Finds cultural mistakes, stereotypes, romaji and seasonal errors in Japan-themed English copy, with a fix for each. Works on social posts, blogs, product and marketing copy before you publish. Advisory, not a certification.
Built around one rule learned the hard way: never make a git mess worse. Before anything risky it snapshots a backup ref, then guides you through the real recovery toolkit — reflog rescue for "lost" commits, interactive rebase, cherry-pick, safe revert vs hard reset, fixing "committed to the wrong branch," and bisect to find where a bug crept in — flagging at each step which moves are reversible and which are destructive. Safety-first git surgery for when things go sideways.
Analyze failed CI/CD pipelines, identify likely root causes, inspect repository configuration and code context, and produce actionable, validated remediation guidance for GitHub Actions, GitLab CI, Jenkins, and related development pipelines.
Paste a git diff and get a PR description, a changelog entry, and reviewer-risk callouts that name the file, what could break, and what to check. Only flags backed by the diff, and "no elevated-risk patterns found" when there are none. Built for AI-sized PRs.
ファイル・URL・調査メモなど手元の複数の資料から、問いに沿って情報を集めて重複を整理し、出典を付けた一つの Markdown の報告書にまとめます。資料どうしの食い違いは片方を黙って選ばず並べて示し、確かめられない点は「要確認」と書きます。
I've managed thousands of pull requests across open-source and enterprise repos — branching strategies, CI debugging, merge conflicts, and review workflows. This skill encodes that entire pipeline so you can automate your PR lifecycle through natural language, just tell me what you need.
交件前，找出漏檔、錯版與審核回條不一致。需要檔案與已接受的清單；Python 本機執行，不需模型。Catch missing files, wrong versions and mismatched review receipts. Local Python download; accepted manifest required. No model needed.