github-issue-dedupe

Detect and consolidate duplicate GitHub issues using semantic similarity matching.

Updated Feb 18, 2026
One-click install
npx skills add https://github.com/Greenmamba29/skillsdotmd_web --skill github-issue-dedupe-greenmamba29
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: github-issue-dedupe
Source: https://github.com/Greenmamba29/skillsdotmd_web/tree/main/.agents/skills/github-issue-dedupe
Command: npx skills add https://github.com/Greenmamba29/skillsdotmd_web --skill github-issue-dedupe-greenmamba29

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill tackles the common problem of duplicate issues cluttering GitHub repositories, saving developers and project managers time and effort.

Core Features & Use Cases

  • Duplicate Detection: Uses semantic similarity to identify issues reporting the same problem.
  • Consolidation: Links duplicates to a canonical issue, keeping all context in one place.
  • Automation: Automatically closes duplicates and adds relevant comments.
  • Use Case: In a busy open-source project, this skill can automatically find and link multiple reports of the same bug, ensuring that developers focus on unique issues and reducing backlog noise.

Quick Start

Run the github-issue-dedupe skill to find and merge duplicate issues in the 'org/my-app' repository.

Frequently Asked Questions about github-issue-dedupe

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

FAQPage Schema
How do I automatically find and consolidate duplicate GitHub issues?

You can detect duplicate GitHub issues by running an automated deduplication script that uses semantic similarity matching to identify redundant reports, link their comments, close the duplicates, and maintain a single canonical issue with consolidated context.

How does semantic similarity matching work for bug tracking deduplication?

Semantic similarity matching for bug tracking deduplication applies cosine similarity to text analysis, comparing the text of GitHub issue reports to identify those describing the same problem and consolidate them into one canonical issue.

Do I need the GitHub CLI to automate issue deduplication in my repository?

Yes, automating GitHub issue deduplication requires the GitHub CLI for fetching issue data from your repository, which is then processed using cosine similarity to identify and consolidate duplicate reports.

Can I use automated issue deduplication for project management in busy open-source projects?

Automated issue deduplication is highly effective for project management in busy open-source projects, automatically finding and linking multiple bug reports to reduce backlog noise and ensure developers focus on unique issues.

What happens to the context when duplicate GitHub issues are closed?

When duplicate GitHub issues are closed, their context is preserved by linking comments to a maintained canonical issue, keeping all relevant information consolidated in one place for developers.

What is the best way to reduce GitHub backlog noise from duplicate bug reports?

The best way to reduce GitHub backlog noise from duplicate bug reports is to implement automated deduplication that detects similar issues, closes the duplicates, and maintains a canonical issue with consolidated context.