Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jamditis/project-retrospective
Generate LESSONS.md retrospective files that capture institutional knowledge, especially failures.
Passed 21 of 22 test cases with the skill, and 15 of 22 without it.
and 6 more in the full report
6 fixed15 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our team just completed rolling out a new internal desk management tool for newsroom editors, but we ran into significant integration bugs and low adoption. I want to document what happened in a structured LESSONS.md postmortem. Here are my raw notes on the deployment timeline, user friction, system configurations vs human mistakes, and team feedback. Please compose a full retrospective document that includes a project overview, technical/process successes, detailed breakdown of system-level vs human-level failures with impact metrics, the main gap between what we assumed vs what was needed, and prioritized action items with assigned owners.
| Checked | Without skill | With skill |
|---|---|---|
| Separates failures into distinct system permission, human action inside system constraints, and quantified cost metrics | Missed | Passed |
| Includes action item tracker issue URLs in the tasks table | Missed | Passed |
| Includes a scheduled 30/60/90-day progress check-in review | Missed | Passed |
The instructions your model reads when the skill loads.
Create LESSONS.md files that capture institutional knowledge, especially failures. Think like a journalist writing about your own project, be specific, be honest, name the actual mistakes.
The 2024–2026 consensus in incident-analysis writing (PagerDuty, J. Paul Reed, Lorin Hochstein) is that pure blamelessness is neurobiologically unrealistic, humans default to blame. Healthier framing: acknowledge the blame bias exists and counter it deliberately. Source: https://postmortems.pagerduty.com/culture/blameless/
Cognitive biases to counter explicitly:
The voice rule isn't "no blame", it's "name the system that permitted the human action, not just the action."
Allspaw's canonical critique (still the dominant view in 2024–2026) calls Five Whys / single-root-cause analysis "seductively satisfying and compellingly simple, but false." It locks analysts into a linear causal chain that terminates in individual blame. Source: https://www.kitchensoap.com/2014/11/14/the-infinite-hows-or-the-dangers-of-the-five-whys/
Use "how" narratives instead, gathering on four prompts:
The retrospective's job is to surface contributing factors, not declare a root cause.
Pre-define triggers before incidents happen, not after. Google SRE specifies criteria: user-visible downtime past a threshold, any data loss, on-call rollbacks, monitoring failures requiring manual discovery, stakeholder request. Source: https://sre.google/sre-book/postmortem-culture/
Translated to journalism:
| Trigger | Examples |
|---|---|
| Live-event failure | Live-blog downtime during election night, breaking-news embed breakage, paywall regression mid-investigation |
| Editorial process failure | Missed correction window, source-management breach, fact-check process bypass |
| Tool failure affecting subscribers | CMS migration regression, paywall logic affecting >X% of readers |
| Stakeholder request | Editor / publisher / source explicitly asking "what happened?" |
test cases passed, vs 15 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.