跳到正文
FunCoding

搜索

搜索文档、智能体、博客、Skill 和 MCP

brainstorm-okrs

Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.

AI 与智能体27kpm-execution/skills/brainstorm-okrs/SKILL.md

安装

将以下指令发送给 Claude Code、Codex 或 Cursor,智能体会先检查内容的安全性,经你确认后再安装。

读取 https://funcoding.ai/skills/phuryn/pm-skills/brainstorm-okrs/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.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

相似的 Skill

mcp-builder
官方
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI 与智能体

internal-comms
官方
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI 与智能体

brand-guidelines
官方
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI 与智能体

algorithmic-art
官方
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI 与智能体

academy-guide
官方
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI 与智能体

template-skill
官方
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI 与智能体