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 contact, diagnose long queues or poor quality, or decide what to automate.
git clone --depth 1 https://github.com/cbrock84/headcount /tmp/support-operations && cp -r /tmp/support-operations/plugins/customer-experience/skills/support-operations ~/.claude/skills/support-operationsSKILL.md
# 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. ## 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.
Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group inside each, tiering effort against account value, coordinating so the account experiences one campaign rather than several, and measuring account progression instead of leads. Use this to decide whether to run an account-based program, build one, or work out why an existing one produces activity and no pipeline.
Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a script that runs in CI. Use this whenever the user wants to set up, expand, audit, or fix a multi-agent or subagent structure for a codebase; asks how to divide work between agents; wants agent charters, roles, or a surface map written; or is hitting agents that collide on the same files, review their own work, or drift from their remit. Also use when sizing a roster or deciding whether a new agent is justified.
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory exposure, or when deciding whether an AI system is fit for a consequential decision.
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a research brief, or assemble evidence for a decision. Also use when comparing options that need a structured, evidence-based verdict rather than an opinion.
Optimizes for AI assistants and AI-generated answers — being retrievable, being cited, and being represented accurately when a model answers on your behalf. Use this when traffic is shifting from links to AI answers, when a brand is misrepresented or absent in AI responses, when planning content for retrieval rather than ranking, or when deciding how AI search changes an existing SEO program.
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
Protects and restores data — backup coverage and scope, retention, immutability against ransomware, and proving restores actually work. Use this to design a backup regime, verify restores, plan retention, protect backups from ransomware, or recover from data loss.
Runs the planning cycle — annual budget, rolling forecast, consolidation of business unit inputs, and the variance analysis that explains actuals against plan. Use this to build or challenge a budget, run a forecast cycle, consolidate departmental submissions, explain why results diverged from plan, or improve forecast accuracy.