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.
80
71%
Does it follow best practices?
Impact
92%
1.26xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/incident-response/skills/postmortem-writing/SKILL.mdQuality
Discovery
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.
This is a well-crafted skill description that clearly communicates specific capabilities (blameless postmortems, root cause analysis, timelines, action items) and provides explicit trigger guidance via a 'Use when' clause. It uses third person voice, includes natural keywords that engineers would use, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Write effective blameless postmortems', 'root cause analysis', 'timelines', and 'action items'. These are distinct, concrete deliverables. | 3 / 3 |
Completeness | Clearly answers both 'what' (write blameless postmortems with root cause analysis, timelines, and action items) and 'when' (conducting incident reviews, writing postmortem documents, or improving incident response processes) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'postmortems', 'root cause analysis', 'incident reviews', 'postmortem documents', 'incident response', 'blameless', 'timelines', 'action items'. Good coverage of terms an engineer would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around incident postmortems and root cause analysis. The combination of 'blameless postmortems', 'incident reviews', and 'incident response' is highly specific and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, well-structured postmortem templates that are immediately usable, which is its primary strength. However, it is severely bloated — much of the content (blameless culture explanation, facilitation tips, do's/don'ts) is common knowledge Claude doesn't need, and the massive inline templates should be split into referenced files. The lack of progressive disclosure and excessive verbosity significantly undermine its effectiveness as a skill file.
Suggestions
Move the three templates into separate referenced files (e.g., TEMPLATE_STANDARD.md, TEMPLATE_5WHYS.md, TEMPLATE_QUICK.md) and keep SKILL.md as a concise overview with links.
Remove the 'Core Concepts' section on blameless culture and the facilitation guide — Claude already understands these concepts and can apply them without explicit instruction.
Cut the 'When to Use This Skill' bullet list and the 'Best Practices' do's/don'ts section, which are generic knowledge that waste token budget.
Add a validation checklist (e.g., 'Before finalizing: verify all action items have owners, due dates, and tickets; confirm timeline has no gaps; ensure root cause addresses systemic issues not individual blame').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It explains concepts Claude already knows well (blameless culture, what postmortems are, facilitation tips like 'encourage quiet participants'). The massive example templates with fictional data (payment service outage) consume enormous token budget. The 'When to Use This Skill' and 'Core Concepts' sections are largely unnecessary padding. | 1 / 3 |
Actionability | The skill provides three complete, copy-paste-ready markdown templates (standard, 5 Whys, quick postmortem) with concrete examples including timelines, action item tables with owners/dates/tickets, and specific formatting. The templates are immediately usable and well-structured. | 3 / 3 |
Workflow Clarity | The postmortem timeline (Day 0 through Quarterly) provides a clear sequence, and the meeting facilitation guide has a structured 60-minute agenda. However, there are no validation checkpoints — no steps to verify the postmortem is complete, no checklist to ensure all sections are filled, and no feedback loop for reviewing action item quality before finalizing. | 2 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no bundle files or references to supporting documents. The three full templates, facilitation guide, anti-patterns, best practices, and resources are all inline, creating a wall of content. The templates alone could each be separate referenced files, with SKILL.md serving as a concise overview. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
bbc5ade
- Reviewed
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.