ワンクリックで
recover
Scan for orphaned worktrees and stale branches after crashes or abandoned sessions. Offers safe cleanup options.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Scan for orphaned worktrees and stale branches after crashes or abandoned sessions. Offers safe cleanup options.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | recover |
| description | Scan for orphaned worktrees and stale branches after crashes or abandoned sessions. Offers safe cleanup options. |
Scan for orphaned worktrees, stale branches, and partial work left behind by crashed or abandoned Claude Code sessions. Read-only by default — reports findings and waits for approval before cleanup.
Invocation: deliberately model-invocable — scanning is read-only. Every cleanup action is gated on explicit user approval.
Don't assume main. Resolve it once and use it everywhere below:
DEFAULT=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's|^origin/||')
DEFAULT=${DEFAULT:-$(git remote show origin 2>/dev/null | sed -n 's/.*HEAD branch: //p')}
DEFAULT=${DEFAULT:-main} # no remote at all — fall back and note it in the report
git worktree list --porcelain
Identify:
.git metadata modified in the last hours — treat as possibly live. git worktree list cannot tell whether a session is actually running; without a lock/heartbeat file or process evidence, classify as unknown activity and never as orphaned.For each orphaned worktree:
git -C <worktree-path> status --short
git -C <worktree-path> branch --show-current
git -C <worktree-path> log --oneline -3
git log "$DEFAULT"..<branch-name> --oneline
Classify each as:
git branch --no-merged "$DEFAULT"
git remote prune origin --dry-run
git for-each-ref --sort=-committerdate --format='%(refname:short) %(committerdate:relative) %(subject)' refs/heads/
Classify:
git worktree prune --dry-run
RECOVER — [DATE]
WORKTREES:
- Active: [N]
- Orphaned: [N]
- [path] — [status] — [branch] — [last commit]
- Stale entries: [N]
BRANCHES:
- Merged (safe to delete): [list]
- Stale (>7 days, not merged): [list]
- Active: [list]
PROPOSED ACTIONS:
1. [action] — [target] — [reason]
OVERALL: [CLEAN / N items need attention]
Only proceed when explicitly approved. Options:
git worktree remove <path>git merge <branch> --no-ffgit cherry-pick <hash>git branch -d <branch>git branch -D <branch>git worktree prunegit remote prune originGenerate a new Claude Code skill from a plain-language description — decides invocation control (disable-model-invocation vs user-invocable), arguments (argument-hint, $ARGUMENTS), and context cost, then scaffolds and tests it.
Audit an LLM evaluation or benchmark repo for integrity and credibility practices. Use when asked to "audit my benchmark," "is my eval trustworthy," "check my leaderboard for contamination," "review this benchmark's methodology," or "what would a reviewer attack in my eval." Greps the target repo for evidence across seven dimensions (pre-registration, contamination, holdout hygiene, judge validity, statistical honesty, reproducibility, leaderboard exclusions) and emits a scored report with file:line evidence, severity, and concrete fixes.
Tripwire check for multi-session drift. Scans state files, recent commits, and file conflicts caused by parallel Claude Code sessions.
Structured session lifecycle for Claude Code — start, checkpoint, end, and daily heartbeat commands that maintain project state across conversations.
Single-source-of-truth drift auditor for documentation-heavy repos. Use when asked to "check for drift," "find copies of this number," "audit the docs for stale facts," or "set up an SSOT manifest." Finds facts hand-copied across files, builds a manifest of canonical locations, and verifies every copy still matches.
Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review