Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计通过

echovaultechovault 搜索

Agent Skill

echovault 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

269

周安装

11

GitHub Stars

132

下载量

87
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:echovault(echovault 搜索)
来源仓库:https://github.com/mraza007/echovault
仓库路径:skills/echovault
安装命令:
npx skills add https://github.com/mraza007/echovault --skill echovault
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/mraza007/echovault --skill echovault

简介

提供跨会话的持久化记忆系统,支持项目上下文检索与历史决策追溯。

  • 适用于需要长期记忆与经验积累的复杂任务场景,如项目复盘与 bug 修复。
  • 必须在使用前调用 memory context 与 memory search 获取历史信息,避免重复错误。
  • 涉及敏感数据存储时应确认脱敏策略与访问权限,防止信息泄露或误用。
  • echovault 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

EchoVault — Agent Memory System

You have persistent memory across sessions. USE IT.

Session start — MANDATORY

Before doing ANY work, retrieve context from previous sessions:

memory context --project

If the user's request relates to a specific topic, also search for it:

memory search "<relevant terms>"

When search results show "Details: available", fetch them:

memory details <memory-id>

Do not skip this step. Prior sessions may contain decisions, bugs, and context that directly affect your current task.

Session end — MANDATORY

Before ending your response to ANY task that involved making changes, debugging, deciding, or learning something, you MUST save a memory. This is not optional. If you did meaningful work, save it.

memory save \
  --title "Short descriptive title" \
  --what "What happened or was decided" \
  --why "Reasoning behind it" \
  --impact "What changed as a result" \
  --tags "tag1,tag2,tag3" \
  --category "<category>" \
  --related-files "path/to/file1,path/to/file2" \
  --source "claude-code" \
  --details "Context:

             Options considered:
             - Option A
             - Option B

             Decision:
             Tradeoffs:
             Follow-up:"

Categories: decision, bug, pattern, setup, learning, context.

Use --source to identify the agent: claude-code, codex, or cursor.

What to save

You MUST save when any of these happen:

  • You made an architectural or design decision
  • You fixed a bug (include root cause and solution)
  • You discovered a non-obvious pattern or gotcha
  • You set up infrastructure, tooling, or configuration
  • You chose one approach over alternatives
  • You learned something about the codebase that isn't in the code
  • The user corrected you or clarified a requirement

What NOT to save

  • Trivial changes (typo fixes, formatting)
  • Information that's already obvious from reading the code
  • Duplicate of an existing memory (search first)

Agent setup (recommended)

Run once to auto-install hooks for your agent:

memory setup claude-code   # or: cursor, codex

To remove: memory uninstall claude-code

Other commands

memory config       # show current configuration
memory sessions     # list session files
memory reindex      # rebuild search index
memory delete <id>  # remove a memory

Rules

  • Retrieve before working. Save before finishing. No exceptions.
  • Always capture thorough details — write for a future agent with no context.
  • Never include API keys, secrets, or credentials.
  • Wrap sensitive values in <redacted> tags.
  • Search before saving to avoid duplicates.
  • One memory per distinct decision or event. Don't bundle unrelated things.

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

35.56%
按下载量换算31

Claude

29.95%
按下载量换算26

Cursor

19.71%
按下载量换算17

Gemini CLI

9.76%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。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