support-analytics

Answer questions about support ticket data by querying SQLite and interpreting results. Use when asked about ticket volume, trends, resolution times, agent workload, or issue patterns.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "support-analytics" with this command: npx skills add elifokaju/support-analytics-agent/elifokaju-support-analytics-agent-support-analytics

Support Analytics Agent

Answer support analytics questions by combining SQL queries with natural language interpretation.

Data Source

SQLite database: data/tickets.db

Schema:

CREATE TABLE tickets (
    ticket_id TEXT PRIMARY KEY,
    created_at TEXT,        -- ISO timestamp
    resolved_at TEXT,       -- ISO timestamp (NULL if open)
    status TEXT,            -- open, resolved
    issue_type TEXT,        -- fraud, transfer, card, account
    urgency TEXT,           -- low, medium, high, critical
    customer_id TEXT,
    assigned_to TEXT        -- agent name
);

Workflow

  1. Understand the question — What metric or insight is the user asking for?
  2. Select or build query — Use a pre-built query from queries/ or construct one
  3. Execute query — Run against SQLite using: sqlite3 data/tickets.db "SELECT ..."
  4. Interpret results — Explain what the numbers mean, not just what they are
  5. Recommend action — If something looks unusual, suggest next steps

Pre-built Queries

Question PatternQuery FileWhat It Returns
"Top issues" / "What's trending"queries/top-issues.sqlIssue types ranked by volume, week-over-week change
"Resolution time" / "How long to resolve"queries/resolution-time.sqlAvg hours by issue type
"Daily volume" / "Ticket trend"queries/daily-volume.sqlDaily counts with fraud breakdown
"What's open" / "Current queue"queries/open-tickets.sqlOpen tickets grouped by urgency
"Agent workload" / "Distribution"queries/agent-workload.sqlTickets per agent with resolution stats

If no pre-built query matches, construct a simple SELECT against the schema above.

Response Format

For quick questions:

[Key finding in 1-2 sentences with specific numbers]

[Comparison to baseline or previous period if available]

[Recommendation if something looks unusual]

For summary requests ("give me a report"):

## Support Summary — [Date Range]

**Volume:** [total tickets] ([change from previous period])

**Top Issues:**
1. [Issue] — [count] ([trend])
2. [Issue] — [count] ([trend])

**Flagged:**
- [Any anomaly worth investigating]

**Recommendation:** [One actionable next step]

Issue Type Reference

TypeCovers
fraudUnauthorized transactions, account takeover, suspicious activity
transferMoney transfer issues, delays, failures
cardCard delivery, activation, transaction problems
accountLogin issues, profile changes, verification

Interpretation Guidelines

  • Spikes >50% week-over-week = flag for investigation
  • Resolution time >24h for high priority = flag as SLA risk
  • Single agent >30% of tickets = potential bottleneck
  • Fraud increases always warrant immediate callout

Example

User: "What are the top issues this week?"

Agent actions:

  1. Run sqlite3 data/tickets.db < queries/top-issues.sql
  2. Get results: fraud 19 (+171%), transfer 11 (+57%), card 8 (+100%), account 4 (+33%)
  3. Interpret and respond:

Fraud is your top issue this week with 19 tickets — up 171% from last week. This spike needs immediate attention.

Transfer issues are second at 11 tickets (+57%). Card issues doubled but remain lower volume at 8.

Recommendation: Investigate the fraud spike to identify if there's a specific pattern or attack vector driving the increase.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

clinic-visit-prep

帮助患者整理就诊前问题、既往记录、检查清单与时间线,不提供诊断。;use for healthcare, intake, prep workflows;do not use for 给诊断结论, 替代医生意见.

Archived SourceRecently Updated
Automation

changelog-curator

从变更记录、提交摘要或发布说明中整理对外 changelog,并区分用户价值与内部改动。;use for changelog, release-notes, docs workflows;do not use for 捏造未发布功能, 替代正式合规审批.

Archived SourceRecently Updated
Automation

klaviyo

Klaviyo API integration with managed OAuth. Access profiles, lists, segments, campaigns, flows, events, metrics, templates, catalogs, and webhooks. Use this skill when users want to manage email marketing, customer data, or integrate with Klaviyo workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).

Archived SourceRecently Updated