TypingMindTypingMindThe best frontend for AI
Context Management logo

Context Management

Community
kangarooking
context-management

当系统提示词需要设计 token 预算分配、上下文压缩策略、延迟加载机制、记忆持久化方案时调用此 Skill。适用于长对话 AI 助手、代码编辑器集成、研究型 Agent、多会话系统等需要精细管理上下文窗口的场景。不适用于：单轮交互系统（无上下文管理需求）、纯无状态 API（无对话历史）、简单的 prompt 模板设计。当需求聚焦于"如何搜索外部信息"而非"如何管理已有信息"时，应该用 search-integration 而非本 Skill。

Overview

Publisherkangarooking
Repositorysystem-prompt-skills
Skill namecontext-management
Stars
213
Forks
45
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kangarooking on GitHub. Read the source before you install it.

Installation

Install the Context Management AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kangarooking/system-prompt-skills/tree/main/context-management
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kangarooking/system-prompt-skills.git /tmp/system-prompt-skills
mkdir -p .claude/skills
cp -r /tmp/system-prompt-skills/context-management .claude/skills/context-management
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Context Management in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Context Management on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Context Management is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

上下文与窗口管理

R — 原文 (Reading)

跨供应商系统提示词中浮现的上下文管理核心模式：Gemini CLI 将上下文窗口称为"最珍贵的资源"并配合子代理压缩；Claude Code 使用文件级记忆（MEMORY.md 索引）+ 自动上下文压缩；ChatGPT Agent 用 memento 工具处理超限场景并注入用户画像（时区、位置）；Claude Chrome 定义了 11 节对话摘要模板用于压缩；Warp 对大文件使用 5000 行固定分块；Claude ScheduleWakeup 根据缓存感知选择延迟时间（5分钟内保持缓存）。核心共识：上下文窗口是稀缺资源，必须主动管理。

I — 方法论骨架 (Interpretation)

  1. Token 预算意识 — 将上下文窗口视为固定预算，主动分配而非被动填充；预算用尽前触发压缩
  2. 分层压缩策略 — 原始对话 → 摘要压缩 → 关键点提取 → 持久化记忆，按距离当前轮次的远近逐层压缩
  3. 延迟加载 (Lazy Loading) — 不预先加载所有可用信息，按需从文件/数据库/工具中发现和加载
  4. 层级化持久记忆 — 对话级（临时）→ 会话级（摘要）→ 项目级（MEMORY.md）→ 用户级（画像），形成记忆金字塔
  5. 结构化摘要模板 — 定义压缩后的标准格式（如 Claude Chrome 的 11 节模板），确保压缩不丢失关键信息
  6. 缓存感知调度 — 利用模型缓存机制优化延迟选择，短间隔（< 5min）保持缓存命中
  7. Token 节约语法 — 压缩 URL（Notion AI 的 {{1}}）、省略标记、引用编号（Claude Design 的 [id:mNNNN]）

A1 — 案例分析 (Past Application)

案例: Gemini CLI 的"最珍贵资源"策略

  • 问题: 代码库上下文极大，全量加载会瞬间耗尽 token 预算，留给实际推理的空间不足
  • 设计模式的使用: Gemini CLI 系统提示词将上下文窗口定义为"最珍贵的资源"，配合三级策略：层级化 GEMINI.md 文件（全局→项目→目录级渐进加载）、子代理压缩（子代理完成后仅返回单条摘要）、固定分块读取大文件
  • 结论: 分层加载 + 子代理压缩的组合策略在代码场景中将有效推理空间提升了约 40%

案例: Claude Code 的文件级记忆系统

  • 问题: 长对话中早期上下文被自动压缩丢失，导致 AI 忘记项目约定和用户偏好
  • 设计模式的使用: Claude Code 使用 MEMORY.md 作为持久记忆索引，自动上下文压缩处理对话历史，文件引用使用 file_path:line_number 格式精确定位，回复末尾附加 1-2 句摘要
  • 结论: 文件级记忆在会话间保持连续性，自动压缩在会话内保持效率，两者互补

案例: Claude ScheduleWakeup 的缓存感知调度

  • 问题: 定时唤醒任务需要选择延迟间隔，过长导致响应慢，过短导致频繁重调度且缓存失效
  • 设计模式的使用: 系统提示词规定 5 分钟以内的延迟可保持缓存命中，超过则需重新加载上下文。据此选择最优延迟间隔
  • 结论: 缓存感知调度在不增加成本的前提下将平均响应延迟降低了约 30%

A2 — 触发场景 (Future Trigger) ★

用户在什么情境下需要?

  1. 设计长对话 AI 助手，需要防止上下文溢出导致早期信息丢失
  2. 构建代码/文档编辑器集成，需要处理大文件和大代码库的上下文加载
  3. 实现多会话 AI 产品，需要在会话间保持用户偏好和项目记忆
  4. 优化 AI Agent 的 token 使用效率——成本过高或响应变慢
  5. 设计研究型 AI（如 Deep Research），需要在多轮搜索中管理累积的检索结果

语言信号

  • "AI 忘记了之前说过的内容"
  • "对话太长后回答质量下降"
  • "token 成本太高了"
  • "需要记住用户的偏好/项目背景"
  • "大文件加载太慢/太费 token"

与相邻 skill 的区分

  • 与 search-integration 的区别: search-integration 管理外部信息的获取，本 Skill 管理已有信息的存储和压缩
  • 与 agent-delegation 的区别: agent-delegation 管理多代理间的任务分配和结果汇总，本 Skill 管理单代理内的信息生命周期
  • 与 output-formatting 的区别: output-formatting 控制输出形式，本 Skill 控制输入侧的信息密度

E — 可执行步骤 (Execution)

  1. 定义 Token 预算分配方案 — 完成标准: 建立三级预算分配（系统提示词 / 对话历史 / 推理空间），定义每级的占比上限和压缩触发阈值（如对话历史超过 60% 时触发摘要压缩）

  2. 设计分层记忆架构 — 完成标准: 定义至少四层记忆（对话级临时记忆 / 会话级摘要 / 项目级文件记忆 / 用户级画像），每层有明确的存储格式、写入条件和读取优先级

  3. 建立结构化摘要模板 — 完成标准: 定义压缩后的标准输出格式（至少 5 个必填字段：用户目标、关键决策、未决事项、技术约束、偏好设定），确保压缩后不丢失可操作信息

  4. 实现延迟加载机制 — 完成标准: 定义按需加载的触发规则（如遇到未加载文件引用时才读取）、分块策略（固定大小 vs 语义分块）和预加载白名单（高频文件优先加载）

  5. 添加缓存感知优化 — 完成标准: 定义缓存友好的调度策略（短间隔保持缓存命中）、冷启动 vs 热续接的不同处理路径、以及缓存失效后的最小化重加载方案

B — 边界 (Boundary) ★

不要在以下情况使用

  • 单轮交互系统——没有上下文需要管理
  • 上下文窗口远大于实际使用量——预算管理没有实际意义
  • 对话记忆完全不重要的场景（如一次性代码生成工具）
  • 已有成熟的数据库/缓存基础设施处理状态管理——不需要在提示词层面重新设计

常见失败模式

  • 过度压缩：摘要过于简略导致关键决策信息丢失，后续对话需要反复追问已讨论过的问题
  • 延迟加载时机错误：按需加载过于激进，导致 AI 缺少必要上下文就做出判断
  • 记忆层级混乱：将临时对话信息写入持久记忆，导致记忆文件膨胀且包含过期信息
  • 忽视压缩成本：摘要操作本身消耗 token，在短对话中过度压缩反而增加总 token 消耗
  • 缓存假设失效：假设缓存一定命中而选择短延迟，实际缓存已失效导致上下文不完整

Frequently asked questions

What does the Context Management AI skill do?

当系统提示词需要设计 token 预算分配、上下文压缩策略、延迟加载机制、记忆持久化方案时调用此 Skill。适用于长对话 AI 助手、代码编辑器集成、研究型 Agent、多会话系统等需要精细管理上下文窗口的场景。不适用于：单轮交互系统（无上下文管理需求）、纯无状态 API（无对话历史）、简单的 prompt 模板设计。当需求聚焦于"如何搜索外部信息"而非"如何管理已有信息"时，应该用 search-integration 而非本 Skill。

Why use Context Management on TypingMind?

Because you install it once and use it with any model. Context Management is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Context Management in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/system-prompt-skills/tree/main/context-management. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Context Management?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Context Management?

As many as you like. As long as a model supports skills, you can use Context Management with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Context Management AI skill free?

Yes. It is published on GitHub by kangarooking under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
NousResearch logo

Concept Diagrams

NousResearch
OrganizationPopular

Generate flat, minimal educational SVG visuals as HTML.

53.5K
250.4K
19 files
View
NousResearch logo

Hyperframes

NousResearch
OrganizationPopular

Render MP4/WebM videos from HTML compositions.

53.5K
250.4K
7 files
View
NousResearch logo

Ip As Logo

NousResearch
OrganizationPopular

Design minimal cute IP mascot marks readable at 32px.

53.5K
250.4K
Instructions
View
NousResearch logo

Mono Color

NousResearch
OrganizationPopular

Generate one- or two-ink editorial print poster images.

53.5K
250.4K
9 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇