refactor(skills): trim repeated guidance and tighten evidence routing - #36
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reduce repeated skill instructions while preserving routing and verification boundaries. Ten of the 15 entry points are shorter, reducing their combined whitespace word count by 8.1%; this measures source size, not runtime token savings.
Correct model-catalog discovery for repository and Codex installations, document side-effect-aware Worklog project previews, and require relevant task ownership and log evidence during PR hygiene. PR review now defines safe diff reuse, fresh metadata checks, conditional local setup, and regression replay that retains the new test.
Validation at
76b90f79f07a7d5df13fbfdd14455f4766adf147: full suite passed on macOS Bash 3.2 (158 checks) and Ubuntu Bash 5.2 (157 checks; zsh unavailable), both with zero failures. Optional Node E2E dependencies were absent locally; the GitHub package job passed E2E. Five resolver tests pass; three fail against the old recipe. All five CI jobs passed, including the Docker install matrix.