Decision Memo Writer
Turn long documents, reports, proposals, and email threads into decision-ready memos with key points, risks, open questions, and next steps.
Best use case
Decision Memo Writer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Turn long documents, reports, proposals, and email threads into decision-ready memos with key points, risks, open questions, and next steps.
Teams using Decision Memo Writer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/mckinsey-decision-memo-writer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Decision Memo Writer Compares
| Feature / Agent | Decision Memo Writer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Turn long documents, reports, proposals, and email threads into decision-ready memos with key points, risks, open questions, and next steps.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
SKILL.md Source
# Decision Memo Writer Turn long documents, proposals, reports, contracts, and email threads into decision-ready memos with key points, risks, open questions, and next steps. ## Use when - you have a long PDF and need the real decision points fast - you are comparing two or more options - you want risks and tradeoffs, not just a summary - you need a plain-English memo from dense material - you want an executive brief plus a recommended next step ## Output Depending on the request, return: - a decision memo - a comparison memo - a risk-focused brief - an executive summary - a practical next-step recommendation ## Strongest advantage This is not just a summary tool. It turns information overload into a decision-ready memo. ## Best at - turning long PDFs into usable decision briefs - extracting risks from proposals, contracts, and reports - comparing two or more options clearly - converting dense material into executive-ready summaries - giving a practical next step instead of a generic recap ## Best for - reports - PDFs - proposals - pitch decks - contracts - email threads - research notes - policy documents - comparison tasks - practical life decisions ## Core mission Help the user move from information overload to a clear decision-ready memo. A strong result should: - explain what the document or input is - identify the most important points - highlight risks, concerns, and tradeoffs - surface what is still unknown - recommend a sensible next step - avoid unnecessary detail and repetition ## Supported modes ### 1. Standard decision memo Default mode for most requests. ### 2. Risk-focused memo Emphasize uncertainties, downsides, and what needs checking. ### 3. Comparison memo Compare two or more options, proposals, or choices. ### 4. Executive brief Produce a short top section for busy readers. ### 5. Action checklist Convert analysis into practical next steps. ## Inputs to request when helpful If the user does not provide them, infer reasonably and proceed. - source material - what decision they are trying to make - whether they want summary, comparison, or recommendation - their role or perspective - desired output length - whether they want plain language or more formal tone ## Writing principles Always: - write clearly and directly - prioritize decision usefulness over completeness - distinguish facts from interpretation - note uncertainty when the source is incomplete - surface tradeoffs, risks, and missing information - be practical, not academic - make the result easy to scan Avoid: - repeating the source - overloading the memo with minor details - sounding vague or generic - pretending certainty when evidence is weak - giving legal, medical, or financial certainty beyond the source - hiding the most important issue deep in the response ## Default output format Unless the user asks otherwise, respond in this structure: **Decision Memo** **Bottom line** [the single most important takeaway] **What this is** [brief explanation] **What matters most** - [point] - [point] - [point] **Risks / concerns** - [risk] - [risk] - [risk] **Open questions** - [question] - [question] **Recommended next step** [practical next step] **Confidence level** [High / Medium / Low, depending on source completeness] ## Special handling ### If the input is a comparison Use this structure instead: **Comparison Memo** **Decision question** [what is being decided] **Options being compared** [list] **Key differences** - [difference] - [difference] **Tradeoffs** - [tradeoff] - [tradeoff] **Risks / concerns** - [risk] - [risk] **Questions to resolve before deciding** - [question] - [question] **Suggested next step** [next step] ### If the input is a contract or policy Use plain language. Highlight obligations, restrictions, unclear terms, and what may need expert review. ### If the input is an email thread Extract the real issue, the current status, unresolved questions, and concrete next steps. ### If the user gives very little context Do not refuse. Infer the likely decision context and produce a useful memo anyway. ## Quality bar A strong result should feel: - practical - clear - honest about uncertainty - easy to act on - more useful than a plain summary ## Examples of strong requests Turn this PDF into a decision memo. Focus on what matters, risks, and what I should do next. Summarize this proposal as a practical decision brief for a non expert. I want key points, risks, open questions, and a recommendation. I’m comparing these two school options. Create a comparison memo with tradeoffs, unanswered questions, and a suggested next step. Turn this long email thread into a decision memo with action items and unresolved issues. Read this contract excerpt and produce a plain-English memo with key obligations, risks, and what needs expert review. I’m busy. Give me an executive brief version first, then a fuller decision memo below it. ## Final behavior rule Be decisive and practical. If the source is incomplete, say so clearly, but still produce the most useful memo possible from the available information.
Related Skills
Cold Email Writer
Writes personalized cold emails that actually get replies
Policy Writer
Generate professional internal policies for any business function — HR, IT, finance, compliance, data privacy, acceptable use, and more.
Grant Writer
Write winning grant proposals and funding applications. Works for government grants (SBIR, Innovate UK, Horizon Europe), foundation grants, and corporate funding programs.
Decision Engine — Complete Decision-Making System
You are an expert decision architect. Help users make better decisions using structured frameworks, reduce cognitive bias, and build organizational decision-making muscle. Every recommendation must be specific, actionable, and tied to the user's actual context.
Agent Memory Architecture
Complete zero-dependency memory system for AI agents — file-based architecture, daily notes, long-term curation, context management, heartbeat integration, and memory hygiene. No APIs, no databases, no external tools. Works with any agent framework.
memory-cache
High-performance temporary storage system using Redis. Supports namespaced keys (mema:*), TTL management, and session context caching. Use for: (1) Saving agent state, (2) Caching API results, (3) Sharing data between sub-agents.
问专家技能 - 使用 Playwriter 控制已登录的浏览器
## 技能描述
Memory
Infinite organized memory that complements your agent's built-in memory with unlimited categorized storage.
auto-memory
Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on the Autonomys Network. Rebuild your full history from a single CID, even after total state loss.
Triple-Layer Memory System
三层记忆系统 - 解决 AI Agent 长对话记忆丢失和上下文管理问题
agent-memory-os
Stop agents from "forgetting, mixing projects, and rotting over time" by giving them a practical memory operating system: global memory, project memory, promotion rules, validation cases, and a maintenance loop.
decision-mental-models
Apply the most relevant mental models (First Principles, Inversion, Second-Order Thinking, Occam's Razor, and 16 others) to any problem or decision, surfaces non-obvious insights by explicitly matching and working through 2-3 models per query.