返回顶部
e

engrm-memory

Use Engrm memory deliberately before coding, during coding, and when saving reusable lessons.

作者: admin | 来源: ClawHub
源自
ClawHub
版本
V 0.1.0
安全检测
已通过
129
下载量
0
收藏
概述
安装方式
版本历史

engrm-memory

# Engrm Memory Use this skill when the user is working on an existing codebase and continuity matters more than a cold start. ## Before you start Use Engrm only if it is already connected and available in the current environment. If Engrm is not available, say that Engrm memory is not connected on this machine and continue without inventing fallback commands or fake setup steps. ## Command guardrails Do not invent Engrm CLI commands like: - `engrm search` - `engrm save` - `engrm timeline` Those are not normal Engrm CLI commands. Memory search, timeline, save, recent activity, and stats are Engrm tool/workflow capabilities, not generic shell commands. ## What this skill is for - Pull relevant prior knowledge into the current session. - Reuse past decisions, fixes, and discoveries before repeating work. - Save new knowledge when the session produces something worth carrying forward. - Make multi-device and multi-agent memory actually useful instead of passive. ## When to use Engrm first Use Engrm before coding when: - the user is resuming work after a break - a project or subsystem looks familiar - the task touches a bug, auth flow, deployment path, or refactor area that may have been handled before - the session starts on a different machine or with a different coding agent Use Engrm during coding when: - the work starts drifting - you need to confirm an earlier decision - you suspect the same issue has already been solved elsewhere Use Engrm after coding when: - a useful decision was made - a bugfix or pattern is likely to recur - the session discovered a real lesson that future work should start with ## Default Engrm workflow 1. Start by checking recent activity or searching relevant memory. 2. Pull timeline or session context if the area has recent churn. 3. Apply prior decisions before changing code. 4. Save only high-signal outcomes, not every trivial step. ## Good Engrm questions - What did we already learn about this area? - Was there an earlier decision for this approach? - Did a previous session touch the same files or subsystem? - Is there a recent bugfix or security note I should reuse? ## Save high-signal memories Prefer saving: - durable decisions - bugfixes with clear cause and resolution - discoveries that unblock later sessions - patterns worth reusing across projects Avoid saving: - obvious implementation details - noisy or temporary dead ends - generic filler that will pollute retrieval later ## What success looks like The agent starts informed, reuses real project memory, and leaves behind a small number of valuable observations that improve the next session.

标签

skill ai

通过对话安装

该技能支持在以下平台通过对话安装:

OpenClaw WorkBuddy QClaw Kimi Claude

方式一:安装 SkillHub 和技能

帮我安装 SkillHub 和 engrm-memory-1776172382 技能

方式二:设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源,然后帮我安装 engrm-memory-1776172382 技能

通过命令行安装

skillhub install engrm-memory-1776172382

下载 Zip 包

⬇ 下载 engrm-memory v0.1.0

文件大小: 2.21 KB | 发布时间: 2026-4-17 14:45

v0.1.0 最新 2026-4-17 14:45
Initial Engrm memory skill release

Archiver·手机版·闲社网·闲社论坛·羊毛社区· 多链控股集团有限公司 · 苏ICP备2025199260号-1

Powered by Discuz! X5.0   © 2024-2025 闲社网·线报更新论坛·羊毛分享社区·http://xianshe.com

p2p_official_large
返回顶部