Draft
Conversation
|
- Require reading all src/transport TypeScript before code_review approval in full mode when transport is in scope; check nested message access and unsafe indexing. - When PR touches test/unit, apply full unit rubric (completeness), not approval based only on the edited test file. - Gitignore and untrack ea-pr-reviewer-workspace (local skill-eval artifacts). Made-with: Cursor
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request adds a comprehensive benchmark and evaluation suite for the first iteration of the
ea-pr-reviewerskill, focused on thepackages/sources/tiingoadapter. It introduces structured evaluation artifacts, detailed grading and rationale for both "with skill" and "without skill" review modes, and provides feedback on the skill's scoping and output format. The changes are organized into benchmark documentation, evaluation metadata, review outputs, and grading results.Benchmark documentation and evaluation setup:
.claude/skills/ea-pr-reviewer-workspace/iteration-1/benchmark-summary.mdsummarizing manual aggregate results, pass rates, and critique of the skill's scoping logic and evaluation artifacts.eval_metadata.jsonfiles. [1] [2]Review outputs and structured results:
response.mdfiles. [1] [2] [3]transcript.md.Grading and evaluation artifacts:
grading.jsonfiles for both skill and baseline runs. [1] [2] [3]These changes establish a reproducible benchmark for PR review skill evaluation, clarify scoping rules, and highlight areas for skill improvement, especially around integration test handling and structured output.
References: [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]