Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

memory记忆

Agent Skill

memory 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,988

周安装

82

GitHub Stars

公开资料未说明

下载量

649
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:memory(记忆)
来源仓库:https://github.com/lidessen/skills
仓库路径:skills/memory
安装命令:
npx skills add https://github.com/lidessen/skills --skill memory
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lidessen/skills --skill memory

简介

用于查找、检索和筛选相关信息,支持关键词匹配和任务场景定位。

  • 适用于 Codex、Claude、Cursor、Gemini CLI,通过 GitHub 安装。
  • 适合快速定位候选结果或整理信息线索。
  • 可结合来源仓库 README 核验具体用法和功能细节。
  • 安装前建议确认权限范围和维护状态,避免触发不必要操作。

SKILL.md

Memory

Memory is not storage. Memory is the foundation for evolution.

Philosophy

Why Memory?

Without memory, every session starts from zero.

Session 1: Makes mistake A
Session 2: Makes mistake A again
Session 3: Makes mistake A again
...forever

With memory, patterns emerge:

Session 1: Makes mistake A, records it
Session 2: Reads record, avoids A, discovers B
Session 3: Reads both, avoids A and B, finds better path
...progress

Memory isn't for the current session—memory is a gift to future sessions.

The Deeper Purpose

Memory transforms isolated events into accumulated wisdom.

Individual record: "We tried X, it failed because Y"
Pattern after 5 records: "Approaches like X tend to fail when Y"
Wisdom after 20 records: "Before attempting X-like solutions, check for Y"

This is how learning works. Not through rules handed down, but through patterns that emerge from recorded experience.

What to Remember

Not everything deserves memory. Record what would hurt if forgotten:

RememberDon't Remember
Decisions and their rationaleImplementation details (use code)
Mistakes and lessonsObvious facts (use docs)
Context that explains "why"Temporary debugging notes
Patterns that emergedThings Git already tracks

The test: "Would a future agent benefit from knowing this?"

Structure

.memory/
├── context.md      → Current state, active concerns (read first)
├── notes/          → Learnings, observations
├── decisions/      → ADRs: what was decided and why
├── todos/          → Tasks that span sessions
└── sessions/       → Session summaries (handoff to next)

context.md

The handoff document. When a new session starts, this tells them:

  • What's currently in progress
  • What concerns are active
  • What needs attention

Keep it current. A stale context.md is worse than none.

Naming Convention

YYYY-MM-DD-kebab-slug.md

Natural sort order. Grep-friendly. Self-documenting.

Core Operations

IntentAction
"Remember this"Create note in .memory/notes/
"We decided X because Y"Create ADR in .memory/decisions/
"What did we learn about Z?"Search .memory/, summarize with citations
"Session ending"Create session summary, update context.md

Record Format

---
type: note | decision | todo | session
status: active | completed | archived
tags: [relevant, keywords]
created: YYYY-MM-DD
---

# Title

Content that future agents will thank you for.

Integration

Memory provides context to other skills:

memory
  │
  ├─► orientation reads context.md at session start
  ├─► dive uses past notes to inform investigation
  ├─► engineering reads decisions before proposing new ones
  └─► refining includes relevant history in PR descriptions

Understanding, Not Rules

TensionResolution
Completeness vs NoiseRecord signal, not noise. Ask: "Would this help a future agent?"
Structure vs FlexibilityUse consistent format, but content matters more than form
Writing vs DoingRecording takes seconds; re-learning takes hours

The Anti-Pattern

The worst failure isn't forgetting to record—it's recording without understanding.

Bad: "Fixed bug in auth"
Good: "Auth was failing silently when token expired mid-request.
       Root cause: async race condition.
       Fix: Added token refresh before sensitive operations.
       Lesson: Any auth code should handle mid-operation expiry."

The second takes 30 seconds longer. It saves the next agent hours.

Reference

See reference/ for:

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

32.33%
按下载量换算210

Claude

30.81%
按下载量换算200

Cursor

19.41%
按下载量换算126

Gemini CLI

9.51%
按下载量换算62

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills