Claude Skill

support-operations

Designs and runs the support function — channels, queues, routing, staffing, service levels, quality, and the metrics that show whether it is working. Use this to set up or fix support operations, choose channels, size a team, set or renegotiate service levels, reduce cost per co

LLM Mart · 0 points · 17 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download cbrock84-headcount-plugins_customer-experience_skills_support-operations-98d1c17.zip · 3 KB

cbrock84/headcount 1633 245 forks MIT Updated 7d ago

Part of cbrock84/headcount — 160 skills

Install

skills CLI npx skills add https://github.com/cbrock84/headcount/tree/main/plugins/customer-experience/skills/support-operations

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install cbrock84-headcount@llmmart

Git git clone https://github.com/cbrock84/headcount.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole cbrock84/headcount collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Support operations

Understand demand before designing supply

Categorize a real sample of recent contacts — a few hundred, read individually, not a report. Almost every support operation finds the same shape: a small number of causes generating most of the volume, and most of those are preventable rather than answerable.

That analysis decides everything downstream. Staffing to demand you have not examined means staffing to demand you could have eliminated.

The hierarchy of handling

In order of cost, cheapest first. Push volume up this list rather than getting faster at the bottom:

Eliminate — fix the product defect or confusing flow generating the contact.
Deflect — answer it in the interface at the moment of confusion, not in a help center nobody visits.
Self-serve — findable documentation for people who go looking.
Automate — genuine resolution of routine requests, not a bot that stalls people before a human.
Assist — a person.

Most support improvement programs work on level 5 exclusively, because it is the visible one.

Channels

Pick by what the work needs, not by what is fashionable. Asynchronous channels are cheaper and better for anything requiring investigation. Synchronous channels are worth their cost for urgency, high-value accounts, and anything where a customer is stuck mid-task.

Every channel you open must be staffed to its expectation. An unstaffed live-chat widget is worse than no chat.

Service levels

Set by severity and customer tier, published internally, and — this is the part usually missing — checked against actual capacity before being promised. A commitment the staffing cannot meet is a commitment to fail visibly.

Measure first response and time to resolution separately. They have different causes: first response is a staffing problem, resolution is usually a product or escalation problem.

Metrics that mean something

Contacts per active customer, trending. The only metric that captures whether the product is getting better rather than the team getting faster.
First-contact resolution — reopens are the honest signal.
Backlog age distribution, not average age. Averages hide the tickets rotting at the back, and those are the ones that become complaints.
Customer-effort, asked at resolution.

Be careful with time-to-close and volume handled. Both are easily gamed and both reward closing over solving.

Staffing

Size to peak-hour concurrency, not to daily volume — queues form in hours, not days. Model the shrinkage honestly: training, breaks, meetings, leave. A plan assuming full utilization understaffs by a wide margin and then blames the team.

Quality

Review a sample of resolved contacts against a rubric agreed with the team, and coach against it. Reviewing only escalations trains for defense rather than quality.

Sources

references/sources.md in this skill lists the outside authorities that settle the questions here — what each one is authoritative for, and what you may do with it. Check them before answering on anything they cover, and cite what you used. Most are free to read and not free to reproduce; the use note on each is binding.

Tooling

Ticketing: Zendesk, Freshdesk, Intercom, Front, Help Scout, and similar; Jira Service Management where support and engineering work one queue.

Knowledge base: usually the ticketing tool's own, or Confluence, Notion, or Guru.

Quality review and workforce management — Klaus, Assembled, and similar — start paying off once you staff shifts rather than a team. Before that they are overhead.

Never

Staff to average volume. Support arrives in peaks.
Publish a service level you have not staffed to meet.
Manage on handle time. It optimizes for closing tickets, not for solving problems.
Let a repeat driver stay a support problem. Route it to whoever owns the cause.

Files (headcount)

references

sources.md 1.9 KB

# Sources — `customer-experience:support-operations`

<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->

Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.

## 18 U.S.C. 2511 — interception of communications

US Congress, via the Office of the Law Revision Counsel · US · public domain (US government) — quote freely

<https://uscode.house.gov/view.xhtml?req=granuleid:USC-prelim-title18-section2511&num=0&edition=prelim>

**Authoritative for:** The federal one-party-consent floor for recording a call, and the criminal exposure for recording without it. It settles only the floor: several states require all-party consent, and there is no free authoritative single document for that matrix — it must be looked up per state.

## Federal Plain Language Guidelines

Plain Language Action and Information Network · US · public domain (US government) — quote freely

<https://www.plainlanguage.gov/guidelines/>

**Authoritative for:** What counts as plain language in user-facing writing — audience-first structure, active voice, short sections. Backed by statute for federal agencies, and the only free normative writing standard that is not one author's style preference.

## PCI Data Security Standard

PCI Security Standards Council · global · **account required — cite it; the user fetches it**

<https://www.pcisecuritystandards.org/document_library/>

**Authoritative for:** Whether a support agent may take a card number by phone, whether that call may be recorded, and what must happen to card data in ticket attachments and screen shares. Assessed by a qualified assessor, so genuinely dispositive.

---

Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

SKILL.md 4.2 KB

---
name: support-operations
description: Designs and runs the support function — channels, queues, routing, staffing, service levels, quality, and the metrics that show whether it is working. Use this to set up or fix support operations, choose channels, size a team, set or renegotiate service levels, reduce cost per contact, diagnose long queues or poor quality, or decide what to automate.
---

# Support operations

## Understand demand before designing supply

Categorize a real sample of recent contacts — a few hundred, read individually, not a report. Almost
every support operation finds the same shape: a small number of causes generating most of the
volume, and most of those are preventable rather than answerable.

That analysis decides everything downstream. Staffing to demand you have not examined means staffing
to demand you could have eliminated.

## The hierarchy of handling

In order of cost, cheapest first. Push volume up this list rather than getting faster at the bottom:

1. **Eliminate** — fix the product defect or confusing flow generating the contact.
2. **Deflect** — answer it in the interface at the moment of confusion, not in a help center nobody
   visits.
3. **Self-serve** — findable documentation for people who go looking.
4. **Automate** — genuine resolution of routine requests, not a bot that stalls people before a
   human.
5. **Assist** — a person.

Most support improvement programs work on level 5 exclusively, because it is the visible one.

## Channels

Pick by what the work needs, not by what is fashionable. Asynchronous channels are cheaper and
better for anything requiring investigation. Synchronous channels are worth their cost for urgency,
high-value accounts, and anything where a customer is stuck mid-task.

Every channel you open must be staffed to its expectation. An unstaffed live-chat widget is worse
than no chat.

## Service levels

Set by severity and customer tier, published internally, and — this is the part usually missing —
**checked against actual capacity before being promised**. A commitment the staffing cannot meet is
a commitment to fail visibly.

Measure first response and time to resolution separately. They have different causes: first response
is a staffing problem, resolution is usually a product or escalation problem.

## Metrics that mean something

- **Contacts per active customer**, trending. The only metric that captures whether the product is
  getting better rather than the team getting faster.
- **First-contact resolution** — reopens are the honest signal.
- **Backlog age distribution**, not average age. Averages hide the tickets rotting at the back, and
  those are the ones that become complaints.
- **Customer-effort**, asked at resolution.

Be careful with time-to-close and volume handled. Both are easily gamed and both reward closing over
solving.

## Staffing

Size to peak-hour concurrency, not to daily volume — queues form in hours, not days. Model the
shrinkage honestly: training, breaks, meetings, leave. A plan assuming full utilization understaffs
by a wide margin and then blames the team.

## Quality

Review a sample of resolved contacts against a rubric agreed with the team, and coach against it.
Reviewing only escalations trains for defense rather than quality.

## Sources

`references/sources.md` in this skill lists the outside authorities that settle the questions
here — what each one is authoritative for, and what you may do with it. Check them before
answering on anything they cover, and cite what you used. Most are free to read and not free
to reproduce; the use note on each is binding.

## Tooling

Ticketing: Zendesk, Freshdesk, Intercom, Front, Help Scout, and similar; Jira Service
Management where support and engineering work one queue.

Knowledge base: usually the ticketing tool's own, or Confluence, Notion, or Guru.

Quality review and workforce management — Klaus, Assembled, and similar — start paying off
once you staff shifts rather than a team. Before that they are overhead.

## Never

- Staff to average volume. Support arrives in peaks.
- Publish a service level you have not staffed to meet.
- Manage on handle time. It optimizes for closing tickets, not for solving problems.
- Let a repeat driver stay a support problem. Route it to whoever owns the cause.