Retro

by Rootly-AI-Labs65832aa6ff7aNo licenseListed Oct 8, 2026Updated Oct 8, 2026

[experimental] Generate a structured post-incident retrospective from incident data. Forked-subagent flow may not have MCP access in all Claude Code contexts.

Instructions onlyDevOps & Cloud

AI-generated overview

Generates a structured post-incident retrospective in markdown from Rootly incident data.

What it does: Pulls an incident record, alert timeline and related incidents through Rootly MCP tools, then writes a copy-pasteable markdown retrospective. The output covers summary, impact, timeline, root cause analysis, contributing factors, what went well, what could be improved, action items and an optional recurring-pattern note. It warns when an incident is still active and marks missing information as unavailable instead of guessing.
When to use it: Use after an incident has been resolved, when you need a consistent retrospective document for review or follow-up. It is also useful for checking whether similar incidents have recurred in the past 90 days. If the forked agent cannot reach the MCP tools, a basic incident summary is suggested instead.
Requirements: Requires the Rootly MCP tools (mcprootly*) and an incident ID; the skill is instructions only and ships no scripts. The forked-subagent flow may not have MCP access in all Claude Code contexts.

Retrospective Generator (experimental)

Experimental: this skill uses context: fork to delegate to the retro-analyst agent. In some Claude Code contexts the forked subagent does not inherit the plugin's MCP tools. If the agent reports MCP tools unavailable, use /rootly:brief <incident> for a basic incident summary instead.

You are generating a structured post-incident retrospective. The output should be copy-pasteable markdown.

Workflow

1. Get Incident Data

The incident ID should be provided in $ARGUMENTS. If not provided, ask the user for it.

Call mcp__rootly__getIncident for the full incident record
Check the incident status:
- If status is started (still active), warn the user: "This incident is still active. Retrospectives are typically done after resolution. Continue anyway?" Wait for confirmation before proceeding.

2. Gather Context

Call mcp__rootly__get_alert_by_short_id or alert search tools for the alert timeline
Call mcp__rootly__find_related_incidents to check for recurring patterns

3. Generate Retrospective

Output as clean, copy-pasteable markdown:

markdown

# Retrospective: [Incident Title]
**Incident ID**: [id]**Date**: [date]**Duration**: [start] to [end] ([total duration])**Severity**: [severity]
## Summary[1-2 sentence summary of what happened]
## Impact- **Duration**: [time from detection to resolution]- **Affected services**: [list]- **Severity**: [level]- **User impact**: [description if available]
## Timeline| Time | Event ||------|-------|| [time] | [event] || ... | ... |
## Root Cause Analysis[Analysis based on incident data, alerts, and resolution steps]
## Contributing Factors- [Factor 1]- [Factor 2]
## What Went Well- [Positive aspect 1]- [Positive aspect 2]
## What Could Be Improved- [Improvement area 1]- [Improvement area 2]
## Action Items| Action | Owner | Priority ||--------|-------|----------|| [action] | [owner if identifiable] | [high/medium/low] |
## Pattern Note[If find_related_incidents shows similar past incidents:]"This is the Nth incident of this type in the last 90 days. Consider systemic fixes."[If no similar incidents: omit this section]

# Retrospective: [Incident Title]
**Incident ID**: [id]**Date**: [date]**Duration**: [start] to [end] ([total duration])**Severity**: [severity]
## Summary[1-2 sentence summary of what happened]
## Impact- **Duration**: [time from detection to resolution]- **Affected services**: [list]- **Severity**: [level]- **User impact**: [description if available]
## Timeline| Time | Event ||------|-------|| [time] | [event] || ... | ... |
## Root Cause Analysis[Analysis based on incident data, alerts, and resolution steps]
## Contributing Factors- [Factor 1]- [Factor 2]
## What Went Well- [Positive aspect 1]- [Positive aspect 2]
## What Could Be Improved- [Improvement area 1]- [Improvement area 2]
## Action Items| Action | Owner | Priority ||--------|-------|----------|| [action] | [owner if identifiable] | [high/medium/low] |
## Pattern Note[If find_related_incidents shows similar past incidents:]"This is the Nth incident of this type in the last 90 days. Consider systemic fixes."[If no similar incidents: omit this section]

Base the analysis on actual incident data. Do not fabricate details. If information is unavailable, note it as "Not available in incident data" rather than guessing.

Source and attribution

Source:Rootly-AI-Labs/rootly-claude-plugininskills/retroat commit65832aa

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Retro

Retrospective Generator (experimental)

Workflow

1. Get Incident Data

2. Gather Context

3. Generate Retrospective

Source and attribution

More from Rootly-AI-Labs/rootly-claude-plugin

Trend

Test

Swap

Status

Respond

Oncall

More in DevOps & Cloud

M5 Onboard

Google Agents Cli Publish

Spanner Basics

Secops Cases

Managed Airflow Migrations

Managed Airflow Dag Troubleshooting