← Back to Skills Marketplace
Incident Postmortem Assistant
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
158
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install incident-postmortem-assistant
Description
将事故线索整理成复盘草案，区分根因、诱因、放大器、影响与修复动作。；use for incident, postmortem, sre workflows；do not use for 归责个人, 篡改时间线.
README (SKILL.md)
事故复盘助手
你是什么
你是“事故复盘助手”这个独立 Skill，负责：将事故线索整理成复盘草案，区分根因、诱因、放大器、影响与修复动作。
Routing
适合使用的情况
- 把事故记录整理成 postmortem 草案
- 区分根因和诱因
- 输入通常包含：时间线、告警、处理记录、影响面
- 优先产出：事故摘要、时间线、后续改进
不适合使用的情况
- 不要归责个人
- 不要篡改时间线
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。
工作规则
- 先把用户提供的信息重组成任务书，再输出结构化结果。
- 缺信息时，优先显式列出“待确认项”，而不是直接编造。
- 默认先给“可审阅草案”，再给“可执行清单”。
- 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
- 如运行环境允许 shell / exec，可使用：
python3 "{baseDir}/scripts/run.py" --input \x3C输入文件> --output \x3C输出文件>
- 如当前环境不能执行脚本，仍要基于
{baseDir}/resources/template.md与{baseDir}/resources/spec.json的结构直接产出文本。
标准输出结构
请尽量按以下结构组织结果：
- 事故摘要
- 时间线
- 根因/诱因/放大器
- 影响分析
- 处理动作
- 后续改进
本地资源
- 规范文件：
{baseDir}/resources/spec.json - 输出模板：
{baseDir}/resources/template.md - 示例输入输出：
{baseDir}/examples/ - 冒烟测试：
{baseDir}/tests/smoke-test.md
安全边界
- 默认采用无责复盘语言。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。
Usage Guidance
This skill appears to do what it says: it formats incident inputs into a structured postmortem and can optionally run a local Python script to audit files or directories. Before running the script, review scripts/run.py (it is included and readable) and: 1) pass only intended files or directories (avoid pointing it at your whole filesystem or sensitive folders); 2) use --dry-run first or run it against example inputs; 3) sanitize sensitive data before feeding it in; and 4) if you plan to let the agent run the script autonomously, be aware the agent could read any paths you direct it to — restrict inputs and review outputs before any external sharing.
Capability Analysis
Type: OpenClaw Skill
Name: incident-postmortem-assistant
Version: 1.0.0
The bundle is a legitimate utility designed to assist SREs in generating incident postmortem reports. The core logic in `scripts/run.py` processes local text, CSV, or directory inputs to extract timelines and root causes, and even includes a safety-oriented 'pattern_audit' mode that scans for leaked secrets or dangerous commands (e.g., `curl|bash`) to highlight them for review. The script uses standard Python libraries, lacks network capabilities, and contains no evidence of obfuscation, data exfiltration, or malicious intent.
Capability Assessment
Purpose & Capability
Name/description (postmortem assistant) align with the included resources and the single Python script. Requiring only python3 is proportional: the script produces structured Markdown reports and audits directories/files which fits incident analysis and repo-level reviews.
Instruction Scope
SKILL.md explicitly permits running the bundled script when shell/exec is available and also says to produce output from bundled template if execution is not possible. The script accepts a path or directory and will read and sample many text file types (md, json, py, sh, csv, etc.). Reading local incident logs and repo files is expected, but running the script with a path that points broadly (e.g., / or home) will cause it to read many local files — be deliberate about what path you pass and prefer dry-run or explicit files.
Install Mechanism
No install spec; instruction-only plus a local Python script. No external downloads or package installs are present.
Credentials
No environment variables or credentials required. The script only uses local file I/O and standard-library parsing; this matches the described purpose.
Persistence & Privilege
always is false and the skill does not request elevated or persistent platform privileges. The script can write an output file (normal); it does not modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install incident-postmortem-assistant - After installation, invoke the skill by name or use
/incident-postmortem-assistant - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the Incident Postmortem Assistant skill.
- Automatically organizes incident clues into structured postmortem drafts, distinguishing root cause, contributing factors, amplifiers, impacts, and remediation actions.
- Emphasizes reviewable drafts and improvement checklists, prioritizing accuracy and transparency.
- Explicitly separates suitable use cases (incident summarization, timeline drafting, etc.) from unsuitable ones (blame assignment, timeline tampering, direct writes to external systems).
- Responds with tasks and clarifies missing information instead of speculating.
- Includes strict safety boundaries against executing high-risk actions or fabricating details; adopts a collaborative “blameless” review language.
Metadata
Frequently Asked Questions
What is Incident Postmortem Assistant?
将事故线索整理成复盘草案，区分根因、诱因、放大器、影响与修复动作。；use for incident, postmortem, sre workflows；do not use for 归责个人, 篡改时间线. It is an AI Agent Skill for Claude Code / OpenClaw, with 158 downloads so far.
How do I install Incident Postmortem Assistant?
Run "/install incident-postmortem-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Incident Postmortem Assistant free?
Yes, Incident Postmortem Assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Incident Postmortem Assistant support?
Incident Postmortem Assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Incident Postmortem Assistant?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills