abczsl520/memory-cn/SKILL.md
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%。
npx skillsauth add openclaw/skills memory-cnInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
当用户请求诊断或优化记忆系统时,按以下步骤执行:
运行诊断脚本检测问题:
bash SKILL_DIR/scripts/diagnose.sh
报告包括:
如果诊断发现问题,应用优化配置:
{
"agents": {
"defaults": {
"memorySearch": {
"chunking": { "tokens": 250, "overlap": 60 },
"query": {
"maxResults": 10,
"minScore": 0.15,
"hybrid": {
"enabled": true,
"vectorWeight": 0.75,
"textWeight": 0.25,
"candidateMultiplier": 8,
"mmr": { "enabled": true, "lambda": 0.7 },
"temporalDecay": { "enabled": true, "halfLifeDays": 90 }
}
}
}
}
}
}
使用 gateway config.patch 应用。
让新日志自动加 tags + 中文分词:
{
"agents": {
"defaults": {
"compaction": {
"memoryFlush": {
"prompt": "将对话内容整理为结构化日志,写入 memory/YYYY-MM-DD.md。\n\n格式要求:\n1. 文件第一行必须是 <!-- tags: 关键词1, 关键词2, ... --> 标签行\n2. 中文关键词之间加空格分隔\n3. 只保留有价值的信息\n4. 控制在 5KB 以内"
}
}
}
}
}
对 memory/projects/*.md 中缺少 tags 的文件,根据内容自动添加 <!-- tags: ... --> 行。
python3 SKILL_DIR/scripts/add-tags.py /path/to/memory/projects/
压缩 >8KB 的旧日志到 <5KB,原文备份到 archive/:
python3 SKILL_DIR/scripts/compress-logs.py /path/to/memory/ --max-kb 5
openclaw memory index --force
建议每周日凌晨自动执行压缩+清理+补标签+重建索引。
unicode61 分词器把连续 CJK 字符当作一个 tokentools
Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.
development
Web scraping platform — Twitter/X data, Vinted marketplace, and general web scraping API
development
SlowMist AI Agent Security Review — comprehensive security framework for skills, repositories, URLs, on-chain addresses, and products (Claude Code version)
data-ai
去除中文文本中的 AI 写作痕迹,使其读起来自然。基于维基百科 AI 写作特征指南,检测 24 种 AI 模式。触发词:humanizer-cn、去除 AI 痕迹、去除 AI 写作痕迹、中文文本人性化。