agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/cat-agent-skills/submissions/customer-service-order-support/skills/handoff-packet/SKILL.md

handoff-packet

Skill95 starsChanged 6 days agoMITView on GitHub

Builds the structured escalation packet when the run cannot resolve - intent, context, contradictions, what was checked, recommended next step. Use on any low-confidence, contradicted, or out-of-scope run: "escalate this", "hand off to tier 2".

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:

    Every packet line cites its record.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Handoff Packet

Purpose

Terminal artifact for non-resolvable runs: no bare transfers (#4.1).

When to use

Low confidence, contradictions, no approved answer, or money-boundary requests.

Inputs

Full payload.

Steps

  1. Packet: intent + confidence, consolidated context with citations, contradiction flags with the carrier scan reference, everything already checked, the recommended next step (e.g., open carrier investigation SVC-DNR-2), and the customer-visible interim reply draft.
  2. Goodwill requests appear as PROPOSALS for the human, never as commitments (#3.1).

Output

Handoff packet + interim reply draft - terminal artifacts.

Grounding requirements

Every packet line cites its record.

Constraints

  • The packet recommends; the human decides. No credits, no payment changes, no exceptions (plugin boundary).

Escalation / uncertainty

Angry-customer pressure changes tone handling, never the path.

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.

Check your setup, free