on-call-handoff
Skill13 starsChanged 3 months agoMITView on GitHub
Summarize a personal or team on-call shift from supplied context, Slack, Datadog, GitHub, and Vercel. Activate when asked for an on-call handoff, shift summary, rotation handoff, what to tell the next on-call, or leaving on-call.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- deep-investigationSkill
- hypothesis-validationSkill
- suggest-follow-upsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Create an accurate handoff that covers notable incidents, pages, operational changes, and open actions.
- Distinctive: line 18
Use the supplied webhook metadata first.
- Distinctive: line 20
Do not require an external incident-management connection.
- Distinctive: line 40
Do not re-investigate alerts/incidents from scratch
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
On-call handoff
Create an accurate handoff that covers notable incidents, pages, operational changes, and open actions. Do not investigate open incidents in depth.
Procedure
1. Set the scope
Identify the team, shift start, shift end, and next responder from the request or conversation. Ask one targeted question only when a missing value blocks the handoff.
2. Collect shift context
Use the supplied webhook metadata first. Read Slack only when the request points to relevant channels or threads. Use Datadog for page, monitor, or service-health facts. Use GitHub when a deploy, pull request, or code change matters.
Do not require an external incident-management connection. State when the available sources cannot confirm a count, owner, schedule, or follow-up.
3. Select notable events
Include high-severity events, recurring pages, ongoing impact, and events with useful operational lessons. Keep low-signal events in a short count or omit them.
4. Identify changes and open actions
Record mitigations, deploys, alert changes, and other concrete improvements made during the shift. List unresolved actions with an owner and due date only when the evidence provides them.
5. Write the handoff
Return the handoff in chat. Use references/template.md as the structure. Mark missing data as "Could not confirm from available sources."
Result
The handoff doc detailed in step 5.
Boundaries
- Do not re-investigate alerts/incidents from scratch
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.