Repository navigation
fix(skills): bring prepare-pr SKILL.md back under its byte ceiling - #16720
bolichen97 wants to merge 1 commit into
Conversation
First Principles Review (Opus 5.5) — ✅ PASSPremise-level review of First-Principles-Verdict: PASS Nothing to check. What this change shipsInventory (2 items) — 2 justifiedIntent: unblock every PR by bringing
[FIRST-PRINCIPLES-REVIEWED] 44a29d6 Description read[DESCRIPTION-READ] 63232b185f7a7e9fb98eec0916e6f6dc210ff1c6db659dd21ca4c8c04864d358 That sha256 names the PR description this verdict read. Recompute it with |
Design Review (Opus 5.5) — ✅ PASSDesign-level review of Design-Verdict: PASS Check the cross-PR race: no merge-time gate stops two green PRs from growing this file past its ceiling together, which caused this break. [DESIGN-REVIEWED] 44a29d6 Description read[DESCRIPTION-READ] 3fa214aeb15e5570926d77f1aebea717ba5f60c5e0f58d5a26c1d85dbbbc7ff5 That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with |
Opus 5.5 Review — ✅ no blocking findingsReviewed Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
|
Closing as a duplicate of #16719, which fixes the same byte-ceiling red and is being merged. |
GPT 6.1 Review — ✅ no blocking findingsGPT 6.1 completed its review of This comment is updated in place on each push. Review detailsNo findings. False positive or not applicable? A repository writer can comment: |
Problem / Motivation
Goal: main's
prepare-pr/SKILL.mdfits its 68 000-byte ceiling again, sotest_review_repair_routing_skill.py::test_slim_skills_do_not_regrow_duplicate_guidance_or_wire_model_ids[prepare-pr-68000]stops failing on every PR.#16196 and #16634 each grew the file and each was green alone; merged together the file is 68 077 bytes, 77 over. Backend Tests shard 3 is red on Linux and Windows for every PR built on current main (e.g. #16503, #16697).
Why it matters
Every open PR inherits the red.
Not a goal
What changed (motivation -> approach -> change)
— see above,— see the profile section) after(single_commit only): the profile section already states that rule once.lacks exactly one tier:T1..tier:T4 label.Backwards compatibility
Compatible: skill text only.
Tests
Manual verification
N/A - text-only change covered by the skill tests.
Related Issues
Part of #16506
Checklist