gitcrawl

Searches local GitHub issue and PR archives before live GitHub triage.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill gitcrawl-amirulandalib
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gitcrawl
Source: https://github.com/AmirulAndalib/Vilvona-AI/tree/main/.agents/skills/gitcrawl
Command: npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill gitcrawl-amirulandalib

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gitcrawl.

What problem does it solve? Live GitHub searches are slow and rate-limited when triaging large repositories. This Skill lets you query a local archive of issues and pull requests first, checking sync freshness and finding duplicates, then escalating to live GitHub only when a mutation or merge decision requires verified current state. ## Core Features & Use Cases - Local Archive Search: Query cached issues and PRs with gitcrawl search, threads, and neighbors commands instead of hitting the GitHub API. - Duplicate Detection: Find duplicate clusters with gitcrawl clusters and inspect them via cluster-detail before closing or labeling issues. - Freshness Verification: Run gitcrawl doctor --json to check archive sync status, and use the gh-shim (gitcrawl gh pr status) with a --live fallback before commenting, merging, or reviewing. - Use Case: When triaging an incoming bug report on openclaw/openclaw, search the local archive for related threads and duplicate clusters, then verify with live gh before closing it as a duplicate. ## Quick Start Ask the assistant to check archive freshness with gitcrawl doctor, then search the local issue archive for threads related to a specific issue number before verifying with live GitHub.

Frequently Asked Questions about gitcrawl

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

FAQPage Schema
How do I search GitHub issues without hitting API rate limits?▼

Use gitcrawl to query a local archive of issues and PRs instead of the live GitHub API. Commands like `gitcrawl search issues` and `gitcrawl threads` return cached results, and `gitcrawl doctor --json` confirms the archive is fresh.

How do I find duplicate GitHub issues in a large repository?▼

Run `gitcrawl clusters <repo> --sort size --min-size 5` to list duplicate clusters, then inspect one with `gitcrawl cluster-detail --id <cluster-id>`. Do not close issues from similarity alone; verify matching intent with live `gh issue view` first.

How do I check if the local GitHub archive is up to date?▼

Run `gitcrawl doctor --json` to check sync freshness before relying on cached results. If the archive is stale or a decision involves mutation, escalate to live data with `gitcrawl gh --live pr status` or the standard `gh` CLI.

Can I merge or close PRs based only on cached gitcrawl data?▼

No. The Skill requires live verification with `gh pr view` or `gitcrawl gh --live` plus checkout proof before commenting, labeling, closing, reopening, merging, or filing a review. Cached data is for discovery, not mutation decisions.

What are the limitations of local GitHub archive search?▼

Local archives can lag behind live GitHub state, so recently opened or updated issues may be missing. The workflow mitigates this by checking freshness with `gitcrawl doctor` and requiring live `gh` verification before any write operation.