Handoff Packet

Builds the structured tier-2 escalation packet for a retail customer-service run that cannot resolve - intent and confidence, cited context, contradiction flags with the carrier scan, everything already checked, the recommended next step, goodwill as a proposal, plus an interim customer reply draft. Use on any low-confidence, contradicted, ungrounded or money-boundary run: "escalate this", "hand off to tier 2", "build the escalation packet", "we can't resolve this", "below confidence, hand it over". Do NOT use for resolvable runs - use resolution-draft instead; not for work-order handovers - u

110 stars 122 forksMarketing, Sales & BusinessOfficial

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add microsoft/cat-agent-skills --skill handoff-packet
Manual install
git clone --depth 1 https://github.com/microsoft/cat-agent-skills.git /tmp/cat-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/cat-agent-skills/submissions/customer-service-order-support/handoff-packet ~/.claude/skills/handoff-packet

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Handoff Packet (tier 2 escalation)

## Purpose
Terminal artifact for non-resolvable runs: no bare transfers (service-rules.md #4.1). The packet recommends; the human decides.

## When to use
- Intent below the confidence floor, a record-vs-account contradiction, no approved answer, conflicting sources, or any refund / credit / payment-change / exception request (#3.1).
- The agent asks to escalate or hand a customer-service case to tier 2.

## When NOT to Use
- A resolvable run with no escalations - use resolution-draft instead.
- A maintenance work-order or shift handover for a technician - use work-order-writeup instead.
- A return / refund case determination - use the returns case-packet instead.
- Executing the escalation (issuing a refund, opening the carrier ticket, sending the reply) - the human does that; this skill only drafts.

## Where the data comes from
This plugin ships no sample data. Every input is the user's own Microsoft 365 content or the output of an earlier skill in this session:
- Files the user names, links or attaches in the chat (an assembled.json or knowledge.json, the customer contact, the order, carrier and loyalty exports).
- Their OneDrive or SharePoint, found with Work IQ search (Microsoft 365 search) by order ID (with or without the ORD- prefix), customer ID or file name when no location is given.
- Customer emails or email attachments found the same way.
Read the full skill on GitHub

Details

Skill name
handoff-packet
Path
submissions/customer-service-order-support/handoff-packet/SKILL.md
License
MIT
Repo updated
15 November 2026

FAQ

What does the Handoff Packet skill do?

Builds the structured tier-2 escalation packet for a retail customer-service run that cannot resolve - intent and confidence, cited context, contradiction flags with the carrier scan, everything already checked, the recommended next step, goodwill as a proposal, plus an interim customer reply draft. Use on any low-confidence, contradicted, ungrounded or money-boundary run: "escalate this", "hand off to tier 2", "build the escalation packet", "we can't resolve this", "below confidence, hand it over". Do NOT use for resolvable runs - use resolution-draft instead; not for work-order handovers - u

How do I install the Handoff Packet skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add microsoft/cat-agent-skills --skill handoff-packet. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Handoff Packet popular?

It lives in microsoft/cat-agent-skills, which has 110 GitHub stars and 122 forks.

Related skills

3 Statements

110

microsoft/cat-agent-skills

Completes existing income statement, balance sheet and cash flow templates while preserving layout, grounding historical inputs and linking forecast formulas with reconciliation checks. Use for "fill in a 3-statement template", "complete an IS/BS/CF framework", "populate my integrated financial model", "link statements in this template", or "finish the forecasts in my three-statement workbook". Do NOT use for blank-slate models or general workbook edits (use xlsx), DCF valuation (use dcf-valuation), or buyout modeling (use lbo-model).

AI, LLMs & Agents122

Accessibility Pass

110

microsoft/cat-agent-skills

Use this skill whenever the user asks to check, review, or fix the accessibility of a PowerPoint deck, Word document, HTML page, or Markdown file, and before handing over any deck or document this agent just generated, so it does not ship with missing alt text, untitled slides, or unreadable colour contrast.

Frontend & Design122

Accessible Learning Materials

110

microsoft/cat-agent-skills

Maintains instructionally equivalent, accessible variants of a set of learning materials — lessons, readings, slides, and handouts — with parity checks against the original learning goals and recorded approvals. Use when the user asks to "make these materials accessible", "audit this lesson set for accessibility", "create an accessible version of this reading", "check reading level and alt text", or "keep my accessible variants in sync". Do NOT use for individual student accommodation or support-plan decisions (IEP, EHCP, or local equivalent), and do NOT use for generic document formatting (us

Learning & Education122

History Retrieve

110

microsoft/cat-agent-skills

Retrieves the asset's maintenance history — prior work orders, similar failures, PM records — and the relevant OEM manual and troubleshooting sections, and attaches them to the mfg.maintenance-triage.v1 contract. Use when the user says "pull the history for <asset>", "has this failed before?", "find the manual section", "any prior work orders?", or after fault-intake completes. Do NOT use for intake — use fault-intake; cause ranking — use failure-mode-rank; priority — use criticality-rank; drafting — use work-order-update.

Marketing, Sales & Business122

Fit Score

110

microsoft/cat-agent-skills

Computes deterministic, pre-governance candidate-role fit scores, utilisation context and provisional ranks with the bundled engines, after bench-query and before constraint-check. Use when the user says "rank the bench", "score the candidates", "who is the best fit?", "compare candidate fit for this role" or "show the provisional ranking". Do NOT use for RFP or vendor-proposal scoring, extracting roles (use role-intake), loading the bench (use bench-query), drafting the slate ("build me a slate"; use slate-draft), eligibility or conflicts (use constraint-check), sales pipeline prioritization

Marketing, Sales & Business122

Inquiry Intake

110

microsoft/cat-agent-skills

Takes a retail customer's service inquiry from any channel (chat, mail, voice transcript) and classifies intent against the taxonomy with the deterministic intent_classify engine - the first hop of every Customer Service & Order Support run. Use when a service inquiry arrives: "where is my order", "it says delivered but I never got it", "new customer inquiry", "a chat just came in", "classify this contact", "start the service run". Do NOT use for supplier or purchase-order delays - use disruption-intake instead; not for return requests - use return-intake instead; not for the approved answer -

Marketing, Sales & Business122

Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.