Incident postmortem drafter

Skill sisodiabhumca/agent-skills/skills/incident-postmortem-drafter

Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.

Install

npx -y skills add sisodiabhumca/agent-skills --skill incident-postmortem-drafter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Vendor-neutral skill to draft a blameless incident postmortem from structured incident inputs (timeline, impact, contributing factors) and produce an actionable report.

SKILL.md

1.6 KB, as published. Nobody here has run it

When to invoke

You have an outage/incident timeline and need a consistent postmortem draft.
You want to standardize incident write-ups across teams.

Inputs needed

Incident metadata: title, date/time, duration, severity.
Impact summary: customer impact, internal impact, key metrics.
Timeline of events (timestamp + event).
Contributing factors (optional) and what went well/poorly.
Action items (optional; can be generated placeholders).

Workflow

Validate required fields and normalize timestamps.
Derive key milestones (start, detection, mitigation, resolution).
Summarize impact and customer communication.
Generate a blameless narrative: what happened and why (avoid personal attribution).
Produce corrective and preventive actions (CPAs) with owners and due dates if provided; otherwise create placeholders.

Output format

Markdown report with:

Summary
Customer impact
Timeline
Root cause / contributing factors (blameless)
Detection and response analysis
What went well / what didn’t
Action items (table)
Follow-ups and references

Guardrails

Do not assign blame to individuals; focus on systems and process.
If inputs are missing, call them out explicitly rather than inventing facts.
Keep timestamps and units consistent.

Reference code

postmortem_drafter.py reads a JSON incident file and writes a Markdown postmortem.

Gives 0 of the 12 instructions most incident response skills give

Counted across 224 of the 224 authors here whose files we hold, read 2026-08-06

Conduct a blameless postmortem within 48 hoursin 24 of 224, across 14 files
perform root cause analysis using five whysin 24 of 224, across 20 files
write a blameless postmortemin 22 of 224, across 19 files
Update stakeholders every 15 to 30 minutesin 19 of 224, across 9 files
assign an owner and due date to every action itemin 18 of 224
Classify incident severity within 5 minutesin 17 of 224, across 7 files
Create a post-mortem documentin 17 of 224, across 14 files
Assign all action items with deadlinesin 14 of 224, across 6 files
Implement immediate mitigation prioritizing user restorationin 13 of 224, across 3 files
assign one incident commanderin 12 of 224
Stop and ask for clarification if inputs are missingin 10 of 224, across 2 files
Escalate earlyin 10 of 224, across 2 files

Said here and by no other author read

validate required fields and normalize timestamps
derive key milestones
summarize impact and customer communication
create placeholder action items if inputs are missing
call out missing inputs explicitly

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.