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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is highly actionable with concrete templates and a clear process workflow, but it is let down by token-inefficient fluff and inconsistent progressive disclosure that inlines large templates while claiming to delegate them to references.

Suggestions

Move Template 2 (5 Whys) and Template 3 (Quick Postmortem) into references/details.md so all templates live in one place, leaving SKILL.md as a concise overview that links out — matching the existing delegation statement.

Remove the fluffy opener and the redundant "When to Use This Skill" list (the description already carries the triggers), and fix the stray code fence on line 60 that breaks the document structure.

Replace the mid-document "## References" section's internal-wiki/... links with real, verifiable file paths or remove them, since they do not resolve to bundle files.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful concrete content, but the opening line is fluffy ("Comprehensive guide...that drive organizational learning and prevent incident recurrence"), the "When to Use" section repeats the description triggers, and full templates are inlined rather than delegated. It is not the lean 'every token earns its place' anchor.	2 / 3
Actionability	It provides copy-paste-ready markdown templates (5 Whys worked example, Quick Postmortem), a time-boxed 60-minute facilitation structure, and concrete do/don't and anti-pattern tables — specific and directly usable.	3 / 3
Workflow Clarity	The postmortem process is laid out as a clear Day 0 → Quarterly timeline and the meeting is a sequenced, time-boxed agenda; this is not a destructive/batch operation, so absent validation gates do not cap the score.	3 / 3
Progressive Disclosure	A real references/details.md is signaled, but the body inlines Template 2 and Template 3 while Template 1 lives in the file — an inconsistent split — and a stray code fence plus a mid-document "## References" section (pointing to non-existent internal-wiki paths) muddy navigation. This fits 'some structure, content that should be separate is inline' rather than the clean one-level-deep anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 is specific, complete, and well-triggered: it states concrete capabilities and an explicit Use-when clause with natural trigger terms in a distinct niche. No changes needed.

Dimension	Reasoning	Score
Specificity	"Write effective blameless postmortems with root cause analysis, timelines, and action items" names multiple concrete actions (root cause analysis, timelines, action items), matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It answers both what ("Write effective blameless postmortems with root cause analysis, timelines, and action items") and when via an explicit "Use when..." clause, satisfying the top anchor.	3 / 3
Trigger Term Quality	"incident reviews", "postmortem documents", and "incident response processes" are natural phrases a user would say when they need this skill, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Blameless postmortem writing is a clear niche with distinct incident-review triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: wshobson/agents
Commit: 5cc2549

Reviewed: 5 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.