本文へ移動
cccskills
無料GitHub で公開

okr-generator

Generates structured OKR plans (Objectives and Key Results) for teams and companies following Google/Intel methodology. Takes company goals, team function, quarter, and current metrics to produce a comprehensive okr-plan.md with objectives, key results, scoring criteria, alignment mapping, tracking cadence, and retrospective templates.

インストール方法を見る

含まれるファイル(5)

  • SKILL.md3.6 KB
  • references/best-practices.md3.1 KB
  • references/inputs.md1.4 KB
  • references/methodology.md2.0 KB
  • references/output-template.md11.4 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。

OKR Generator

Generate a comprehensive, actionable okr-plan.md from user inputs, applying the Google/Intel OKR framework.

Contents

  • references/methodology.md -- Core OKR principles (non-negotiable rules to apply).
  • references/inputs.md -- The four required inputs plus optional context.
  • references/output-template.md -- Exact structure of the generated okr-plan.md.
  • references/best-practices.md -- Appendix content (common mistakes, OKR cycle, grading by KR type, reading list).

Workflow

  1. Read references/inputs.md. Collect the four required inputs: company goals, team function, quarter/period, current metrics/baseline. If any are missing, ask for them. Never fabricate baselines.
  2. Read references/methodology.md and apply every core principle. Objectives are qualitative and inspirational (no numbers); key results are quantitative and measurable (always a number).
  3. Design 3-5 objectives. Attach 3-4 key results to each. Mark each as Committed or Aspirational, targeting roughly 60-70% committed and 30-40% aspirational across the plan.
  4. Map every objective to at least one company goal. Build both the alignment table and the cascade diagram. Drop any objective that does not ladder up.
  5. Write a 5-level scoring rubric (0.0, 0.3, 0.5, 0.7, 1.0) for every key result, with KR-specific descriptions.
  6. List initiatives separately from key results. Initiatives are the activities ("how"); key results are the measured outcomes ("what"). Never conflate them.
  7. Document dependencies and risks. Assign a single owner role to every objective and key result.
  8. Define the tracking cadence (weekly check-in, monthly scoring, quarterly retrospective) and include all three templates plus the appendix from references/best-practices.md.
  9. Generate the full document per references/output-template.md as okr-plan.md in the working directory (or a user-specified path). Produce at least 400 substantive lines, no filler.
  10. Summarize the plan: objective count and committed/aspirational split, the most ambitious key result, key dependencies/risks, and the recommended first action.

Generation Rules

  • Validate inputs before generating; base all targets on the provided baselines (committed: ~10-30% improvement; aspirational: ~50-100%+ or breakthrough).
  • Objectives qualitative, key results quantitative. Rewrite any KR lacking a number.
  • Every objective maps to a company goal; every KR has a single owner and a scoring rubric.
  • Never connect OKR scores to compensation, promotion, or performance reviews. Include the decoupling reminder in the scoring guide.
  • Include all templates in full (weekly, monthly, quarterly). Do not abbreviate.

Edge Cases

  • Multiple teams: Generate one plan per team in its own file (e.g., okr-plan-engineering.md, okr-plan-marketing.md).
  • Company-level OKRs: Remove team-to-company alignment; show department-level cascade instead.
  • Mid-quarter adjustment: Preserve original OKRs, mark adjusted ones with [ADJUSTED], and include rationale per change.
  • Previous-quarter scores provided: Calibrate ambition -- if the team scored 1.0 on everything, push harder; if below 0.4, investigate whether the cause was execution or target-setting.

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

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

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。

OneWave-AI/claude-skills3402026年10月2日 更新

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

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。

OneWave-AI/claude-skills3402026年10月2日 更新

Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

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。

OneWave-AI/claude-skills3402026年10月2日 更新

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

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。

OneWave-AI/claude-skills3402026年10月2日 更新

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

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。

OneWave-AI/claude-skills3402026年10月2日 更新

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

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。

OneWave-AI/claude-skills3402026年10月2日 更新

OneWave-AI のスキルをすべて見る

このスキルの問題を報告する