Github Issue Dedupe

Organization

warpdotdev

github-issue-dedupe

Detect duplicate GitHub issues using semantic search and keyword matching. Use when asked to find duplicates, check for similar issues, or set up automated duplicate detection.

Overview

Publisher	warpdotdev
Repository	`oz-skills`
Skill name	`github-issue-dedupe`
Stars	824
Forks	68
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by warpdotdev on GitHub. Read the source before you install it.

Installation

Install the Github Issue Dedupe AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/warpdotdev/oz-skills/tree/main/.agents/skills/github-issue-dedupe
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/warpdotdev/oz-skills.git /tmp/oz-skills
mkdir -p .claude/skills
cp -r /tmp/oz-skills/.agents/skills/github-issue-dedupe .claude/skills/github-issue-dedupe

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Issue Dedupe in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Github Issue Dedupe on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Github Issue Dedupe is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

GitHub Duplicate Issue Detection

Find duplicate GitHub issues using multi-strategy search. Can be run manually or automated via GitHub Actions.

Workflow

1. Gather Issue Context

Extract key information from the target issue:

Issue number and title
Full body content
Error messages or stack traces
Keywords and technical terms
Symptoms or behavior descriptions

2. Search Strategy

Use gh to search for related issues using multiple strategies:

Keyword search from title and body
Search for similar error messages
Look for similar symptoms

3. Candidate Inspection

For each potential duplicate:

View full issue with gh issue view <number>
Compare:
- Root cause (same underlying problem?)
- Symptoms (identical behavior?)
- Error messages (exact match or very similar?)
- Affected components (same area of code?)

High confidence indicators:

Identical error messages
Same reproduction steps
Same root cause with different descriptions
One issue references the other

Low confidence (not duplicates):

Similar symptoms but different causes
Related but independent bugs
Same component but different behaviors

4. Report Findings

If duplicates found:

Post comment on target issue:

bash
gh issue comment <number> --body "This is potentially a duplicate of #123 and #456."

Format rules:

Single duplicate: "This is potentially a duplicate of #123."
Two duplicates: "This is potentially a duplicate of #123 and #456."
Three+ duplicates: "This is potentially a duplicate of #123, #456, and #789."

Only comment if high confidence (90%+ certain). When uncertain, do nothing.

Examples

Example 1: Clear Duplicate

Target Issue #150:


Title: "Dropdown menu stays open on mobile Safari"
Body: Clicking menu items doesn't close dropdown on iOS

Search process:

bash
gh issue list --search "dropdown mobile safari"
gh issue list --search "menu doesn't close"
gh issue view 87  # Found similar issue

Issue #87:


Title: "Mobile menu not closing after selection"
Body: On iOS Safari, menu stays open after clicking items

Determination: Duplicate

Same symptom (menu stays open)
Same platform (iOS Safari)
Same root cause

Example 2: Similar But Not Duplicate

Target Issue #200:


Title: "Form validation error on submit"
Error: "Cannot read property 'value' of null"

Search process:

bash
gh issue list --search "form validation"
gh issue list --search "Cannot read property value null"
gh issue view 175

Issue #175:


Title: "Form submission fails"
Error: "Cannot read property 'email' of undefined"

Determination: Not duplicate

Different error messages
Different null references (value vs email)
Related area but different bugs

Example 3: Multiple Duplicates

Target Issue #300:


Title: "Build fails with 'module not found' error"
Error: Error: Cannot find module './config'

Search results:

Issue #250: Same error, same module
Issue #280: Same error, same module
Issue #290: Different module error (not duplicate)

Action:

bash
gh issue comment 300 --body "This is potentially a duplicate of #250 and #280."

Frequently asked questions

What does the Github Issue Dedupe AI skill do?

Detect duplicate GitHub issues using semantic search and keyword matching. Use when asked to find duplicates, check for similar issues, or set up automated duplicate detection.

Why use Github Issue Dedupe on TypingMind?

Because you install it once and use it with any model. Github Issue Dedupe is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Github Issue Dedupe in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/warpdotdev/oz-skills/tree/main/.agents/skills/github-issue-dedupe. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Github Issue Dedupe?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Github Issue Dedupe?

As many as you like. As long as a model supports skills, you can use Github Issue Dedupe with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Github Issue Dedupe AI skill free?

Yes. It is published on GitHub by warpdotdev under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Deploy Release Test

vercel

OrganizationPopular

Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the test_e2e_deploy_release.yml GitHub Actions workflow. Use only when asked to…

Insight Error Page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new `errors/<slug>.mdx` page, auditing an existing one, or checking that a page matches the framework fix…

Mcp Apps Builder

**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP…

Canary

Post-deploy canary monitoring. (gstack)

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

GitHub Duplicate Issue Detection

Workflow

1. Gather Issue Context

2. Search Strategy

3. Candidate Inspection

4. Report Findings

Examples

Example 1: Clear Duplicate

Example 2: Similar But Not Duplicate

Example 3: Multiple Duplicates

Frequently asked questions

Related AI Skills

Set up your own AI workspace now