\"cs-sop\"

SkillMedia

cs-sop helps your AI design customer service operations from the ground up. Once added, your AI can put together a complete support setup, from team tiers and response templates to escalation and complaint handling, so customers get consistent, quality answers.

Available today. Use it from your connected AI after setup.

After adding the skill, tell your AI what you need, such as setting up a support team, creating service standards, or improving response quality, and it will draft the operations for you.

Then ask your AI: use the \"cs-sop\" skill

What your AI can do with it

  • Design tiered support structures with L1, L2, and L3 levels
  • Create response templates for customer conversations
  • Define service level agreements (SLAs)
  • Write clear escalation procedures
  • Set up processes for handling customer complaints
  • Improve the quality of customer responses

What this skill tells your AI

The instructions your AI receives, as published by charlieviettq/awesome-agent-skill in .claude/skills/cs-sop/SKILL.md and read by ahel’s review.

Framework

IRON LAW: Tier the Support, Not the Customer

Every customer deserves quality service. But not every issue needs a
senior specialist. Route by ISSUE COMPLEXITY, not by customer "importance."

L1 handles 70-80% of volume (simple, repeatable)
L2 handles 15-20% (requires expertise)
L3 handles 5% (requires engineering or management)

Three-Tier Support Model

TierHandlesSkills RequiredResolution Target
L1 (Basic)FAQ, order status, password reset, simple returnsScript-following, product basics, empathy< 5 minutes, first-contact resolution
L2 (Specialist)Technical issues, billing disputes, complex returns, product defectsDeep product knowledge, judgment, negotiation< 24 hours
L3 (Expert)System bugs, legal/compliance, executive escalations, crisisEngineering, legal, or management involvement< 72 hours, case-by-case

Case Categorization

CategoryExamplesPrioritySLA (First Response)
CriticalService outage, security breach, safety issueP1< 15 minutes
HighPayment failure, account locked, order errorP2< 1 hour
MediumProduct question, feature request, general complaintP3< 4 hours
LowFeedback, suggestion, general inquiryP4< 24 hours

Complaint Handling: LAST Framework

  1. Listen: Let the customer express fully without interrupting
  2. Apologize: Acknowledge their frustration sincerely ("I'm sorry this happened")
  3. Solve: Offer a concrete solution or next step
  4. Thank: Thank them for bringing it to your attention

Escalation Rules

TriggerEscalate ToTimeline
L1 can't resolve in 15 minL2Immediate warm handoff
Customer requests supervisorL2 or Team LeadWithin 5 minutes
Issue involves refund > NT$XL2 (approval authority)Same interaction
Legal threat or media mentionL3 + Legal + PRImmediate
Repeat contact (3+ on same issue)L2 + investigationAfter 3rd contact

Response Template Structure

[Greeting] Hi {name}, thank you for contacting us.

[Acknowledge] I understand you're experiencing {issue}.

[Action] Here's what I've done / Here's what we'll do:
1. {specific action}
2. {timeline}

[Next steps] {what the customer should expect / do next}

[Close] Is there anything else I can help you with?

Output Format

# Customer Service SOP: {Business}

## Support Tiers
| Tier | Scope | Team Size | Tools |
|------|-------|----------|-------|
| L1 | {scope} | {N people} | {tools} |
| L2 | {scope} | {N} | {tools} |
| L3 | {scope} | {N} | {tools} |

## SLA Targets
| Priority | First Response | Resolution | Escalation |
|----------|--------------|-----------|-----------|
| P1 | {time} | {time} | {to whom} |
| P2 | ... | ... | ... |

## Top 10 Contact Reasons
| # | Reason | Volume % | Resolution | Template? |
|---|--------|---------|-----------|----------|
| 1 | {reason} | {%} | L1/L2 | Y/N |

## Escalation Flowchart
{Decision tree for when to escalate}

## Quality Metrics
| Metric | Target |
|--------|--------|
| First Contact Resolution | > 70% |
| CSAT | > 4.2/5 |
| Avg Response Time | < {X} hours |
| Escalation Rate | < 20% |

Gotchas

  • SLAs must be MEASURABLE: "Respond quickly" is not an SLA. "First response within 1 hour for P2 tickets" is. If you can't measure it, you can't manage it.
  • Warm handoff > cold transfer: When escalating, the L1 agent should brief L2 before transferring. Forcing the customer to repeat their story destroys satisfaction.
  • Empower L1 with resolution authority: If L1 must escalate every refund, 70% of volume goes to L2 unnecessarily. Give L1 authority for refunds under a threshold (e.g., NT$500).
  • Templates are starting points, not scripts: Robotic copy-paste responses feel worse than no response. Agents should personalize templates to the specific situation.
  • Taiwan CS expectations: Taiwan customers expect fast LINE response (within minutes during business hours), polite and apologetic tone, and willingness to go the extra mile. The bar for "good service" is high.

References

  • For CSAT/NPS survey design, see the cs-analytics skill
  • For chatbot-human handoff design, see the cs-chatbot-design skill

Signals

GitHub stars
26
Forks
9
Last commit
Jul 2026
Advanced
Catalog kind
skill
Gateway key
cs-sop
Source
github.com/charlieviettq/awesome-agent-skill