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异常

context-use上下文使用

Agent Skill

context-use 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

245

周安装

10

GitHub Stars

27

下载量

79
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:context-use(上下文使用)
来源仓库:https://github.com/onfabric/context-use
仓库路径:skills/context-use
安装命令:
npx skills add https://github.com/onfabric/context-use --skill context-use
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/onfabric/context-use --skill context-use

简介

context-use 是个人记忆命令行工具,依赖 OpenAI API 存储和检索用户历史信息。

  • 适用于回忆过往对话、项目细节或个人偏好的增强型问答场景。
  • 支持 ChatGPT 数据导入和历史事件记录功能。
  • 需设置 OpenAI API 密钥并通过 config show/set-key 命令完成初始化。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

context-use — Personal Memory CLI

Install: pip install context-use Requires OpenAI API key. Check: context-use config show. Set: context-use config set-key <key>.

When to Use

Use this skill when the user:

  • References past conversations, projects, or events ("remember when…", "we talked about…", "last time…")
  • Mentions people, places, or habits from their life
  • Asks something where their personal history would improve the answer
  • Wants to record something about themselves ("remember that I…")
  • Asks about their preferences, routines, or interests
  • Wants to import or process a data export (ChatGPT, Claude, Instagram, Google)
  • Asks "what do you know about me?" or similar

Do not use when the question is purely technical, general knowledge, or already answered in this session.

Bootstrap (first time)

If context-use memories list --limit 1 returns nothing, the user hasn't ingested data yet.

  1. Ask them for the path to their ZIP data export (they must download it themselves — see the provider table in Ingest).
  2. Run the pipeline: context-use pipeline --quick <provider> <path-to-zip>
  3. Generate a profile so the user can see what you now know about them: context-use agent profile Share the profile with the user — it builds trust and lets them correct anything wrong early.

Core Rule

Always search memories before responding to anything personal. Weave results naturally — never announce "I found this in your memories."

Commands

Search (primary)

context-use memories search "<query>" --top-k 5
context-use memories search "<query>" --from 2024-01-01 --to 2024-12-31

Use when: user references past conversations, projects, people, events; says "remember when…"; topic benefits from personal context. Skip when: purely technical question; general knowledge; already searched this session. If nothing relevant comes back, move on without mentioning it.

Browse

context-use memories list [--limit 20]
context-use memories get <uuid>

Create / Update / Archive

context-use memories create --content "..." --from 2024-03-01 --to 2024-03-31
context-use memories update <id> --content "..."
context-use memories archive <id1> <id2> --superseded-by <new-id>

Use when: user says "remember that I…"; memory needs correction; memories should merge. Skip when: info is transient or only relevant to current task.

Export

context-use memories export [--format json] [--out path/to/file.md]

Agent

context-use agent synthesise    # distill pattern memories from events
context-use agent profile       # compile first-person user profile
context-use agent ask "..."     # free-form memory task

Suggest synthesise after ingesting new data.

Ingest

User must download their own export (ZIP, don't unzip):

ProviderExport location
ChatGPTSettings → Data Controls → Export Data
ClaudeSettings → Account → Export Data
InstagramSettings → Accounts Center → Download your information (JSON)
Googletakeout.google.com → select products → ZIP
context-use pipeline --quick <provider> <path-to-zip>   # last 30 days
context-use pipeline <provider> <path-to-zip>            # full history, batch API

Providers: chatgpt, claude, instagram, google. Verify: context-use memories list --limit 5.

Errors

ErrorAction
"OpenAI API key not configured"Ask user for key → context-use config set-key <key>
Rate limits (quick mode)Drop --quick to use batch API
Export not readyNormal for Instagram/Google — user waits
context-use not foundpip install context-use
No memories foundGuide user through Bootstrap
Unknown providerMust be: chatgpt, claude, instagram, google
File not foundVerify path with ls, confirm ZIP location

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

35.33%
按下载量换算28

Claude

30.96%
按下载量换算24

Cursor

16.05%
按下载量换算13

Gemini CLI

8.21%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

未通过

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