postmortem-writing

Comprehensive guide to writing effective, blameless postmortems that drive organizational learning and prevent incident recurrence.

Quality

41%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/postmortem-writing/SKILL.md

Quality

Content

46%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides rich, concrete postmortem templates and facilitation guidance, but suffers from severe verbosity by inlining everything into a single massive file. The actual Instructions section is generic boilerplate that doesn't leverage the detailed content below it, and the skill references a bundle file that doesn't exist. The content would be significantly improved by extracting templates into separate files and replacing the generic instructions with a clear, concise workflow for Claude to follow.

Suggestions

Extract the three postmortem templates and the facilitation guide into separate referenced files (e.g., templates/standard.md, templates/5-whys.md, templates/quick.md, guides/facilitation.md) and keep only a concise overview with navigation in SKILL.md.

Replace the generic Instructions section ('Apply relevant best practices and validate outcomes') with a specific decision workflow: e.g., determine severity → select template → gather inputs → draft sections → review checklist.

Either create the referenced 'resources/implementation-playbook.md' bundle file or remove the reference to avoid broken navigation.

Remove the blameless culture comparison table and concept explanations that Claude already understands — instead, just state 'Use blameless framing: focus on systems and conditions, not individuals.'

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines, with extensive template content inlined that Claude doesn't need spelled out in such detail. The blameless culture table explains concepts Claude already understands, and the full postmortem templates with fictional examples are excessively padded. Much of this could be in referenced files or dramatically condensed.	2 / 5
Actionability	The templates are concrete and copy-paste ready with specific fields, example data, and structured formats. The facilitation guide provides specific time-boxed steps. However, the core 'Instructions' section is extremely vague ('Apply relevant best practices and validate outcomes') and doesn't give Claude specific guidance on how to actually write a postmortem — the templates do the heavy lifting.	4 / 5
Workflow Clarity	The Quick Start timeline provides a rough sequence, and the facilitation guide has a clear meeting structure. However, there's no explicit workflow for Claude to follow when writing a postmortem — no validation steps, no decision points for which template to use, and no feedback loops. The Instructions section is generic boilerplate rather than a clear process.	3 / 5
Progressive Disclosure	The skill references 'resources/implementation-playbook.md' but no bundle files exist. All three full templates are inlined in the main SKILL.md creating a monolithic document. The templates, facilitation guide, and anti-patterns should be in separate referenced files, with the main skill providing a concise overview and navigation.	2 / 5
	Total	11 / 20 Passed

Description

36%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies its domain (postmortems) but reads more like a document subtitle than a functional skill description. It lacks concrete actions, explicit trigger conditions, and natural user language variations that would help Claude reliably select it from a pool of skills.

Suggestions

Add a 'Use when...' clause with trigger terms like 'incident report', 'post-incident review', 'RCA', 'root cause analysis', 'outage', or 'retrospective'.

List specific concrete actions such as 'structure incident timelines, identify root causes, draft action items, write blameless narratives, create executive summaries'.

Include synonym coverage for natural user phrases: 'postmortem', 'post-mortem', 'incident review', 'after-action report', 'retrospective'.

Dimension	Reasoning	Score
Specificity	Names the domain (postmortems) but actions are minimal and generic - 'writing effective, blameless postmortems' is one vague action. No concrete specifics like 'structure timeline sections, identify root causes, draft action items, write executive summaries.'	2 / 5
Completeness	Has a vague 'what' (guide to writing postmortems) but completely lacks a 'when' clause. There is no explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 3, and this barely addresses 'what' concretely.	2 / 5
Trigger Term Quality	Includes relevant keywords like 'postmortems', 'blameless', 'incident recurrence', and 'organizational learning', but misses natural user phrases like 'incident report', 'post-incident review', 'RCA', 'root cause analysis', 'outage review', or 'retrospective'.	3 / 5
Distinctiveness Conflict Risk	Somewhat specific to postmortems/incident reviews, but could overlap with general writing skills, incident management skills, or documentation skills. The term 'comprehensive guide' is generic framing that doesn't help distinguish it.	3 / 5
	Total	10 / 20 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/postmortem-writing/SKILL.md
Commit: 57c135b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.