{
  "schema": "https://ai-atoms.com/schemas/skill-v1.json",
  "type": "skill",
  "id": "skill/customer-escalation",
  "version": "1.0.0",
  "name": "customer-escalation",
  "description": "Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.",
  "system_prompt_fragment": "# /customer-escalation\n\n> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).\n\nPackage a support issue into a structured escalation brief for engineering, product, or leadership. Gathers context, structures reproduction steps, assesses business impact, and identifies the right escalation target.\n\n## Usage\n\n```\n/customer-escalation <issue description> [customer name or account]\n```\n\nExamples:\n- `/customer-escalation API returning 500 errors intermittently for Acme Corp`\n- `/customer-escalation Data export is missing rows — 3 customers reported this week`\n- `/customer-escalation SSO login loop affecting all Enterprise customers`\n- `/customer-escalation Customer threatening to churn over missing audit log feature`\n\n## Workflow\n\n### 1. Understand the Issue\n\nParse the input and determine:\n\n- **What's broken or needed**: The core technical or product issue\n- **Who's affected**: Specific customer(s), segment, or all users\n- **How long**: When did this start? How long has the customer been waiting?\n- **What's been tried**: Any troubleshooting or workarounds attempted\n- **Why escalate now**: What makes this need attention beyond normal support\n\nUse the \"When to Escalate vs. Handle in Support\" criteria below to confirm this warrants escalation.\n\n### 2. Gather Context\n\nPull together relevant information from available sources:\n\n- **~~support platform**: Related tickets, timeline of communications, previous troubleshooting\n- **~~CRM** (if connected): Account details, key contacts, previous escalations\n- **~~chat**: Internal discussions about this issue, similar reports from other customers\n- **~~project tracker** (if connected): Related bug reports or feature requests, engineering status\n- **~~knowledge base**: Known issues or workarounds, relevant documentation\n\n### 3. Assess Business Impact\n\nUsing the impact dimensions below, quantify:\n\n- **Breadth**: How many customers/users affected? Growing?\n- **Depth**: Blocked vs. inconvenienced?\n- **Duration**: How long has this been going on?\n- **Revenue**: ARR at risk? Pending deals affected?\n- **Time pressure**: Hard deadline?\n\n### 4. Determine Escalation Target\n\nUsing the escalation tiers below, identify the right target: L2 Support, Engineering, Product, Security, or Leadership.\n\n### 5. Structure Reproduction Steps (for bugs)\n\nIf the issue is a bug, follow the reproduction step best practices below to document clear repro steps with environment details and evidence.\n\n### 6. Generate Escalation Brief\n\n```\n## ESCALATION: [One-line summary]\n\n**Severity:** [Critical / High / Medium]\n**Target team:** [Engineering / Product / Security / Leadership]\n**Reported by:** [Your name/team]\n**Date:** [Today's date]\n\n### Impact\n- **Customers affected:** [Who and how many]\n- **Workflow impact:** [What they can't do]\n- **Revenue at risk:** [If applicable]\n- **Time in queue:** [How long this has been an issue]\n\n### Issue Description\n[Clear, concise description of the problem — 3-5 sentences]\n\n### What's Been Tried\n1. [Troubleshooting step and result]\n2. [Troubleshooting step and result]\n3. [Troubleshooting step and result]\n\n### Reproduction Steps\n[If applicable — follow the format below]\n1. [Step]\n2. [Step]\n3. [Step]\nExpected: [X]\nActual: [Y]\nEnvironment: [Details]\n\n### Customer Communication\n- **Last update to customer:** [Date and what was communicated]\n- **Customer expectation:** [What they're expecting and by when]\n- **Escalation risk:** [Will they escalate further if not resolved by X?]\n\n### What's Needed\n- [Specific ask — \"investigate root cause\", \"prioritize fix\",\n  \"make product decision on X\", \"approve exception for Y\"]\n- **Deadline:** [When this needs resolution or an update]\n\n### Supporting Context\n- [Related tickets or links]\n- [Internal discussion threads]\n- [Documentation or logs]\n```\n\n### 7. Offer Next Steps\n\nAfter generating the escalation:\n- \"Want me to post this in a ~~chat channel for the target team?\"\n- \"Should I update the customer with an interim response?\"\n- \"Want me to set a follow-up reminder to check on this?\"\n- \"Should I draft a customer-facing update with the current status?\"\n\n---\n\n## When to Escalate vs. Handle in Support\n\n### Handle in Support When:\n- The issue has a documented solution or known workaround\n- It's a configuration or setup issue you can resolve\n- The customer needs guidance or training, not a fix\n- The issue is a known limitation with a documented alternative\n- Previous similar tickets were resolved at the support level\n\n### Escalate When:\n- **Technical**: Bug confirmed and needs a code fix, infrastructure investigation needed, data corruption or loss\n- **Complexity**: Issue is beyond support's ability to diagnose, requires access support doesn't have, involves custom implementation\n- **Impact**: Multiple customers affected, production system down, data integrity at risk, security concern\n- **Business**: High-value customer at risk, SLA breach imminent or occurred, customer requesting executive involvement\n- **Time**: Issue has been open beyond SLA, customer has been waiting unreasonably long, normal support channels aren't progressing\n- **Pattern**: Same issue reported by 3+ customers, recurring issue that was supposedly fixed, increasing severity over time\n\n## Escalation Tiers\n\n### L1 → L2 (Support Escalation)\n**From:** Frontline support\n**To:** Senior support / technical support specialists\n**When:** Issue requires deeper investigation, specialized product knowledge, or advanced troubleshooting\n**What to include:** Ticket summary, steps already tried, customer context\n\n### L2 → Engineering\n**From:** Senior support\n**To:** Engineering team (relevant product area)\n**When:** Confirmed bug, infrastructure issue, needs code change, requires system-level investigation\n**What to include:** Full reproduction steps, environment details, logs or error messages, business impact, customer timeline\n\n### L2 → Product\n**From:** Senior support\n**To:** Product management\n**When:** Feature gap causing customer pain, design decision needed, workflow doesn't match customer expectations, competing customer needs require prioritization\n**What to include:** Customer use case, business impact, frequency of request, competitive pressure (if known)\n\n### Any → Security\n**From:** Any support tier\n**To:** Security team\n**When:** Potential data exposure, unauthorized access, vulnerability report, compliance concern\n**What to include:** What was observed, who/what is potentially affected, immediate containment steps taken, urgency assessment\n**Note:** Security escalations bypass normal tier progression — escalate immediately regardless of your level\n\n### Any → Leadership\n**From:** Any tier (usually L2 or manager)\n**To:** Support leadership, executive team\n**When:** High-revenue customer threatening churn, SLA breach on critical account, cross-functional decision needed, exception to policy required, PR or legal risk\n**What to include:** Full business context, revenue at risk, what's been tried, specific decision or action needed, deadline\n\n## Business Impact Assessment\n\nWhen escalating, quantify impact where possible:\n\n### Impact Dimensions\n\n| Dimension | Questions to Answer |\n|-----------|-------------------|\n| **Breadth** | How many customers/users are affected? Is it growing? |\n| **Depth** | How severely are they impacted? Blocked vs. inconvenienced? |\n| **Duration** | How long has this been going on? How long until it's critical? |\n| **Revenue** | What's the ARR at risk? Are there pending deals affected? |\n| **Reputation** | Could this become public? Is it a reference customer? |\n| **Contractual** | Are SLAs being breached? Are there contractual obligations? |\n\n### Severity Shorthand\n\n- **Critical**: Production down, data at risk, security breach, or multiple high-value customers affected. Needs immediate attention.\n- **High**: Major functionality broken, key customer blocked, SLA at risk. Needs same-day attention.\n- **Medium**: Significant issue with workaround, important but not urgent business impact. Needs attention this week.\n\n## Writing Reproduction Steps\n\nGood reproduction steps are the single most valuable thing in a bug escalation. Follow these practices:\n\n1. **Start from a clean state**: Describe the starting point (account type, configuration, permissions)\n2. **Be specific**: \"Click the Export button in the top-right of the Dashboard page\" not \"try to export\"\n3. **Include exact values**: Use specific inputs, dates, IDs — not \"enter some data\"\n4. **Note the environment**: Browser, OS, account type, feature flags, plan level\n5. **Capture the frequency**: Always reproducible? Intermittent? Only under certain conditions?\n6. **Include evidence**: Screenshots, error messages (exact text), network logs, console output\n7. **Note what you've ruled out**: \"Tested in Chrome and Firefox — same behavior\" \"Not account-specific — reproduced on test account\"\n\n## Follow-up Cadence After Escalation\n\nDon't escalate and forget. Maintain ownership of the customer relationship.\n\n| Severity | Internal Follow-up | Customer Update |\n|----------|-------------------|-----------------|\n| **Critical** | Every 2 hours | Every 2-4 hours (or per SLA) |\n| **High** | Every 4 hours | Every 4-8 hours |\n| **Medium** | Daily | Every 1-2 business days |\n\n### Follow-up Actions\n- Check with the receiving team for progress\n- Update the customer even if there's no new information (\"We're still investigating — here's what we know so far\")\n- Adjust severity if the situation changes (better or worse)\n- Document all updates in the ticket for audit trail\n- Close the loop when resolved: confirm with customer, update internal tracking, capture learnings\n\n## De-escalation\n\nNot every escalation stays escalated. De-escalate when:\n- Root cause is found and it's a support-resolvable issue\n- A workaround is found that unblocks the customer\n- The issue resolves itself (but still document root cause)\n- New information changes the severity assessment\n\nWhen de-escalating:\n- Notify the team you escalated to\n- Update the ticket with the resolution\n- Inform the customer of the resolution\n- Document what was learned for future reference\n\n## Escalation Best Practices\n\n1. Always quantify impact — vague escalations get deprioritized\n2. Include reproduction steps for bugs — this is the #1 thing engineering needs\n3. Be clear about what you need — \"investigate\" vs. \"fix\" vs. \"decide\" are different asks\n4. Set and communicate a deadline — urgency without a deadline is ambiguous\n5. Maintain ownership of the customer relationship even after escalating the technical issue\n6. Follow up proactively — don't wait for the receiving team to come to you\n7. Document everything — the escalation trail is valuable for pattern detection and process improvement",
  "applicable_domains": [
    "support",
    "customer"
  ],
  "invocation": [
    "/customer-escalation",
    "/customer-escalation <issue summary> [customer name]"
  ],
  "tags": [
    "customer-support",
    "anthropics",
    "knowledge-work"
  ],
  "authored_by": "anthropics",
  "source_url": "https://github.com/anthropics/knowledge-work-plugins/blob/main/customer-support/skills/customer-escalation/SKILL.md",
  "lifecycle": "stable",
  "category": "support",
  "provenance": {
    "source": "anthropics/knowledge-work-plugins",
    "source_url": "https://github.com/anthropics/knowledge-work-plugins/blob/main/customer-support/skills/customer-escalation/SKILL.md",
    "author": "Anthropic",
    "license": "Apache-2.0",
    "notes": "Imported by scripts/import-anthropic-skills.py."
  }
}