gitcrawl

Search local GitHub issue and PR archives to identify related threads.

7|12|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/borealBytes/my-farm-advisor --skill gitcrawl-borealbytes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gitcrawl
Source: https://github.com/borealBytes/my-farm-advisor/tree/main/.agents/skills/gitcrawl
Command: npx skills add https://github.com/borealBytes/my-farm-advisor --skill gitcrawl-borealbytes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local GitHub issue/PR archives enable offline triage and faster discovery before hitting live GitHub searches.

Core Features & Use Cases

  • Use cached data to identify candidates, neighbors, and clusters.
  • Support for repository-wide triage across multiple projects.
  • Use cases include incident triage, duplicate detection, and historical context gathering for PRs and issues.

Quick Start

Run gitcrawl doctor --json to validate archives, then run gitcrawl threads <repo> --numbers <issue-or-pr-number> --include-closed --json to locate related threads.

Frequently Asked Questions about gitcrawl

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search local GitHub issue archives for offline triage?

To search local GitHub issue archives for offline triage, run gitcrawl commands to query cached data, discovering candidates, neighbors, and clusters across multiple repository projects without hitting live APIs.

What is the best way to detect duplicate issues in GitHub repositories?

The best way to detect duplicate issues in GitHub repositories is correlating local PR and issue archives to identify neighbors and clusters, keeping triage accurate before executing live GitHub searches.

Do I need to install Go to use gitcrawl for historical context gathering?

Yes, historical context gathering requires the gitcrawl binary and its Go-based installation to be available in your environment, enabling cached checks and live lookups across OpenClaw repositories.

How do I validate cached GitHub pull request archives before triage?

To validate cached GitHub pull request archives before triage, run gitcrawl doctor --json to ensure archive integrity, then use gitcrawl threads with --include-closed --json to locate related threads.

When should I use offline GitHub issue search instead of live queries?

Use offline GitHub issue search instead of live queries when performing repository-wide triage across multiple projects, needing faster discovery, or gathering historical context for incident triage without API rate limits.