fix(evals): correct pr-management-code-review fixtures#667
Merged
Conversation
Collapse "What's been built" to one line per item; all 22 planned work items preserved verbatim; redundant shipped-state notes trimmed. Generated-by: Claude (Opus 4.7)
Populate four empty stub directories in tools/skill-evals/evals/pr-management-code-review/ with fixture cases: - selector-resolution (4 cases): parser tests covering single-pr, composed area+collab+max flags, default my-reviews, and requested-only with dry-run and inline:off - review-risk-classify (4 cases): per-finding severity tests covering blocking (GPL dep), major (missing tests), minor (AI disclosure absent), and none (clean code-quality change) - injection-guard (4 cases): prompt-injection resistance across PR-body, code-comment, commit-message, and a clean-PR control - review-handoff (3 cases): confirmation-gate tests for confirm-post, dry-run-skip, and wording-edit re-draft Clear the "lacks a dedicated eval suite" Known-gap from specs/pr-management-family.md now that acceptance criterion 6 is met. Update pr-management-code-review/README.md from 79 to 112 total cases and add the four new suites to the table; sync the skill-evals top-level README. Generated-by: Claude (Opus 4.7)
- injection-guard: grade excerpt as prose via grading-schema.json; fix case-1 gold to name both invoked authorities (security-team + maintainer) - selector-resolution: state area_label carries the area: prefix so the exact-match is deterministic - step-2.5-slop-detection: drop S2 from case-6 gold (injection body is not template-only; outcome stays early-exit)
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
2 participants
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.
Summary
case-1 gold to name both invoked authorities (security-team + maintainer)
exact-match is deterministic
template-only; outcome stays early-exit)
Type of change
.claude/skills/<name>/) — eval fixtures updated belowtools/<system>/*.md)tools/*/withpyproject.toml)docs/,README.md,CONTRIBUTING.md)projects/_template/)prek, workflows, validators)Test plan
prek run --all-filespassesuv run pytest/ruff check/mypypasses(
PYTHONPATH=tools/skill-evals/src python3 -m skill_evals.runner tools/skill-evals/evals/<skill>/)(a regression test for the bug fixed / the behaviour added — see CONTRIBUTING.md)