Iterative Retrieval logo

Iterative Retrieval

CommunityPopular
xu-xiang
iterative-retrieval

逐步优化上下文检索以解决子代理上下文问题的模式

Overview

Publisherxu-xiang
Repositoryeverything-claude-code-zh
Skill nameiterative-retrieval
Stars
2K
Forks
327
Bundled files
Instructions only
LicenseMIT
Links
  • 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 xu-xiang on GitHub. Read the source before you install it.

Installation

Install the Iterative Retrieval 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/xu-xiang/everything-claude-code-zh/tree/main/docs/zh-CN/skills/iterative-retrieval
  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/xu-xiang/everything-claude-code-zh.git /tmp/everything-claude-code-zh
mkdir -p .claude/skills
cp -r /tmp/everything-claude-code-zh/docs/zh-CN/skills/iterative-retrieval .claude/skills/iterative-retrieval
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Iterative Retrieval 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 Iterative Retrieval 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 Iterative Retrieval 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.

迭代检索模式

解决多智能体工作流中的“上下文问题”,即子智能体在开始工作前不知道需要哪些上下文。

何时激活

  • 当需要生成需要代码库上下文但无法预先预测的子代理时
  • 构建需要逐步完善上下文的多代理工作流时
  • 在代理任务中遇到"上下文过大"或"缺少上下文"的失败时
  • 为代码探索设计类似 RAG 的检索管道时
  • 在代理编排中优化令牌使用时

问题

子智能体被生成时上下文有限。它们不知道:

  • 哪些文件包含相关代码
  • 代码库中存在哪些模式
  • 项目使用什么术语

标准方法会失败:

  • 发送所有内容:超出上下文限制
  • 不发送任何内容:智能体缺乏关键信息
  • 猜测所需内容:经常出错

解决方案:迭代检索

一个逐步优化上下文的 4 阶段循环:

┌─────────────────────────────────────────────┐
│                                             │
│   ┌──────────┐      ┌──────────┐            │
│   │ DISPATCH │─────▶│ EVALUATE │            │
│   └──────────┘      └──────────┘            │
│        ▲                  │                 │
│        │                  ▼                 │
│   ┌──────────┐      ┌──────────┐            │
│   │   LOOP   │◀─────│  REFINE  │            │
│   └──────────┘      └──────────┘            │
│                                             │
│        Max 3 cycles, then proceed           │
└─────────────────────────────────────────────┘

阶段 1:调度

初始的广泛查询以收集候选文件:

javascript
// Start with high-level intent
const initialQuery = {
  patterns: ['src/**/*.ts', 'lib/**/*.ts'],
  keywords: ['authentication', 'user', 'session'],
  excludes: ['*.test.ts', '*.spec.ts']
};

// Dispatch to retrieval agent
const candidates = await retrieveFiles(initialQuery);

阶段 2:评估

评估检索到的内容的相关性:

javascript
function evaluateRelevance(files, task) {
  return files.map(file => ({
    path: file.path,
    relevance: scoreRelevance(file.content, task),
    reason: explainRelevance(file.content, task),
    missingContext: identifyGaps(file.content, task)
  }));
}

评分标准:

  • 高 (0.8-1.0):直接实现目标功能
  • 中 (0.5-0.7):包含相关模式或类型
  • 低 (0.2-0.4):略微相关
  • 无 (0-0.2):不相关,排除

阶段 3:优化

根据评估结果更新搜索条件:

javascript
function refineQuery(evaluation, previousQuery) {
  return {
    // Add new patterns discovered in high-relevance files
    patterns: [...previousQuery.patterns, ...extractPatterns(evaluation)],

    // Add terminology found in codebase
    keywords: [...previousQuery.keywords, ...extractKeywords(evaluation)],

    // Exclude confirmed irrelevant paths
    excludes: [...previousQuery.excludes, ...evaluation
      .filter(e => e.relevance < 0.2)
      .map(e => e.path)
    ],

    // Target specific gaps
    focusAreas: evaluation
      .flatMap(e => e.missingContext)
      .filter(unique)
  };
}

阶段 4:循环

使用优化后的条件重复(最多 3 个周期):

javascript
async function iterativeRetrieve(task, maxCycles = 3) {
  let query = createInitialQuery(task);
  let bestContext = [];

  for (let cycle = 0; cycle < maxCycles; cycle++) {
    const candidates = await retrieveFiles(query);
    const evaluation = evaluateRelevance(candidates, task);

    // Check if we have sufficient context
    const highRelevance = evaluation.filter(e => e.relevance >= 0.7);
    if (highRelevance.length >= 3 && !hasCriticalGaps(evaluation)) {
      return highRelevance;
    }

    // Refine and continue
    query = refineQuery(evaluation, query);
    bestContext = mergeContext(bestContext, highRelevance);
  }

  return bestContext;
}

实际示例

示例 1:错误修复上下文

Task: "Fix the authentication token expiry bug"

Cycle 1:
  DISPATCH: Search for "token", "auth", "expiry" in src/**
  EVALUATE: Found auth.ts (0.9), tokens.ts (0.8), user.ts (0.3)
  REFINE: Add "refresh", "jwt" keywords; exclude user.ts

Cycle 2:
  DISPATCH: Search refined terms
  EVALUATE: Found session-manager.ts (0.95), jwt-utils.ts (0.85)
  REFINE: Sufficient context (2 high-relevance files)

Result: auth.ts, tokens.ts, session-manager.ts, jwt-utils.ts

示例 2:功能实现

Task: "Add rate limiting to API endpoints"

Cycle 1:
  DISPATCH: Search "rate", "limit", "api" in routes/**
  EVALUATE: No matches - codebase uses "throttle" terminology
  REFINE: Add "throttle", "middleware" keywords

Cycle 2:
  DISPATCH: Search refined terms
  EVALUATE: Found throttle.ts (0.9), middleware/index.ts (0.7)
  REFINE: Need router patterns

Cycle 3:
  DISPATCH: Search "router", "express" patterns
  EVALUATE: Found router-setup.ts (0.8)
  REFINE: Sufficient context

Result: throttle.ts, middleware/index.ts, router-setup.ts

与智能体集成

在智能体提示中使用:

markdown
在为该任务检索上下文时:
1. 从广泛的关键词搜索开始
2. 评估每个文件的相关性(0-1 分制)
3. 识别仍缺失哪些上下文
4. 优化搜索条件并重复(最多 3 个循环)
5. 返回相关性 >= 0.7 的文件

最佳实践

  1. 先宽泛,后逐步细化 - 不要过度指定初始查询
  2. 学习代码库术语 - 第一轮循环通常能揭示命名约定
  3. 跟踪缺失内容 - 明确识别差距以驱动优化
  4. 在“足够好”时停止 - 3 个高相关性文件胜过 10 个中等相关性文件
  5. 自信地排除 - 低相关性文件不会变得相关

相关

  • 长篇指南 - 子智能体编排部分
  • continuous-learning 技能 - 用于随时间改进的模式
  • 在 ~/.claude/agents/ 中的智能体定义

Frequently asked questions

What does the Iterative Retrieval AI skill do?

逐步优化上下文检索以解决子代理上下文问题的模式

Why use Iterative Retrieval on TypingMind?

Because you install it once and use it with any model. Iterative Retrieval 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 Iterative Retrieval in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xu-xiang/everything-claude-code-zh/tree/main/docs/zh-CN/skills/iterative-retrieval. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Iterative Retrieval?

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 Iterative Retrieval?

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

Is the Iterative Retrieval AI skill free?

Yes. It is published on GitHub by xu-xiang 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.

View all

Set up your own AI workspace now

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