Skip to content
Get packs

Geofeed Tuner

Checks and improves IP geolocation feed CSV files for RFC 8805 compliance and real-world accuracy

Source Download skill
Repository
github/awesome-copilot
Stars
40,703
Licence
MIT
Files
6 files

What it does

This skill teaches an AI agent to help network operators build and clean up a geolocation feed, a public CSV file that says which city or country each block of their public IP addresses is in. Once installed, the agent checks the file's structure and consistency against the RFC 8805 standard, looks for data quality problems, looks up tuning suggestions through a Fastah service, and produces an HTML report summarising the findings. The skill's files are reference data and instructions; the agent is told to write and run Python scripts to do the checks.

Great for

  • Network engineers at ISPs, mobile carriers, or hosting companies who publish a geofeed
  • Operators who want to validate a CSV geofeed before submitting it to geolocation providers
  • Teams reviewing IP location accuracy for publicly routable address space

Skip it if

  • Managing private or internal IP addresses, which the skill explicitly excludes because it applies only to publicly routable addresses
  • General web or front-end design work despite the category label, since the skill has nothing to do with visual design
  • Users without Python 3, since the workflow depends on running Python scripts

Try asking

  • “Check my geofeed CSV at this path for RFC 8805 formatting errors”
  • “Review my IP geolocation feed and suggest improvements for accuracy”
  • “Create a geofeed in CSV format for my ISP's IPv4 and IPv6 prefixes”
  • “Generate an HTML tuning report for my geofeed file”
Step-by-step guide: how to use Geofeed TunerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the MIT licence and an attribution note.

    geofeed-tuner.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip geofeed-tuner.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip geofeed-tuner.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Use the example CSV in assets/example to see the expected format before submitting your own file
  • Keep your feed limited to publicly routable prefixes and review the report before publishing anything
  • Note that Phase 4 sends data to an external Fastah MCP service; check that you are comfortable with that before using the skill on sensitive network data

What's inside

  • assets/example/01-user-input-rfc8805-feed.csv
  • assets/iso3166-1.json
  • assets/small-territories.json
  • references/rfc8805.txt
  • references/snippets-python3.md
  • SKILL.md

Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.