runbook
The facts
Its description
Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowledge into exact step-by-step commands, adding troubleshooting and rollback steps to an existing procedure, or writing escalation paths for when things go wrong.
The description the agent reads to decide when to use it.
When it starts
The agent would pick this skill when someone asks to document a recurring operational task or procedure as a repeatable, step-by-step runbook — especially one an on-call or ops person has to run — or asks to add troubleshooting, rollback, or escalation detail to an existing procedure.
Things a person might say (the model's guesses)
- “Write a runbook for our nightly data sync job”
- “Turn our tribal knowledge about restarting the payments service into a step-by-step doc”
- “Add troubleshooting and rollback steps to our existing deploy runbook”
A model's summary of when it is used.
What it takes when started
<process or task name>
What to type after its name when you start it.
Runs scripts
python sync.py
Scripts the text names. Found by matching words, so treat them as pointers.
Licence
Apache-2.0, from LICENSE
The terms its author shares it under, which let it be shown here.
The text
Most marks come from matching words in the file, so treat them as pointers.
/runbook
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Create a step-by-step operational runbook for a recurring task or procedure.
Raw lines 1 to 12Boilerplate, lines 13 to 18. The same text appears in 24 other files here. Close
Output
## Runbook: [Task Name]
**Owner:** [Team/Person] | **Frequency:** [Daily/Weekly/Monthly/As Needed]
**Last Updated:** [Date] | **Last Run:** [Date]
### Purpose
[What this runbook accomplishes and when to use it]
### Prerequisites
- [ ] [Access or permission needed]
- [ ] [Tool or system required]
- [ ] [Data or input needed]
### Procedure
#### Step 1: [Name][Exact command, action, or instruction]
**Expected result:** [What should happen]
**If it fails:** [What to do]
#### Step 2: [Name][Exact command, action, or instruction]
**Expected result:** [What should happen]
**If it fails:** [What to do]
### Verification
- [ ] [How to confirm the task completed successfully]
- [ ] [What to check]
### Troubleshooting
| Symptom | Likely Cause | Fix |
|---------|-------------|-----|
| [What you see] | [Why] | [What to do] |
### Rollback
[How to undo this if something goes wrong]
### Escalation
| Situation | Contact | Method |
|-----------|---------|--------|
| [When to escalate] | [Who] | [How to reach them] |
### History
| Date | Run By | Notes |
|------|--------|-------|
| [Date] | [Person] | [Any issues or observations] |Raw lines 19 to 72If Connectors Available
If ~~knowledge base is connected:
- Search for existing runbooks to update rather than create from scratch
- Publish the completed runbook to your ops wiki
If ~~ITSM is connected:
- Link the runbook to related incident types and change requests
- Auto-populate escalation contacts from on-call schedules
Tips
- Be painfully specific — "Run the script" is not a step. "Run
python sync.py --prod --dry-runfrom the ops server" is. - Include failure modes — What can go wrong at each step and what to do about it.
- Test the runbook — Have someone unfamiliar with the process follow it. Fix where they get stuck.
From anthropics/knowledge-work-plugins at 2574e29, 2026-10-27. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.