alirezarezvani/claude-skills / business-growth/support-ops/skills/support-ops
support-ops
VerifiedUse for any customer support operations question - SLA attainment and breaches (first response, resolution, business hours, weekends, tickets about to breach), how many agents to schedule per hour for a phone, chat or email queue and where the roster is short (Erlang C, service level, handle time, shrinkage, occupancy, backlog), or which ticket topics to deflect with help-center articles, automate with macros or fix as product bugs. Works from a helpdesk ticket export with stdlib scripts.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.7 KB |
| assets/intervals.example.csv | other | 136 B |
| assets/sla_policy.example.json | config | 519 B |
| assets/tickets.example.csv | other | 803 B |
| references/deflection_and_kcs.md | markdown | 2.4 KB |
| references/sla_design_and_measurement.md | markdown | 2.8 KB |
| references/staffing_and_erlang_c.md | markdown | 2.6 KB |
| scripts/deflection_finder.py | script | 9.0 KB |
| scripts/sla_check.py | script | 12.4 KB |
| scripts/staffing_plan.py | script | 10.1 KB |
references/deflection_and_kcs.md
View on GitHub# Deflection, automation and root-cause fixes
Confidence: π’ primary source, π‘ established secondary source, π΄ common practice.
## Three different fixes for three different problems
| Signal in the tickets | What it means | Action |
|---|---|---|
| One answer resolves most tickets, few reopen | the customer could have found it | **DEFLECT**: publish where customers look (help center, in-product, the form itself) |
| A common answer exists but agents adapt it | agents need speed, customers still need a person | **AUTOMATE**: macro, structured form, workflow |
| Many reopen, or the subject names an error | the product is the problem | **FIX_ROOT_CAUSE**: a bug report with the ticket count and hours attached |
| Answers vary | unknown | **REVIEW**: read 20 tickets before deciding |
Writing an article for a defect teaches customers to work around it and hides the cost from the team that could remove it. π΄
## KCS: capture in the workflow, improve from use
π’ Knowledge-Centered Service (KCS) has agents capture and reuse knowledge while solving tickets (the Solve Loop), and analyses the collected knowledge and its reuse to improve content and to feed product fixes upstream (the Evolve Loop). [1] The macro column in a ticket export is a cheap proxy for reuse: the share of tickets closed with the same answer is what `deflection_finder.py` calls concentration.
## Claims to make carefully
- Deflection hours are an **upper bound**: they assume every customer who would have written finds and trusts the article. Measure after launch: contact rate for the topic per active customer, before and after. π΄
- A help-center view is not a deflected ticket. Count only the drop in contacts for that topic. π΄
- Customers prefer to solve simple problems themselves, and repeat contacts drive disloyalty more than slow first answers. π‘ [2][3]
- Pareto: in most queues a handful of reasons carry most volume; rank only the head, and only reasons with enough tickets to trust the rates. π΄ [4]
## Sources
1. Consortium for Service Innovation, *KCS v6 Practices Guide*, library.serviceinnovation.org
2. M. Dixon, K. Freeman, N. Toman, "Stop Trying to Delight Your Customers", Harvard Business Review, July-August 2010
3. M. Dixon, N. Toman, R. DeLisi, *The Effortless Experience*, Portfolio/Penguin, 2013
4. J. M. Juran, *Quality Control Handbook*, McGraw-Hill (Pareto principle as "vital few, trivial many")
5. AXELOS, *ITIL 4 Practice Guide: Problem Management*, 2020
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |