish stretch.

3. Too many Objectives Bad: 5-7 Objectives per team. Good: 1-3 Objectives max. Doerr: "A few well-chosen OKRs send a clear message about what we say no to."

4. No baseline Bad: "Improve conversion rate to 10%" Good: "Improve conversion rate from 6% to 10%"

Quality Checklist

  • OKR type stated: committed or aspirational
  • Objective is inspirational and qualitative (not a task)
  • 3-5 Key Results per Objective
  • Each KR has baseline and target
  • KRs are outcome-based, not output-based
  • CFR check done: conversation, feedback, recognition defined
  • Team OKRs connect to company OKRs
  • Missing baselines flagged with owners

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Design clean and consistent APIs. Use when the user says "design an API", "API design review", "design these endpoints", "REST API for X", "GraphQL schema", "API contract", "how should this endpoint work", "review my API design", or wants to create or improve an API interface - even if they don't explicitly say "API design".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

qa-aman のスキルをすべて見る

このスキルの問題を報告する