القائمة
Ensure the current branch is cleanly rebased onto the remote base branch so that `origin/{base}..HEAD` only shows this branch's commits.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Fully autonomous PR polish loop. Runs N rounds of local bramble review (codex + cursor, optionally + gemini), folds in any existing PR comments and CI failures as round-1 input, fixes findings locally, pushes once at the end.
Compare bramble code-review output across reviewer configs (cursor with composer-2, codex with gpt-5.4-mini, gemini with gemini-3.1-flash-lite-preview). Runs each config three times against the same branch — turn 1 fresh, turn 2 resumed with default follow-up prompt, turn 3 resumed with fresh prompt — to also characterize backend resume behavior, then compares findings side-by-side and logs results.
Build and use a ground-truth eval dataset for bramble code-review. Two modes. COLLECTION scans past /pr-polish'd PRs and judges each into a frozen ground truth — multiple rounds of bramble re-review + an independent judge sub-agent per round, until the judge's full-diff bug census saturates. REPLAY runs a reviewer-under-test and scores it mechanically against that frozen ground truth — precision/recall/F1, no sub-agents, cheap and repeatable.
One-shot review of an external GitHub PR. Checks out the PR into an isolated worktree (or temp clone), runs `bramble code-review` against the diff, and produces a calibrated verdict — APPROVE unless there is a blocking correctness issue, with optional improvements listed separately. Read-only on the remote PR, never pushes. User-invoked only via `/external-pr-review`.
Iterative review of a markdown design document. Reads the doc, proposes a tailored grilling rubric, runs N rounds of codex+cursor (optionally +gemini) against the doc with that rubric, edits between rounds, commits locally each round. Never pushes.
"Fully autonomous eval loop for the delegator agent. Runs real-mode tests, analyzes output for usability gaps, spawns fix agents, rebuilds, and re-tests until clean.
| name | git:sync-base |
| description | Ensure the current branch is cleanly rebased onto the remote base branch so that `origin/{base}..HEAD` only shows this branch's commits. |
| argument-hint | |
| disable-model-invocation | false |
python3 .claude/skills/git:sync-base/git-sync.py --verbose
Override base branch with --base <branch> if needed. Auto-detects via origin/HEAD. Pass --no-push to skip the post-rebase force-push. Pass --backup to create a timestamped backup branch before rebasing.
The script:
$GIT_DIR/sync-base.lock) so two runs in the same worktree can't race. Does NOT block other worktrees sharing the bare repo.origin/<base> and origin/<current-branch> (narrow refspec, not git fetch origin).origin/<base> to a SHA once and rebases onto that SHA. Other worktrees advancing origin/<base> mid-run cannot affect us. Includes a cherry-pick fallback for branches containing duplicate copies of base commits.--force-with-lease=refs/heads/<branch>:<fetched-remote-sha> plus --force-if-includes) using the SHA fetched in step 3.The rebase is paused and the output includes a conflict report listing each file and its type (deleted_by_us, deleted_by_them, both_modified, both_added, both_deleted).
Resolve each conflicted file based on its type:
git rm <file> or git checkout --theirs <file> && git add <file>)<<<<<<< markers, git add <file>git add <file>Then continue:
python3 .claude/skills/git:sync-base/git-sync.py --verbose --continue
Repeat until the script exits 0. --continue uses the same pinned target SHA saved at the start of the original run, and will also force-push on success (unless --no-push is passed).
A non-conflict failure. Common causes and fixes:
$(git rev-parse --git-dir)/sync-base.lock.git log HEAD..origin/<branch> before overriding. The rebase itself succeeded; only the push step failed, so you can re-run (the rebase will be a no-op and the push will retry with a fresh lease).