Use when a PR is broken and needs to be fixed — CI failures, merge conflicts, BEHIND base branch, or failing tests.
From menpx claudepluginhub baleen37/bstack --plugin bstackThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Diagnose and fix a broken PR.
# Single call — all needed fields
gh pr view --json state,mergeable,mergeStateStatus
MERGED → done, nothing to fixCLOSED → reopen if neededOPEN + UNKNOWN → CI settling, re-check in a few secondsCI failure — if wait-for-merge.sh printed a run-id, use it directly:
gh run view <run-id> --log-failed 2>&1 | grep -A3 "not ok\|Error\|FAILED" | head -40
# fix, commit, push
gh pr checks --watch > /dev/null 2>&1; echo "CI: $?"
Failing tests — run locally first, never fix blind:
<test command>
# fix, commit, push
Conflict (DIRTY)
git fetch origin && git merge origin/<base>
# resolve, commit, push
BEHIND base
git fetch origin && git merge origin/<base> && git push
gh pr checks --watch exits 0 (suppress output, check exit code only).