中文记忆优化 (Chinese Memory Optimizer)

OpenClaw + Ollama 中文记忆系统优化。诊断 FTS5 unicode61 中文分词 bug，优化搜索参数，自动维护记忆文件。命中率从 55% 提升到 100%。

This skill appears to do what it claims: local diagnostics and maintenance of OpenClaw memory for Chinese text. Before running: 1) Verify script paths (SKILL.md references SKILL_DIR/scripts/ but files appear at repo root) and run in a safe test environment first. 2) Back up your memory folder and the SQLite DB (~/.openclaw/memory/main.sqlite) before executing non-dry-run operations. 3) Use --dry-run options (add-tags.py has --dry-run; compress-logs.py supports --dry-run; cleanup.sh defaults to dry-run) to see intended changes. 4) Inspect the JSON config patch the skill recommends applying — applying gateway/openclaw config changes affects agent behavior globally. 5) Be cautious with cleanup.sh: it will delete files if run with execution enabled and confirmed. The scripts do not perform network calls or request credentials, but they do read and modify local files, so treat them as privileged local maintenance tools.

Type: OpenClaw Skill Name: memory-cn Version: 1.0.0 The skill bundle is designed to optimize Chinese language memory search in OpenClaw by addressing FTS5 tokenization issues and managing log file sizes. It includes scripts for database diagnosis (diagnose.sh), automated metadata tagging (add-tags.py), log compression with backups (compress-logs.py), and cleanup of redundant session data (cleanup.sh). While the scripts perform file modifications and deletions, these actions are strictly scoped to markdown files within the memory directory and are aligned with the stated purpose of system maintenance, including safeguards like dry-run modes and file backups.