CtrlK
BlogDocsLog inGet started
Tessl Logo

postmortem-writing

Write effective blameless postmortems with root cause analysis, timelines, and action items. Use when conducting incident reviews, writing postmortem documents, or improving incident response processes.

81

1.17x
Quality

71%

Does it follow best practices?

Impact

99%

1.17x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/incident-response/skills/postmortem-writing/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

31%

Storefront Checkout Outage — Post-Incident Write-Up

Standard postmortem document

Criteria
Without context
With context

Blameless language

100%

100%

Required header fields

100%

100%

Executive Summary present

100%

100%

UTC timeline table

100%

100%

RCA subsections

62%

100%

Contributing factors listed

100%

100%

Detection section

66%

100%

Impact subsections

37%

100%

Lessons Learned subsections

25%

100%

Action items table format

50%

100%

No orphan action items

57%

100%

Appendix section

50%

100%

Response section present

50%

100%

99%

2%

Authentication Service Failure — Root Cause Deep Dive

5 Whys root cause analysis

Criteria
Without context
With context

5 Whys structure

100%

100%

Evidence per step

100%

100%

Problem statement

100%

100%

Multiple root causes

100%

100%

Root cause classification

100%

75%

Systemic improvements table

75%

100%

Reaches organisational depth

100%

100%

Blameless framing

100%

100%

Proximate vs systemic distinction

100%

100%

Actionable improvements

100%

100%

100%

13%

Data Pipeline Incident — Facilitate the Postmortem Review Meeting

Postmortem meeting facilitation

Criteria
Without context
With context

5 meeting phases

100%

100%

Correct time allocations

50%

100%

Total 60 minutes

100%

100%

Blameless opening

100%

100%

Redirect blame to systems

100%

100%

Encourage quiet participants

100%

100%

Time-box tangents

100%

100%

Document dissenting views

28%

100%

Action item format with owners

70%

100%

Closing confirms owners

100%

100%

Anti-pattern avoidance

100%

100%

Analysis discussion questions

100%

100%

Repository
wshobson/agents
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.