Skip to content
Back to skills

Csv Metrics

ASecurity

Compute summary statistics for a CSV and write a JSON + markdown report. Use when the user asks to analyze, summarize, profile, or compute metrics for a CSV / tabular dataset.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 3, 2026
ai-agentspythonbash

Security analysis

A92/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 2 files and shows the line behind each finding

Scanned October 4, 2026

npx -y skills add yaniv-golan/cowork-harness --skill csv-metrics --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Csv Metrics?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Csv Metrics
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yaniv-golan-csv-metrics/badge)](https://www.skillsdirectory.com/skills/yaniv-golan-csv-metrics)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: csv-metrics
description: Compute summary statistics for a CSV and write a JSON + markdown report. Use when the user asks to analyze, summarize, profile, or compute metrics for a CSV / tabular dataset.
---

# csv-metrics

Profiles a CSV and writes two deliverables: a structured `metrics.json` and a
human-readable `summary.md`. The work is done by a **bundled producer script**
(`scripts/metrics.py`) — you run it, you don't reimplement it.

## When to use

The user has a CSV (in `uploads/` or a connected project folder) and wants
per-column statistics or a metrics report.

## How to run

1. Locate the CSV. Default for this example: `uploads/sales.csv`.
2. Run the bundled producer, passing the CSV and the output directory. The
   script lives under this skill's `scripts/` folder, reachable via
   `${CLAUDE_PLUGIN_ROOT}`:

   ```bash
   S="${CLAUDE_PLUGIN_ROOT}/skills/csv-metrics/scripts/metrics.py"
   [ -f "$S" ] || S="$(find /sessions/*/mnt/.local-plugins /sessions/*/mnt/.remote-plugins \
     -path '*/skills/csv-metrics/scripts/metrics.py' 2>/dev/null | head -1)"
   python3 "$S" uploads/sales.csv outputs
   ```

   In Cowork's default host-loop mode the bash tool rewrites the host path the agent writes in
   for `${CLAUDE_PLUGIN_ROOT}` to the plugin's mount inside the VM, so the first line finds the
   script; the second line is the fallback for a Desktop older than 1.40609.0, or a plugin whose
   mount path the rewrite skips, and finds the script at that mount.

   It writes `outputs/metrics.json` and `outputs/summary.md` and prints a
   one-line summary.
3. Read `outputs/summary.md`, then reply with a single line that includes the
   row count and the path `outputs/metrics.json`.

## Constraints

- The producer uses **only the Python standard library** — no `pip install`, no
  network. That is deliberate: under Cowork the agent runs with default-deny
  egress and no pypi access, so a skill's producer must be self-contained.
- Treat `outputs/` as write-once for the deliverable: don't delete or rewrite
  the files after the producer emits them.

Files in this skill

  • SKILL.md1.9 KB
  • scripts/metrics.py4.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.