Agent skill

Code Change Summarizer

by ArabelaTso in ArabelaTso/Skills-4-SE

Generates clear and structured pull request descriptions from code changes.

Apache-2.0Auto-check passedDevelopment

Install Code Change Summarizer

skills CLI
$ npx skills add ArabelaTso/Skills-4-SE --skill code-change-summarizer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ArabelaTso/Skills-4-SE code-change-summarizer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/code-change-summarizer .claude/skills/code-change-summarizer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-change-summarizer
GitHub stars
253
Token cost
~3.6k tokens
SKILL.md length
628 words
Files
2 (incl. references)
Skills in repo
150
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generates clear and structured pull request descriptions from code changes.

  • Works in 10 steps: Analyze Code Changes → Create Initial Summary → Document Changes → …
  • Claude needs to:
  • SKILL.md covers Workflow, Output Format, Best Practices and Common Scenarios, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Change Summarizer is an agent skill from ArabelaTso/Skills-4-SE. Generates clear and structured pull request descriptions from code changes. Use when Claude needs to: (1) Create PR descriptions from git diffs or code changes, (2) Summarize what changed and why, (3) Document breaking changes with migration guides, (4) Add technical details and design decisions, (5) Provide testing instructions, (6) Enhance descriptions with security, performance, and architecture notes, (7) Document dependency changes. Takes code changes as input, outputs comprehensive PR description in Markdown.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/pr-templates.md`).

It sits in Development, covering Pull requests, Code migrations and Architecture decision records. It works with Git. The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.

When your agent uses it

  • Claude needs to:
  • Create PR descriptions from git diffs
  • Summarize what changed and why
  • Document breaking changes with migration guides

Example prompts

  • “Use the code-change-summarizer skill to generate clear and structured pull request descriptions from code changes”
  • “/code-change-summarizer”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Analyze Code Changes
  2. Create Initial Summary
  3. Document Changes
  4. Identify Breaking Changes
  5. Document Dependencies
  6. Provide Testing Instructions
  7. Enhance with Context
  8. Add Documentation Notes
  9. Link Related Issues
  10. Review and Refine

What it can do on your machine

Read from SKILL.md and the folder at commit 4f38503. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, language and javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Code Change Summarizer loads about 3.6k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 136 tokens; SKILL.md has 628 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 628 words, ~3,625 tokens.

Download SKILL.mdSave it as .claude/skills/code-change-summarizer/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
code-change-summarizer
description
Generates clear and structured pull request descriptions from code changes. Use when Claude needs to: (1) Create PR descriptions from git diffs or code changes, (2) Summarize what changed and why, (3) Document breaking changes with migration guides, (4) Add technical details and design decisions, (5) Provide testing instructions, (6) Enhance descriptions with security, performance, and architecture notes, (7) Document dependency changes. Takes code changes as input, outputs comprehensive PR description in Markdown.

Code Change Summarizer

Generate clear, structured pull request descriptions from code changes.

Workflow

1. Analyze Code Changes

Gather code changes:

  • Git diff output
  • Modified files list
  • Commit messages
  • Related issue numbers

Understand the changes:

  • Read through all modified files
  • Identify what changed (added/modified/removed/fixed)
  • Understand the purpose of changes
  • Note any patterns or themes

Categorize changes:

  • Feature additions: New functionality
  • Bug fixes: Issue resolutions
  • Refactoring: Code improvements without behavior changes
  • Documentation: Doc updates
  • Tests: Test additions or modifications
  • Dependencies: Package updates
  • Configuration: Config or build changes
2. Create Initial Summary

Write a clear title:

Format: [Type] Brief description (max 72 characters)

Types:

  • feat: New feature
  • fix: Bug fix
  • refactor: Code refactoring
  • docs: Documentation
  • test: Tests
  • chore: Maintenance
  • perf: Performance
  • style: Code style
  • ci: CI/CD
  • build: Build system

Examples:

  • feat: Add user authentication with OAuth2
  • fix: Resolve memory leak in data processor
  • refactor: Simplify error handling logic

Write summary paragraph:

  • 2-3 sentences
  • Explain what and why
  • Use active voice
  • Be concise and clear

Example:

This PR adds OAuth2 authentication to the user login system. The change
improves security by using industry-standard authentication and enables
single sign-on with external providers.
3. Document Changes

List changes by category:

Added:

  • New features or functionality
  • New files or components
  • New API endpoints

Modified:

  • Changed behavior or implementation
  • Updated configuration
  • Refactored code

Removed:

  • Deprecated features
  • Deleted files
  • Removed dependencies

Fixed:

  • Bug fixes
  • Issue resolutions
  • Error corrections

Example:

markdown
## Changes

### Added
- OAuth2 authentication flow
- User session management
- Login/logout endpoints

### Modified
- User model to include OAuth tokens
- Authentication middleware
- Database schema

### Fixed
- Session timeout not working correctly
- Memory leak in token refresh
4. Identify Breaking Changes

Check for breaking changes:

  • API signature changes
  • Removed functionality
  • Changed behavior
  • Configuration changes
  • Database schema changes
  • Dependency updates with breaking changes

Document each breaking change:

Format:

markdown
## Breaking Changes

⚠️ **[Breaking change description]**

**Impact:** [Who/what is affected]

**Migration Guide:**
1. [Step 1]
2. [Step 2]

**Before:**
```[language]
// Old code

After:

language
// New code

**Example:**
```markdown
## Breaking Changes

⚠️ **Authentication endpoint signature changed**

**Impact:** All API clients must update their authentication calls.

**Migration Guide:**
1. Update authentication endpoint from `/auth/login` to `/auth/oauth/login`
2. Include `provider` parameter in request body
3. Handle new response format with OAuth tokens

**Before:**
```javascript
POST /auth/login
{ "username": "user", "password": "pass" }

After:

javascript
POST /auth/oauth/login
{ "username": "user", "password": "pass", "provider": "google" }

### 5. Add Technical Details

**Explain implementation approach:**
- High-level technical approach
- Key algorithms or patterns used
- Important implementation details

**Document design decisions:**
- Why this approach was chosen
- Alternatives considered
- Trade-offs made

**Note architecture changes:**
- New components or modules
- Changed relationships
- Updated data flow

**Example:**
```markdown
## Technical Details

### Implementation Approach
Implemented OAuth2 using the Authorization Code flow with PKCE for enhanced
security. The authentication flow is handled by a new `AuthService` that
manages token exchange and refresh.

### Key Design Decisions
- **OAuth2 over SAML:** Chose OAuth2 for better mobile support and simpler
  implementation
- **PKCE extension:** Added PKCE to protect against authorization code
  interception attacks
- **Token storage:** Store refresh tokens in secure HTTP-only cookies

### Architecture Changes
- Added new `AuthService` layer between controllers and OAuth provider
- Introduced `TokenManager` for token lifecycle management
- Updated database schema to store OAuth provider information
6. Document Dependencies

List dependency changes:

Added dependencies:

  • Package name and version
  • Why it was added
  • What it's used for

Updated dependencies:

  • Old version → New version
  • Why it was updated
  • Any breaking changes

Removed dependencies:

  • Package name
  • Why it was removed
  • What replaced it (if anything)

Example:

markdown
## Dependencies

### Added
- `passport@0.6.0` - OAuth2 authentication library
- `passport-google-oauth20@2.0.0` - Google OAuth2 strategy

### Updated
- `express@4.17.1` → `express@4.18.2` - Security patches and bug fixes
- `jsonwebtoken@8.5.1` → `jsonwebtoken@9.0.0` - Updated for Node 18 support

### Removed
- `bcrypt@5.0.1` - Replaced by OAuth2, no longer needed for password hashing
7. Provide Testing Instructions

Write step-by-step testing guide:

Format:

markdown
## Testing

### How to Test
1. [Setup step]
2. [Action to perform]
3. [Expected result]
4. [Edge case to verify]

### Test Coverage
- Added [X] unit tests
- Added [Y] integration tests
- Current coverage: [Z]%

### Manual Testing Checklist
- [ ] Test scenario 1
- [ ] Test scenario 2
- [ ] Test edge case 1

Example:

markdown
## Testing

### How to Test
1. Start the application: `npm start`
2. Navigate to `/login`
3. Click "Sign in with Google"
4. Complete OAuth flow in popup
5. Verify you're redirected back and logged in
6. Check that session persists after page refresh

### Test Coverage
- Added 15 unit tests for AuthService
- Added 8 integration tests for OAuth flow
- Current coverage: 87% (up from 82%)

### Manual Testing Checklist
- [ ] Google OAuth login works
- [ ] Session persists across page refreshes
- [ ] Logout clears session correctly
- [ ] Token refresh works when token expires
- [ ] Error handling for failed OAuth
8. Enhance with Context

Add security considerations:

  • Security improvements made
  • Security implications
  • Vulnerabilities addressed
  • Security review status

Add performance impact:

  • Expected performance changes
  • Benchmark results
  • Optimization details
  • Resource usage changes

Add architecture notes:

  • Architectural patterns used
  • System design changes
  • Integration points
  • Scalability considerations

Example:

markdown
## Security Considerations

### Improvements
- ✅ Implemented PKCE to prevent authorization code interception
- ✅ Store refresh tokens in HTTP-only cookies to prevent XSS
- ✅ Added rate limiting on authentication endpoints
- ✅ Validate OAuth state parameter to prevent CSRF

### Security Review
- [ ] Security team review pending
- [ ] Penetration testing scheduled

## Performance Impact

### Expected Changes
- Login time: ~500ms (OAuth redirect adds latency)
- Token validation: <10ms (cached in memory)
- Database queries: +2 per login (OAuth token storage)

### Optimizations
- Implemented token caching to reduce database hits
- Added connection pooling for OAuth provider requests

## Architecture Notes

### Patterns Used
- **Strategy Pattern:** Different OAuth providers (Google, GitHub, etc.)
- **Factory Pattern:** Token creation and validation
- **Middleware Pattern:** Authentication checks

### Integration Points
- Integrates with existing User model
- Hooks into session management middleware
- Compatible with existing authorization system
9. Add Documentation Notes

List documentation updates:

markdown
## Documentation

- [ ] Updated README with OAuth setup instructions
- [ ] Added API documentation for new endpoints
- [ ] Updated environment variables guide
- [ ] Added OAuth provider configuration guide
- [ ] Updated changelog

Reference related issues:

markdown
## Related Issues

Closes #123
Fixes #456
Related to #789
Show full SKILL.md (276 more words)Show less
11. Review and Refine

Review the PR description:

  • Is the summary clear?
  • Are all changes documented?
  • Are breaking changes highlighted?
  • Are testing instructions complete?
  • Is context sufficient?

Refine for clarity:

  • Remove unnecessary details
  • Add missing information
  • Improve wording
  • Fix formatting

Verify completeness:

  • All sections filled out
  • No placeholders left
  • Links work
  • Code examples correct

Output Format

Generate a complete PR description in Markdown:

markdown
# [Type] Brief description

## Summary
[2-3 sentence overview]

## Changes

### Added
- [Item 1]
- [Item 2]

### Modified
- [Item 1]

### Fixed
- [Item 1]

## Breaking Changes
[If any, with migration guide]

## Technical Details

### Implementation Approach
[Explanation]

### Key Design Decisions
- [Decision 1]
- [Decision 2]

### Architecture Changes
[Description]

## Dependencies

### Added
- [Package] - [Reason]

### Updated
- [Package] - [Reason]

## Testing

### How to Test
1. [Step 1]
2. [Step 2]

### Test Coverage
- [Details]

### Manual Testing Checklist
- [ ] [Item 1]
- [ ] [Item 2]

## Security Considerations
[Details]

## Performance Impact
[Details]

## Architecture Notes
[Details]

## Documentation
- [ ] [Item 1]
- [ ] [Item 2]

## Related Issues
Closes #[number]

## Checklist
- [ ] Code follows style guidelines
- [ ] Self-review completed
- [ ] Tests added/updated
- [ ] Documentation updated
- [ ] All tests passing

See pr-templates.md for detailed templates.

Best Practices

Summary
  • Keep it concise (2-3 sentences)
  • Explain what and why
  • Use active voice
  • Be specific
Changes
  • Group by type (Added/Modified/Removed/Fixed)
  • Be specific but concise
  • Use bullet points
  • Link to related issues
Breaking Changes
  • Clearly mark with ⚠️
  • Provide migration guide
  • Show before/after examples
  • Explain impact
Technical Details
  • Explain approach
  • Document decisions
  • Note architecture changes
  • Keep it relevant
Testing
  • Provide clear instructions
  • Include expected results
  • List edge cases
  • Note coverage changes
Context
  • Add security notes
  • Note performance impact
  • Explain architecture changes
  • Document dependencies

Common Scenarios

Scenario 1: Feature Addition

Input: Code adding user authentication

Output:

markdown
# feat: Add user authentication with OAuth2

## Summary
This PR implements OAuth2 authentication for user login. Users can now
sign in using their Google or GitHub accounts, improving security and
user experience.

## Changes

### Added
- OAuth2 authentication flow
- Google and GitHub OAuth providers
- User session management
- Login/logout endpoints

### Modified
- User model to include OAuth tokens
- Database schema for OAuth data

## Testing

### How to Test
1. Start app: `npm start`
2. Navigate to `/login`
3. Click "Sign in with Google"
4. Complete OAuth flow
5. Verify successful login

### Test Coverage
- Added 15 unit tests
- Added 8 integration tests
- Coverage: 87%
Scenario 2: Bug Fix

Input: Code fixing memory leak

Output:

markdown
# fix: Resolve memory leak in data processor

## Summary
This PR fixes a memory leak in the data processor that was causing
memory usage to grow unbounded during long-running operations.

## Changes

### Fixed
- Memory leak in DataProcessor.process()
- Improper cleanup of event listeners
- Unclosed database connections

## Technical Details

### Root Cause
Event listeners were not being removed after processing completed,
causing references to processed data to remain in memory.

### Solution
- Added proper cleanup in finally block
- Implemented connection pooling
- Added memory monitoring

## Testing

### How to Test
1. Run long-running process: `npm run process-large-dataset`
2. Monitor memory usage
3. Verify memory stays stable

Fixes #456
Scenario 3: Refactoring

Input: Code refactoring error handling

Output:

markdown
# refactor: Simplify error handling logic

## Summary
This PR refactors error handling across the application to use a
consistent pattern, improving maintainability and reducing code
duplication.

## Changes

### Modified
- Centralized error handling in ErrorHandler class
- Updated all controllers to use new error handling
- Simplified error response format

### Removed
- Duplicate error handling code in controllers
- Inconsistent error response formats

## Technical Details

### Implementation Approach
Introduced a centralized ErrorHandler class that provides consistent
error handling and response formatting across all endpoints.

### Benefits
- Reduced code duplication by 40%
- Consistent error responses
- Easier to maintain and extend

## Testing

### Behavior Verification
All existing tests pass, confirming no behavior changes.

### Test Coverage
- Updated 25 existing tests
- Coverage maintained at 85%

Troubleshooting

Issue: Not enough context in code changes

Solution:

  • Ask for commit messages
  • Request related issue descriptions
  • Check for comments in code
  • Ask user for context
Issue: Unclear what changed

Solution:

  • Review git diff carefully
  • Look for patterns in changes
  • Check file names for clues
  • Ask user for clarification
Issue: Can't determine breaking changes

Solution:

  • Look for API signature changes
  • Check for removed functionality
  • Review dependency updates
  • Ask user if unsure
Issue: Missing testing information

Solution:

  • Suggest basic testing steps
  • Recommend test coverage goals
  • Provide testing checklist template
  • Ask user for specific test scenarios

© ArabelaTso, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/code-change-summarizer of ArabelaTso/Skills-4-SE.

  • SKILL.md
  • references/pr-templates.md

Open the folder on GitHubat commit 4f38503

Compare with similar skills

Code Change Summarizer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Change Summarizer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Change Summarizer this skillArabelaTso/Skills-4-SE253—~3.6kAutomated safety check: PassApache-2.0
Review GitHub PRNVIDIA/OpenShell15k—~1.7kAutomated safety check: PassApache-2.0
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT

Similar skills

  • Review GitHub PR

    NVIDIA/OpenShell

    Official

    Review a GitHub pull request by summarizing its diff and key design decisions.

    15k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    55k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed

More from ArabelaTso/Skills-4-SE

All 150 skills in this repo
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Metamorphic Test Generator

    ArabelaTso/Skills-4-SE

    Generate test cases using metamorphic testing by applying transformations based on metamorphic properties.

    253 GitHub stars~798 tokensUpdated 1 mo ago
    Auto-check passed
  • Reproduction Trace Instrumenter

    ArabelaTso/Skills-4-SE

    Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.

    253 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Spring Mvc To Boot Migrator

    ArabelaTso/Skills-4-SE

    Automatically migrate Spring MVC applications to Spring Boot.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • State Snapshot Instrumenter

    ArabelaTso/Skills-4-SE

    Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Code Change Summarizer

What does Code Change Summarizer do?

Generates clear and structured pull request descriptions from code changes. Code Change Summarizer is an agent skill from ArabelaTso/Skills-4-SE. Generates clear and structured pull request descriptions from code changes.

When should I use Code Change Summarizer?

Code Change Summarizer fits situations like: Claude needs to:; create PR descriptions from git diffs; summarize what changed and why; document breaking changes with migration guides.

How do I install Code Change Summarizer in Claude Code?

Run `npx skills add ArabelaTso/Skills-4-SE --skill code-change-summarizer -a claude-code`. Or copy the skill folder (skills/code-change-summarizer in ArabelaTso/Skills-4-SE) into .claude/skills/code-change-summarizer in your project. Claude Code loads it when a task matches its description.

How do I install Code Change Summarizer in Codex?

Run `npx skills add ArabelaTso/Skills-4-SE --skill code-change-summarizer -a codex`. Or copy the skill folder (skills/code-change-summarizer in ArabelaTso/Skills-4-SE) into .agents/skills/code-change-summarizer in your project. Codex loads it when a task matches its description.

Can I use Code Change Summarizer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ArabelaTso/Skills-4-SE --skill code-change-summarizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-change-summarizer, .gemini/skills/code-change-summarizer, .github/skills/code-change-summarizer and .opencode/skills/code-change-summarizer in your project.

What does Code Change Summarizer need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Change Summarizer is instructions for the agent only.

Does Code Change Summarizer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Code Change Summarizer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Change Summarizer use?

Code Change Summarizer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Change Summarizer use?

About 3.6k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Code Change Summarizer?

Skills that share tags, products or a category with Code Change Summarizer: Review GitHub PR (NVIDIA/OpenShell, 15k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars) and PR Design Doc (OpenHands/OpenHands, 90k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Change Summarizer?

ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 150 skills in this directory. The repository was last updated on August 21, 2026.

Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.