Menu
Modify code for type enforced. Use when asked to change code, refactor, or implement new functionality.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Add or extend a test for type_enforced. Use when asked to write a test, add test coverage, or verify new type_enforced behavior.
Run benchmark tests for the type_enforced package. Use when asked to evaluate performance changes or compare different implementations.
Format type_enforced/ and test/ with autoflake + black. Use when asked to format, lint, clean up style, prettify, or before committing Python changes.
Release checklist for type_enforced (version bump, docs regeneration, build, publish). Owner-only — do not execute; use this when asked to cut a release, bump the version, generate docs, or publish to PyPI, to explain why you're stopping instead.
Run the type_enforced test suite via nox (all supported Python versions) or pytest (local venv). Use when asked to run tests, verify changes, or check CI-equivalent behavior.
| name | changing-code |
| description | Modify code for type enforced. Use when asked to change code, refactor, or implement new functionality. |
If you are asked to change code, refactor, or implement new functionality, use this skill. It is intended for modifying existing code in the type_enforced package, not for writing tests (see add-test) or running tests (see test).
[ ] Identify the relevant file(s) in the type_enforced/ package
[ ] Make all necessary changes
[ ] Ensure that the code adheres to the project's conventions and style guidelines
[ ] Determine if making a new test is necessary and if so, create it using the add-test skill
[ ] Run the test suite using the test skill aiming for a quick first pass to check for obvious issues
[ ] If the tests pass
[ ] Use the benchmark skill to run the benchmark tests and compare the results with the previous benchmarks
[ ] If the benchmarks are worse, consider optimizing the code or reverting changes. If noticibly different, report the issue to the user and provide relevant information.
[ ] Run the linter using the lint skill to ensure code formatting is correct
[ ] Run a complete test suite with test skill to ensure all tests pass across all supported Python versions.
[ ] If the tests pass return to the user with a summary of the changes made and any relevant information about the implementation.
[ ] If the tests fail, diagnose if the issue is with any new tests, with the code changes, or with existing tests.
[ ] If you find yourself stuck in a loop of failing tests, report the issue to the user and provide any relevant information about the failure.
[ ] If the issue is with new tests, move back to the Making the necessary changes step and continue from there.
[ ] If the issue is with code changes, fix them and rerun the test suite.
[ ] If the issue is with existing tests, report it to the user and provide any relevant information about the failure.
