feat: 24 - Add comprehensive evals for tdd-workflow skill#25
Open
miroslavpojer wants to merge 7 commits into
Open
feat: 24 - Add comprehensive evals for tdd-workflow skill#25miroslavpojer wants to merge 7 commits into
miroslavpojer wants to merge 7 commits into
Conversation
Collaborator
|
I have used a TDD skill in the past, that is well rated (144k of stars): https://github.com/mattpocock/skills/tree/main/skills/engineering/tdd. The author (@ |
…and design decisions
Contributor
Author
I did comparison and current version is hybrid solution - the solution introduce vertical principle for test creation. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This PR establishes a complete eval suite for the
tdd-workflowskill, enabling rigorous testing of TDD workflow triggering and body execution across multiple scenarios.What's included:
evals/evals.json: 9 eval cases covering happy-path (implement function, fix bug, new class), regressions (no code before confirmation, no private member access), edge cases (existing SPEC.md), output format validation, negative cases, and paraphrased triggersevals/trigger-eval.json: 15 trigger validation cases (11 should-trigger, 4 should-not-trigger) verifying the skill activates on explicit TDD requests, implicit code-writing intent, and programmatic variations, while correctly ignoring conceptual questions and pure refactorsevals/files/bank-account-spec.md: Fixture SPEC.md used by the private-member-access regression eval to ensure tests interact only with public interfacesTesting approach:
Next steps:
Run eval suite via Copilot CLI (
gh copilot+Use the skill-creator skill to test my skill at skills/tdd-workflow) to measure trigger accuracy and body output quality against baseline.Closes #24