Skip to content

opensite-ai/opensite-skills / large-scale-refactor

large-scale-refactor

Unverified

Guardrails, protocols, and operating constraints for large-scale, long-running, or parallelized AI coding tasks — migrations, codebase-wide refactors, framework upgrades, and any task touching 50+ files. Prevents scope creep, context drift, silent compounding errors, and emergent behavior outside the defined task boundary. Use when refactoring across files, migrating frameworks, upgrading dependencies, replacing or renaming patterns throughout a codebase, or any task touching 50+ files.

CONTRIBUTING.md

View on GitHub
# Contributing to large-scale-refactor

Thanks for your interest in contributing to the `large-scale-refactor` skill.

## Getting Started

1. Fork the repository
2. Clone your fork and create a feature branch
3. Make your changes
4. Run the test suite (see below)
5. Submit a pull request

## Running Tests

The skill's verification scripts have a pytest test suite. No external dependencies
are required beyond Python 3.8+ and pytest.

```bash
# Install pytest (if not already available)
pip install pytest

# Run the test suite
python -m pytest large-scale-refactor/scripts/test_verify_scope.py -v
```

## What to Contribute

- Bug fixes in the verification scripts (`verify_scope.py`, `generate_allowlist.py`)
- New test cases for edge cases in pattern matching
- Improvements to templates (`templates/`)
- Platform-specific notes for additional AI coding agents
- Documentation clarifications

## PR Conventions

- One logical change per PR
- Include a test case if your change affects `verify_scope.py` or `generate_allowlist.py`
- Update `SKILL.md` if your change affects guardrail language or protocols
- Keep commit messages descriptive: `fix(verify_scope): handle edge case in directory prefix matching`

## Code Style

- Python scripts use stdlib only (no external dependencies)
- Follow existing patterns in the codebase
- Type hints are encouraged but not strictly required

## License

By contributing, you agree that your contributions will be licensed under the MIT License.
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall