incident-retrospective

Generate structured blameless postmortems from incident data in Markdown.

12|2|Updated Apr 21, 2026
One-click install
npx skills add https://github.com/haomingz/kimi-skills --skill incident-retrospective
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: incident-retrospective
Source: https://github.com/haomingz/kimi-skills/tree/main/skills/incident-retrospective
Command: npx skills add https://github.com/haomingz/kimi-skills --skill incident-retrospective

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Blameless Postmortems are critical for learning from incidents, but teams often struggle to collect consistent facts, perform root-cause analysis, and produce professional, shareable reports. This Skill provides a guided, six-step SOP to collect incident data, analyze root causes with 5 Whys, define SMART action items, and generate production-ready postmortem documents.

Core Features & Use Cases

  • Interactive, question-driven data collection aligned with best practices to ensure completeness and consistency.
  • Structured outputs that include incident overview, timeline, root-cause analysis, action items, and lessons learned for easy sharing and archival.
  • Flexible workflows: interactive prompts or JSON input, and outputs in Chinese or English to fit diverse teams.

Quick Start

Provide incident details or use the built-in interactive prompts to generate a formatted postmortem.

Frequently Asked Questions about incident-retrospective

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a blameless postmortem after an incident?

To write a blameless postmortem, use a structured process that collects incident facts, applies the 5 Whys for root-cause analysis, and generates a shareable report with action items. This ensures teams learn from incidents without assigning blame.

What is the 5 Whys technique for root-cause analysis?

The 5 Whys technique for root-cause analysis involves asking 'why' iteratively to drill down into the fundamental cause of an incident. It moves beyond surface-level symptoms to identify systemic issues for effective post-incident reviews.

Can I generate a postmortem report from JSON incident data?

Yes, you can generate a postmortem report from JSON incident data. Providing structured JSON input skips interactive data collection and directly outputs a formatted Markdown document containing the timeline, root cause, and lessons learned.

What sections should be included in an incident report?

An incident report should include sections for an incident overview, a detailed timeline, root-cause analysis, SMART action items, and lessons learned. These structured outputs ensure completeness and consistency for archival and sharing.

Does this postmortem generator support output in Chinese and English?

Yes, this postmortem generator supports output in both Chinese and English. It fits diverse on-call teams by producing structured Markdown incident reports in the preferred language of your organization.

How do I define SMART action items for an RCA exercise?

To define SMART action items for an RCA exercise, ensure each corrective task is Specific, Measurable, Achievable, Relevant, and Time-bound. This translates root-cause findings into accountable engineering improvements.