Skip to main content

Github Expert - Agentic tools for github

Project description

ge — GitHub Engineering for AI Agents

Tools and skills that let AI coding agents work on GitHub issues, PRs, and discussions intelligently.

pip install ge
ge install-skills   # register skills with Claude Code

Now, from any project, tell your AI agent "work on issue #42" — it will prepare full context, check freshness, download media, and proceed with informed decisions.

Install skills for Claude Code

ge ships Claude Code skills that teach the agent how to work on GitHub issues. After installing the package, register the skills globally:

ge install-skills

This creates symlinks in ~/.claude/skills/ pointing to the skills bundled with ge. From then on, when you ask Claude Code to work on a GitHub issue in any project, it will automatically:

  1. Verify the issue belongs to the current project
  2. Fetch the full issue context (body, comments, media, cross-references)
  3. Analyze freshness — is it stale? already fixed? has related merged PRs?
  4. Ask you before working on ambiguous or likely-resolved issues
  5. Request you paste images when visual context matters

Three skills are installed:

Skill Purpose
ge Full workflow — verify, prepare, analyze, work
ge-analyze Quick triage — check if an issue is worth working on
ge-context Context preparation — fetch and assemble structured documents

To remove the skills: ge uninstall-skills

What it does

ge fetches an issue or PR and assembles everything an agent needs:

  • Issue/PR body and all comments — with media URLs rewritten to local paths
  • Images downloaded — screenshots, mockups, error captures (with auto-detected extensions)
  • Video frames extracted — via ffmpeg scene detection; bare GitHub asset URLs are auto-detected as video/image from content
  • Freshness analysis — is this issue stale? already fixed? has related merged PRs?
  • Cross-references — commits and PRs that mention this issue
  • Code file checks — do the files mentioned in the issue still exist?

All via gh CLI, so private repos just work.

Quick start

# Install
pip install ge

# Prepare context for an issue
ge prepare owner/repo --number 42

# Or from a URL
ge prepare https://github.com/owner/repo/pull/7

# Just check freshness (no download)
ge analyze-issue owner/repo 42

Requirements

  • gh CLI — installed and authenticated (gh auth login)
  • ffmpeg — optional, for video frame extraction
  • Python 3.10+

Commands

ge prepare <repo> --number <N>              Full context (auto-detects issue/PR/discussion)
ge prepare <url>                           Full context from a GitHub URL
ge prepare-discussion <repo> --number <N>  Full context for a GitHub Discussion
ge analyze-issue <repo> <N>                Freshness analysis (JSON, no download)
ge analyze-pr <repo> <N>                   PR review analysis with CI status (JSON)
ge fetch-issue <repo> <N>                  Raw issue JSON
ge fetch-pr <repo> <N>                     Raw PR JSON
ge fetch-discussion <repo> <N>             GitHub Discussion JSON
ge media <file.md>                 Download media from markdown
ge video-frames <video>            Extract frames (scene detection by default)
ge install-skills                  Register skills with Claude Code (~/.claude/skills/)
ge uninstall-skills                Remove ge skill symlinks

Project structure

ge/
├── __init__.py      # Facade: prepare(), install_skills(), etc.
├── __main__.py      # CLI via argh (SSOT: _cli_commands list)
├── github.py        # GitHub API via `gh` CLI subprocess
├── media.py         # Image download + video frame extraction (ffmpeg)
├── analysis.py      # Staleness/freshness/relevance analysis
├── context.py       # Assembles everything into context docs
├── util.py          # Internal helpers: gh wrapper, URL parsing, media extraction
└── data/skills/     # Claude Code skills (symlinked by install-skills)
    ├── ge/          # Full workflow skill
    ├── ge-analyze/  # Triage/staleness skill
    └── ge-context/  # Context preparation skill

Python API

import ge

ctx = ge.prepare_issue('owner/repo', 42)
ctx = ge.prepare_pr('owner/repo', 7)
ctx = ge.prepare_discussion('owner/repo', 5)

# Or from any GitHub URL (auto-detects type)
ctx = ge.prepare('https://github.com/owner/repo/issues/42')
ctx = ge.prepare('https://github.com/owner/repo/discussions/5')

# Just analysis
analysis = ge.analyze_issue('owner/repo', 42)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ge-0.1.4.tar.gz (42.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ge-0.1.4-py3-none-any.whl (29.5 kB view details)

Uploaded Python 3

File details

Details for the file ge-0.1.4.tar.gz.

File metadata

  • Download URL: ge-0.1.4.tar.gz
  • Upload date:
  • Size: 42.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.2 {"installer":{"name":"uv","version":"0.11.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for ge-0.1.4.tar.gz
Algorithm Hash digest
SHA256 bb65b8b4152d5c97bd3a77942f6865b34e01d9175333ead7b1c9a56a4cb4abf6
MD5 138723a6a5ef40f009368301cdb81324
BLAKE2b-256 2d50da15bf0d4c45689049c5699832a609893c60b2584cbb535f85d65f4a57a8

See more details on using hashes here.

File details

Details for the file ge-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: ge-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 29.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.2 {"installer":{"name":"uv","version":"0.11.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for ge-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 5335bbad17399f095c82b8cf8b23abe63af97e5235173abc6dd13c724630a437
MD5 a0fde9ffbb6b38f853d912e73edd99d7
BLAKE2b-256 03a1beae61b134a24b783c5b326ee2a1372281092c1074cc6fa785ec4635f173

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page