跳到正文
cccskills
免费在 GitHub 公开

memory-hygiene

Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.

中文简介正在准备中。当前显示原文说明。

mahsumaktas/agent-evolution-kit星标 2(GitHub 2 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md1.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Memory Hygiene

Keep vector memory lean. Prevent token waste from junk memories.

Quick Commands

Audit: Check what's in memory

memory_recall query="*" limit=50

Wipe: Clear all vector memory

rm -rf ~/.clawdbot/memory/lancedb/

Then restart gateway: clawdbot gateway restart

Reseed: After wipe, store key facts from MEMORY.md

memory_store text="<fact>" category="preference|fact|decision" importance=0.9

Config: Disable Auto-Capture

The main source of junk is autoCapture: true. Disable it:

{
  "plugins": {
    "entries": {
      "memory-lancedb": {
        "config": {
          "autoCapture": false,
          "autoRecall": true
        }
      }
    }
  }
}

Use gateway action=config.patch to apply.

What to Store (Intentionally)

✅ Store:

  • User preferences (tools, workflows, communication style)
  • Key decisions (project choices, architecture)
  • Important facts (accounts, credentials locations, contacts)
  • Lessons learned

❌ Never store:

  • Heartbeat status ("HEARTBEAT_OK", "No new messages")
  • Transient info (current time, temp states)
  • Raw message logs (already in files)
  • OAuth URLs or tokens

Monthly Maintenance Cron

Set up a monthly wipe + reseed:

cron action=add job={
  "name": "memory-maintenance",
  "schedule": "0 4 1 * *",
  "text": "Monthly memory maintenance: 1) Wipe ~/.clawdbot/memory/lancedb/ 2) Parse MEMORY.md 3) Store key facts to fresh LanceDB 4) Report completion"
}

Storage Guidelines

When using memory_store:

  • Keep text concise (<100 words)
  • Use appropriate category
  • Set importance 0.7-1.0 for valuable info
  • One concept per memory entry

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

中文简介正在准备中。当前显示原文说明。

mahsumaktas/agent-evolution-kit22026年3月4日 更新

Agent islemlerini policy'ye gore denetle. Hassas islem oncesi governance kontrolu calistir. Tetikleyiciler: destructive komut, dosya sistemi erisimi, rate limit, butce kontrolu, trust score yonetimi.

中文简介正在准备中。当前显示原文说明。

mahsumaktas/agent-evolution-kit22026年3月4日 更新

Evaluate and improve AgentSystem learning quality for memory/self-compound jobs. Use when bots forget, write filler summaries, fail to update learnings, or memory quality regresses over time.

中文简介正在准备中。当前显示原文说明。

mahsumaktas/agent-evolution-kit22026年3月4日 更新

Operate and validate AgentSystem live quality alarm (systemd timer + alert state) to keep memory/proactivity/consistency regressions visible in real time.

中文简介正在准备中。当前显示原文说明。

mahsumaktas/agent-evolution-kit22026年3月4日 更新

Audit and improve AgentSystem memory retention, proactive behavior, learning quality, and agent consistency. Use when bots forget context, skip memory writes, wait for explicit prompts, or repeat the same errors across runs.

中文简介正在准备中。当前显示原文说明。

mahsumaktas/agent-evolution-kit22026年3月4日 更新

Audit and remediate AgentSystem cron output hygiene by detecting raw tool logs, stack traces, and noisy summaries. Use when jobs leak 403/429/internal details, summaries are not user-safe, or post-change validation is required.

中文简介正在准备中。当前显示原文说明。

mahsumaktas/agent-evolution-kit22026年3月4日 更新

查看 mahsumaktas 的全部技能

报告此技能的问题