菜单
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/plur-ai/plur --skill effective-memory命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
基于 SOC 职业分类
正在显示 SKILL.md
| name | Effective Memory |
| description | The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected. |
| version | 1.1.0 |
| creator | plur-ai |
| license | MIT |
| tags | ["memory","learning","best-practices","session-management","feedback","safety","verification","discipline","time"] |
| x-datacore | {"id":"effective-memory","injection_policy":"on_match","match_terms":["memory","learn","remember","session","feedback","engram","forget","correction","preference","recall","verification","safety","plur"],"domain":"plur.best-practices","engram_count":12} |
Your agent has memory. These habits make it actually useful.
Without them, memory is a growing pile of assertions nobody retrieves. With them, memory compounds — each session builds on the last, corrections stick, and the agent gets measurably better over time.
This pack is pinned in PLUR 0.9.4+. Engrams here bypass keyword gating and are always eligible for injection at session start. They cover the meta-rules every agent needs regardless of domain: how to capture corrections, when to recall before answering, what "verified" means, how to stay safe with destructive actions, and why never to type a weekday from memory.
npx @plur-ai/cli@0.9.4 packs install effective-memory
(In 0.9.4+, plur init auto-installs this pack — manual install is rarely needed.)
12 engrams covering:
plur_learn immediately on corrections; detect correction-shaped phrases.plur_recall before factual answers; don't confabulate.plur_session_start / plur_session_end; plur_feedback on injected engrams; plur_timeline for long-horizon agents.Pinned engrams (introduced in PLUR 0.9.4) bypass the keyword-relevance gate in scoreEngram and per-pack/per-domain caps in fillTokenBudget. They are always eligible for injection regardless of how the user's query keywords overlap with the engram statement. Use this for cross-cutting meta-rules only; pinning everything defeats the purpose.
| Version | Changes |
|---|---|
| 1.1.0 | Consolidated plur-required meta-rules into this pack. All engrams now pinned: true. Added verification, safety, discipline, and time-handling rules. Engram count 8 → 12. |
| 1.0.0 | Initial pack — 8 engrams covering session bookends, learning triggers, and feedback loops. |