agentleFS
kaandgnshkaandgnsh/Claude-Blue/skills/soc-operations/shift-handoff/SKILL.md

shift-handoff

Skill0 starsChanged 16 days agoMITView on GitHub

Produce a SOC shift handoff that transfers open incidents, pending actions, platform health issues and watch items without losing context. Use at shift change, when handing a case to another team or time zone, or when summarizing the queue for a lead.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Do a verbal or live walkthrough of anything critical.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Shift Handoff

Most dropped incidents are dropped at handoff. A handoff lists what the next shift must do, not what this shift did.

Workflow

  1. Pull the open queue sorted by severity then age. For each case note owner, status, and the single next action with a deadline.
  2. List time-bound items: pending approvals, containment awaiting confirmation, vendor/legal callbacks, IOC sweeps running, embargoed advisories.
  3. List platform health: log sources silent beyond their expected interval, EDR sensors offline on critical assets, failed SOAR playbooks, ingestion lag. Example check (Sentinel): Heartbeat | summarize last=max(TimeGenerated) by Computer | where last < ago(1h); Splunk: | tstats latest(_time) as last where index=* by index, sourcetype | where last < relative_time(now(), "-2h").
  4. List watch items: entities under heightened monitoring, temporary detections deployed, threat intel requiring attention.
  5. Do a verbal or live walkthrough of anything critical; the written note is the record, not a substitute for a conversation on a P1.
  6. Incoming analyst acknowledges in writing; ownership changes in the ticketing system, not just in chat.

Template

Shift handoff <date> <from shift> → <to shift>   Lead: <>
CRITICAL / ACTIVE
 - <case> sev<> owner→<new owner>  Next: <action> by <UTC time>  Blocker: <>
PENDING APPROVALS / CALLBACKS
 - <item> waiting on <who> since <t>
PLATFORM HEALTH
 - <source> silent since <t> (ticket <>)
WATCH ITEMS
 - <entity> monitor for <behaviour> until <date>; temp rule <id> expires <date>
QUEUE: <n> open (<by severity>), oldest <age>
Acknowledged by: <name> at <t>

Pitfalls

  • "Monitoring" without a defined trigger and end date.
  • Leaving containment state ambiguous ("isolated?"). State verified state and how it was verified.
  • Handoffs only in chat; they are not searchable or auditable later.

Related skills

incident-command, case-documentation, log-pipeline-health, soc-performance-metrics

References

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.