write-a-postmortem

Write a blameless incident postmortem under postmortems/ following the Google SRE shape — evidence-based timeline, trigger vs root cause vs symptom, contributing factors, what went well, and owned+dated+verifiable action items. Read when asked to write a postmortem, do an incident review, run a root cause analysis, write up the outage, retro on the outage, or when the user says we had an incident and wants it documented. Do NOT read to frame a proposal (use frame-a-proposal), write a spec (use write-a-spec), record a decision (use record-a-decision), or review a design (use review-a-design) — a postmortem documents an incident that already happened, it does not propose, specify, decide, or critique future work.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

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

A strong, highly actionable instruction skill with a clearly sequenced, gate-validated workflow and concrete tool-call examples throughout. The main weaknesses are mild rhetorical padding and a single-file structure that, at this length, could benefit from splitting detail into a reference file.

Suggestions

Trim rhetorical emphasis (e.g. 'not a slogan you paste in the header,' 'impact is the currency') to tighten conciseness without losing the behavioral guidance.

Extract the worked examples — blamelessness rules (Step 0), trigger/root-cause/symptom definitions (Step 6), and the sample timeline (Step 5) — into a references/ file linked from SKILL.md to improve progressive disclosure.

Add a brief overview or quick-start block at the top summarizing the 11-step flow before the detailed steps, so the structure is navigable at a glance.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence, but rhetorical flourishes ('not a slogan you paste in the header,' 'impact is the currency,' 'the single worst failure this skill can commit') are minor over-emphasis that could be trimmed without losing the guidance.	4 / 5
Actionability	Copy-paste-ready tool calls (exec, search, write, audit), a concrete filename pattern (YYYY-MM-DD-name.md), and fully worked examples (a timestamped timeline, an owned+dated+verifiable action item) cover the common cases.	5 / 5
Workflow Clarity	Eleven sequenced steps (Step 0–11) with explicit HARD GATE validation checkpoints and a validate→fix feedback loop ('audit({...}) returns clean — fix every finding'), matching the explicit-checkpoints anchor.	5 / 5
Progressive Disclosure	Well-organized into clear named sections with no nested references, but it is a ~200-line single file with no overview/quick-start pointing to deeper material; some worked examples (blamelessness rules, trigger/root-cause definitions, sample timeline) could be split into a reference file to keep SKILL.md leaner.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%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.

An excellent description: concrete deliverables, comprehensive natural-language triggers, explicit what/when, and active disambiguation from sibling skills. Voice is imperative throughout, consistent with the rubric's good examples and free of first/second-person pronouns, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables of the SRE shape — 'evidence-based timeline, trigger vs root cause vs symptom, contributing factors, what went well, and owned+dated+verifiable action items' — giving comprehensive, non-vague coverage of what the skill produces.	5 / 5
Completeness	Explicitly answers both what ('Write a blameless incident postmortem ... following the Google SRE shape') and when ('Read when asked to write a postmortem ...') with concrete trigger phrases, plus a negative boundary.	5 / 5
Trigger Term Quality	Covers natural user phrasings with synonyms — 'write a postmortem,' 'do an incident review,' 'run a root cause analysis,' 'write up the outage,' 'retro on the outage,' 'we had an incident' — matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit disambiguation — 'Do NOT read to frame a proposal (use frame-a-proposal), write a spec (use write-a-spec), record a decision (use record-a-decision), or review a design (use review-a-design)' — minimizing wrong-skill triggering.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: inkeep/open-knowledge
Path: packages/server/assets/skills/packs/software-lifecycle/write-a-postmortem/SKILL.md
Commit: e84b75f

Reviewed: 8 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.