← Back to Skills Marketplace
gitgoodordietrying

CSV Data Pipeline

by gitgoodordietrying · GitHub ↗ · v1.0.0
linuxdarwinwin32 ✓ Security Clean
7410
Downloads
2
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install csv-pipeline
Description
Process, transform, analyze, and report on CSV and JSON data files. Use when the user needs to filter rows, join datasets, compute aggregates, convert formats, deduplicate, or generate summary reports from tabular data. Works with any CSV, TSV, or JSON Lines file.
Usage Guidance
Install this if you want an agent to help process local CSV, TSV, JSON, or JSON Lines files. Give clear file paths, keep backups before overwriting important datasets, and only use sensitive data when you intend the agent to read and transform it.
Capability Analysis
Type: OpenClaw Skill Name: csv-pipeline Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'csv-pipeline' is benign. All commands and Python code provided in SKILL.md are standard utilities and library functions for local CSV/JSON data processing (e.g., `head`, `awk`, `sort`, `csv`, `json`). There is no evidence of data exfiltration, malicious execution (like downloading and running remote payloads), persistence mechanisms, or obfuscation. The SKILL.md content serves as legitimate instructions for using the skill and does not contain any prompt injection attempts designed to subvert the agent's behavior or access unrelated sensitive data.
Capability Assessment
Purpose & Capability
The documented shell and Python examples match the stated purpose: inspecting, filtering, joining, deduplicating, converting, validating, aggregating, and reporting on CSV, TSV, JSON, and JSON Lines files.
Instruction Scope
The skill tells an agent to read and write local data files, which is expected for data processing, but users should provide explicit input and output paths to avoid accidental overwrites.
Install Mechanism
The artifact is instruction-only Markdown and declares only standard runtime availability such as Python or common command-line tools; it does not bundle executables or install external packages.
Credentials
Local file access and standard tools such as Python csv/json, awk, sort, and sqlite3 are proportionate to CSV/JSON processing; no network, account, browser profile, or credential access is requested.
Persistence & Privilege
No persistence, background workers, privilege escalation, scheduled execution, obfuscation, or long-lived state are present in the artifact.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install csv-pipeline
  3. After installation, invoke the skill by name or use /csv-pipeline
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - CSV/JSON/TSV data processing with filtering, joining, grouping, aggregation, format conversion, deduplication, validation, and report generation using Python and standard CLI tools.
Metadata
Slug csv-pipeline
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is CSV Data Pipeline?

Process, transform, analyze, and report on CSV and JSON data files. Use when the user needs to filter rows, join datasets, compute aggregates, convert formats, deduplicate, or generate summary reports from tabular data. Works with any CSV, TSV, or JSON Lines file. It is an AI Agent Skill for Claude Code / OpenClaw, with 7410 downloads so far.

How do I install CSV Data Pipeline?

Run "/install csv-pipeline" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is CSV Data Pipeline free?

Yes, CSV Data Pipeline is completely free (open-source). You can download, install and use it at no cost.

Which platforms does CSV Data Pipeline support?

CSV Data Pipeline is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).

Who created CSV Data Pipeline?

It is built and maintained by gitgoodordietrying (@gitgoodordietrying); the current version is v1.0.0.

💬 Comments