Ring:Generating Pr Descriptions logo

Ring:Generating Pr Descriptions

Organization
LerianStudio
ring:generating-pr-descriptions

Generating pull request descriptions from git branch changes with automatic title generation, change-type detection, and smart analysis. Uses branch-only scope to avoid full history analysis. Use when preparing a PR for review. Skip when the PR is a single trivial commit or description already exists.

Overview

PublisherLerianStudio
Repositoryring
Skill namering:generating-pr-descriptions
Stars
215
Forks
28
Bundled files
Instructions only
LicenseApache-2.0
Links
  • 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 LerianStudio on GitHub. Read the source before you install it.

Installation

Install the Ring:Generating Pr Descriptions AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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/LerianStudio/ring.git /tmp/ring
mkdir -p .claude/skills
cp -r /tmp/ring/default/skills/generating-pr-descriptions .claude/skills/lerianstudio-ring-generating-pr-descriptions
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ring:Generating Pr Descriptions 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 Ring:Generating Pr Descriptions 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 Ring:Generating Pr Descriptions 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.

Generating PR Descriptions

When to use

  • Preparing a pull request for review and need a comprehensive description
  • Generating a PR title automatically from commit message analysis
  • Classifying the type of change (bug fix, feature, breaking change)
  • Saving a reusable PR description to docs/pr-descriptions/<branch-name-with-hyphens>.md

Skip when

  • The PR is a single trivial commit with an obvious description
  • A PR description already exists and does not need regeneration
  • The branch has no commits beyond the base branch

Process

1. Git Branch Analysis - CRITICAL: Branch-Only Scope

  • MANDATORY: Identify actual branch point to avoid analyzing entire development history
  • Detect the base branch (develop, main, master) that the current branch was created from
  • CORRECT APPROACH: Use git merge-base HEAD <base-branch> to find the true divergence point
  • CORRECT APPROACH: Use git log --oneline $(git merge-base HEAD <base-branch>)..HEAD for branch-specific commits
  • CORRECT APPROACH: Use git diff $(git merge-base HEAD <base-branch>)..HEAD for branch-specific changes
  • NEVER rely on manual HEAD~n counting — it breaks on merges, rebases, and long-lived branches
  • Run git status --porcelain to identify uncommitted files (excluded from PR)
  • Enforce that PR analyzes ONLY commits made on the current feature branch, not development history
  • Determine if this is a bug fix, feature, or breaking change based on actual branch commits

2. Change Classification

  • Analyze file patterns and change types
  • Identify the type of change (bug fix, new feature, breaking change, etc.)
  • Detect if documentation updates are needed
  • Determine testing requirements

3. PR Description Generation

  • Create comprehensive description following the template format
  • Include summary of changes and motivation based on ONLY branch-specific commits
  • Pre-fill appropriate checkboxes based on change analysis
  • Suggest testing strategies
  • Derive the output filename from the full branch name with slashes replaced by hyphens (e.g., feature/FE-157 -> feature-FE-157.md)
  • Save to docs/pr-descriptions/<derived-filename> (create directory if needed)

CRITICAL Implementation Steps

Step 1: Branch Analysis (MANDATORY)

bash
# 1. Get branch structure to identify commits
git log --oneline --decorate --graph -10

# 2. Count commits unique to current branch
# Look for where branch diverged from main/develop
# Example output shows 2 commits on feature/PLU-393:
# * 06603bf (HEAD -> feature/PLU-393) fix(i18n): add missing translations
# * d40c631 feat(ui): enhance templates system with calendar filter
# * 30664b1 (develop) Merge branch 'develop' into feature/libs

Step 2: Extract Branch-Only Changes (MANDATORY)

bash
# Use HEAD~n where n = number of branch commits
git log --oneline HEAD~2..HEAD           # Get branch commits
git diff HEAD~2..HEAD --name-status      # Get changed files
git diff HEAD~2..HEAD --stat            # Get change statistics

Step 3: Validation (MANDATORY)

  • Verify commit count matches actual branch commits
  • Ensure no base branch commits are included in analysis
  • Confirm file changes align with branch purpose

WRONG APPROACH - DO NOT USE:

bash
git log main..HEAD      # Includes entire development history
git diff main...HEAD    # Includes all changes since branch creation

Generated Template Structure

The skill generates pull requests following this exact structure:

markdown
# [Auto-generated PR title: short, under 70 chars, using conventional commit prefix]

# Description

[Auto-generated summary of changes and motivation based on commits]

## Type of change

- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
- [ ] This change requires a documentation update

PR Title Generation

  • Auto-generated from commit message analysis
  • Uses conventional commit prefix (feat:, fix:, chore:, refactor:, etc.) based on the dominant change type
  • Kept under 70 characters, concise and descriptive
  • Placed as the first # heading in the output file

Change Type Detection

  • Bug fix: Detects fixes, corrections, and patches in commit messages
  • New feature: Identifies new functionality, components, or capabilities
  • Breaking change: Flags API changes, removed functionality, or incompatible changes
  • Documentation update: Detects changes to .md files, comments, or docs folders

Implementation Requirements - CRITICAL

MANDATORY Git Command Usage:

  1. Branch Point Detection:

    bash
    git log --oneline --decorate --graph -10
    # Identify where current branch diverged from base
    # Count commits unique to current branch
  2. Branch-Only Analysis Commands:

    bash
    # For 2 commits on current branch:
    git log --oneline HEAD~2..HEAD
    git diff HEAD~2..HEAD --name-status
    git diff HEAD~2..HEAD --stat
    
    # NEVER use these (includes all development history):
    git log main..HEAD  # WRONG
    git diff main...HEAD  # WRONG
  3. Branch Point Validation:

    • If branch has 3 commits: use HEAD~3..HEAD
    • If branch has 5 commits: use HEAD~5..HEAD
    • Always verify commit count matches actual branch commits

Smart Analysis Features

  • File Pattern Recognition: Detects frontend/backend changes, test files, config changes
  • Commit Message Analysis: Uses conventional commits to determine change types
  • Dependency Detection: Identifies if package.json or similar files changed
  • Test Coverage: Suggests appropriate testing based on changed components

Notes

  • Critical: Uses HEAD~n..HEAD approach to analyze ONLY current branch commits
  • Branch Validation: Verifies number of commits on branch before analysis
  • Feature Branch Scope: Analyzes only commits made specifically on the current feature branch
  • Committed Changes Only: Analyzes committed changes in the branch only, ignores uncommitted files
  • Precise Scope: Prevents inclusion of entire development history in PR description
  • Generated PRs reflect actual feature branch changes, not cumulative project history
  • Breaking changes are flagged based on actual branch commits only
  • Generated PR descriptions are saved to docs/pr-descriptions/<branch-name-with-hyphens>.md for easy copying to GitHub/GitLab

Frequently asked questions

What does the Ring:Generating Pr Descriptions AI skill do?

Generating pull request descriptions from git branch changes with automatic title generation, change-type detection, and smart analysis. Uses branch-only scope to avoid full history analysis. Use when preparing a PR for review. Skip when the PR is a single trivial commit or description already exists.

Why use Ring:Generating Pr Descriptions on TypingMind?

Because you install it once and use it with any model. Ring:Generating Pr Descriptions 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 Ring:Generating Pr Descriptions in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LerianStudio/ring/tree/main/default/skills/generating-pr-descriptions. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ring:Generating Pr Descriptions?

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 Ring:Generating Pr Descriptions?

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

Is the Ring:Generating Pr Descriptions AI skill free?

Yes. It is published on GitHub by LerianStudio under the Apache-2.0 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇