Skip to content
Operations · Playbook

What happened, why the system allowed it, and what changes. No names in the blame column.

A blameless incident report with an exact timeline, contributing conditions, a fix, and follow-ups that each have an owner and a date.

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
100 Playbooks in the catalogDelivered as Claude Skill + plain .mdReviewed Oct 22, 2026Instruction-only · verifiable

After an incident, the report is often written to settle who was at fault. It ends with someone being reminded to be more careful, the same conditions stay in place, and the same failure returns a few months later with a different person involved.

Incident Report works from the raw facts: messages, timestamps, and what people knew at the time. It builds the timeline, asks why the failure was possible until it reaches a condition in the system, and separates the immediate fix from the changes that prevent a repeat. A final pass removes blame.

What you get

What it produces.

  • →A three-sentence summary with impact in time, money, or customers
  • →A neutral timeline with gaps marked, not filled
  • →Contributing conditions traced to missing checks or unclear handoffs
  • →Follow-ups with owner, due date, and a way to confirm they worked
Who it's for
  • ✦Operations managers documenting an outage, miss, or wrong shipment
  • ✦Small-business owners who want fewer repeat mistakes
  • ✦Team leads writing up a near miss for the team
What's included
  • →incident-report.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →incident-report-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
  • →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
Delivery
Emailed within 60 seconds of payment
Compatibility
Claude, ChatGPT, Gemini, any LLM
License
One-time purchase, yours to keep
Sample output

What it does with a real question.

The brief

On Tuesday, March 12, our nightly inventory sync failed around 2:00 a.m. and nobody noticed until a warehouse lead flagged mismatched counts at 9:30. Between those times, 47 orders shipped against stock we didn't have, and 12 customers got delayed shipments. Ops on-call was paged but the alert went to a retired Slack channel. Please write the report with timeline, cause, fix, and follow-ups.

Summary and impact. On Tuesday, March 12, the nightly inventory sync failed at about 2:00 a.m. and ran undetected for roughly seven and a half hours. In that window, 47 orders shipped against stock we did not have, and 12 customers received delayed shipments. Dollar cost and support hours are unknown from what we have.

Timeline. 2:00 a.m., sync fails. The on-call page fires, but it posts to a retired Slack channel, so no one sees it. Orders keep shipping against stale counts through the morning. 9:30 a.m., a warehouse lead spots mismatched counts and raises it.

Cause. I'd resist calling this a monitoring failure, because the monitoring worked: it fired. The real question is why a page could go to a dead channel without anyone knowing. Asking why three times lands on the system. Retiring the channel never triggered a review of what routed to it, and nothing confirms alerts reach a live human. Detection came from a person's eye, not a safeguard, which is worth keeping.

Fix. Re-run the sync, reconcile counts, and contact the 12 affected customers with a revised ship date.

Next move. Audit every alert destination this week and repoint anything aimed at retired channels. Then add a standing check that a test page reaches a person, with a named owner and a due date. I would drop any follow-up phrased as "remind on-call to watch the channel."

The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.

Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.

One-time purchase
$12.99
Yours to keep
No subscription · free updates within v1.x

Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable

Questions

Before you buy.

How is this different from just asking Claude directly?

Asked cold, Claude often writes a tidy narrative that quietly settles on a person or a vague cause such as carelessness. This one demands exact times, keeps assumptions apart from facts, keeps asking why until it reaches a system condition, and rewrites any follow-up that amounts to a warning.

How is this different from a Tool?

Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.

Will this work with ChatGPT, Gemini, and other LLMs?

Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.

Can I share this with my team?

It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.

What if it doesn't work for me?

If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.

More Operations Playbooks

Other Playbooks.