Imagine the project already failed, then work backward to find why. More powerful than risk assessment because it assumes failure is certain. Use when user says "pre-mortem", "premortem", "imagine this failed", "what could go wrong", "risk analysis", "before we launch", "stress test", "what would kill this", "project risks".
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install pre-mortem-analyst或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install pre-mortem-analyst⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/pre-mortem-analyst/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: pre-mortem-analyst description: Imagine the project already failed, then work backward to find why. More powerful than risk assessment because it assumes failure is certain. Use when user says "pre-mortem", "premortem", "imagine this failed", "what could go wrong", "risk analysis", "before we launch", "stress test", "what would kill this", "project risks". ---
Risk Assessment: "What MIGHT go wrong?" → Optimism bias filters answers Pre-Mortem: "It's 6 months later. It FAILED. Why?" → Liberates honest analysis
Research: Pre-mortems increase problem identification by 30%.
PROJECT: [Name]
FAILURE SCENARIO: "It's [date]. [Project] has completely failed."
WHY IT FAILED:
👥 PEOPLE: [Cause] - L×I: H/H | Prevent: [x] | Warning: [y]
⚙️ PROCESS: [Cause] - L×I: M/H | Prevent: [x] | Warning: [y]
💻 TECHNOLOGY: [Cause] - L×I: L/H | Prevent: [x] | Warning: [y]
🌍 EXTERNAL: [Cause] - L×I: M/M | Prevent: [x] | Warning: [y]
TOP 3 PRIORITIES:
1. [Risk] → [Specific action]
2. [Risk] → [Specific action]
3. [Risk] → [Specific action]
WARNING SIGNS TO MONITOR:
□ [Early indicator 1]
□ [Early indicator 2]| Category | Common Causes | |----------|---------------| | People | Key person leaves, skill gaps, misalignment, low buy-in | | Process | Aggressive timeline, scope creep, dependency issues | | Tech | Doesn't scale, integration fails, security breach | | External | Market shift, competitor move, regulation change |
Compounds with:
--- See references/examples.md for Artem-specific pre-mortems
安装 Pre-Mortem Analyst 后，可以对 AI 说这些话来触发它
Help me get started with Pre-Mortem Analyst
Explains what Pre-Mortem Analyst does, walks through the setup, and runs a quick demo based on your current project
Use Pre-Mortem Analyst to imagine the project already failed, then work backward to find why
Invokes Pre-Mortem Analyst with the right parameters and returns the result directly in the conversation
What can I do with Pre-Mortem Analyst in my data & analytics workflow?
Lists the top use cases for Pre-Mortem Analyst, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/pre-mortem-analyst/ 目录（个人级，所有项目可用），或 .claude/skills/pre-mortem-analyst/（项目级）。重启 AI 客户端后，用 /pre-mortem-analyst 主动调用，或让 AI 根据上下文自动发现并使用。
Pre-Mortem Analyst 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Pre-Mortem Analyst 可免费安装使用。请查阅仓库了解许可证信息。
Imagine the project already failed, then work backward to find why. More powerful than risk assessment because it assumes failure is certain. Use when user says "pre-mortem", "premortem", "imagine this failed", "what could go wrong", "risk analysis", "before we launch", "stress test", "what would kill this", "project risks".
Automate my data & analytics tasks using Pre-Mortem Analyst
Identifies repetitive steps in your workflow and sets up Pre-Mortem Analyst to handle them automatically
Pre-Mortem Analyst 属于「Data & Analytics」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。