pandas — Claude Code skill: support ticket analytics
A skill that brings pandas expertise to support operations: SLA compliance, agent metrics, PostgreSQL pulls. Useful when you need to dig through tickets and build a report.
npx skills add manutej/luxor-claude-marketplace --skill pandas -a claude-codeWhat pandas does
The skill gives the agent pandas patterns aimed at customer support: DataFrame operations, .loc[] and .iloc[] indexing, the query method, multi-level indexes, time series work. It ships with ready-made function templates — first response and resolution times, SLA checks split by priority, ticket volume resampled by period with rolling averages, and per-agent metrics covering CSAT and reopen rate.
There is a separate section on PostgreSQL through SQLAlchemy: building the connection engine and loading tickets with a date filter. Dependencies are listed in the skill itself: pandas>=2.2.0, sqlalchemy>=2.0.0, psycopg2-binary>=2.9.0, numpy>=1.26.0, openpyxl>=3.1.0, pytest>=8.0.0. Install them first. Without psycopg2-binary the PostgreSQL connection will not come up, and without openpyxl you get no Excel export.
The skill targets several platforms: Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each has its own install path and its own SKILL.md location.
What it helps with
- measure first response and resolution time per ticket
- check whether support meets SLA targets by priority
- build weekly volume trends with rolling averages
- compare agents on CSAT and reopen rate
- pull tickets from PostgreSQL into a DataFrame and export a report to Excel
Example prompts for the agent
- Compute SLA compliance for last month's tickets, broken down by priority
- Build agent metrics: average response time, CSAT, reopen rate
- Load tickets from PostgreSQL for the quarter and chart the weekly trend
How to install pandas
1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill pandas -a claude-code2Manually: put the files in place
~/.claude/skills/pandas/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pandas/
1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill pandas -a codex2Manually: put the files in place
.agents/skills/pandas/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill pandas -a cursor2Manually: put the files in place
.cursor/skills/pandas/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install manutej/luxor-claude-marketplace pandas2Manually: put the files in place
.github/skills/pandas/SKILL.md1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill pandas -a gemini-cli2Platform CLI
gemini skills install https://github.com/manutej/luxor-claude-marketplace --path plugins/luxor-database-pro/skills/pandasManually: put the files in place
.devin/skills/pandas/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill pandas -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pandas
How do I install pandas in Claude?
Run npx skills add manutej/luxor-claude-marketplace --skill pandas -a claude-code. The skill lands in ~/.claude/skills/pandas/SKILL.md.
What does the pandas skill do?
It hands the agent data analysis templates for support work: SLA calculations, agent metrics, ticket volume over time, and PostgreSQL loads via SQLAlchemy.
What do I need before using it?
The dependencies it lists: pandas>=2.2.0, sqlalchemy>=2.0.0, psycopg2-binary>=2.9.0, numpy>=1.26.0, openpyxl>=3.1.0, pytest>=8.0.0.