Use when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency, broken cross-links, stale project state, duplicate / conflicting feedback rules, naming violations, frontmatter gaps, and oversized files. Phase 1 is a read-only scan and report. Phase 2 applies fixes only for findings the user explicitly picks.
安装
npx skills add KerberosClaw/kc_ai_skills --skill memory-lintnpx skills add KerberosClaw/kc_ai_skills --skill memory-lint -a claude-code -gnpx skills add KerberosClaw/kc_ai_skills --skill memory-lint -a codex -ggemini skills install https://github.com/KerberosClaw/kc_ai_skills.git --path memory-lintgh skill install KerberosClaw/kc_ai_skills memory-lintgit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills /tmp/KerberosClaw__kc_ai_skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/KerberosClaw__kc_ai_skills/memory-lint ~/.claude/skills/memory-lint # Claude Code
cp -R /tmp/KerberosClaw__kc_ai_skills/memory-lint ~/.agents/skills/memory-lint # Codex, Cursor, Gemini CLI, Copilot, OpenCode