Quaere Semantic

This skill should be used whenever the user asks to "read", "review", "explore", "understand", "explain", "全文レビュー", "意味を分析", or "コード探索" in depth, or whenever implementation requires understanding existing code's intent before changing it. The skill forces per-symbol meaning analysis — splitting mechanical behavior from domain intent, naming invariants and failure modes, mapping backward and forward slice — so the agent does not paraphrase code as understanding. Trigger when surface-level scanning would produce a wrong edit.

haru0416-dev Updated

File contents

haru0416-dev/quaere commit ec842e5912

Frequently asked questions

npx get-skill add haru0416-dev/quaere-semantic