docs/zh-CN/skills/iterative-retrieval/SKILL.md
逐步优化上下文检索以解决子代理上下文问题的模式
npx skillsauth add affaan-m/everything-claude-code iterative-retrievalInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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。
子智能体被生成时上下文有限。它们不知道:
标准方法会失败:
一个逐步优化上下文的 4 阶段循环:
┌─────────────────────────────────────────────┐
│ │
│ ┌──────────┐ ┌──────────┐ │
│ │ 调度 │─────│ 评估 │ │
│ └──────────┘ └──────────┘ │
│ ▲ │ │
│ │ ▼ │
│ ┌──────────┐ ┌──────────┐ │
│ │ 循环 │─────│ 优化 │ │
│ └──────────┘ └──────────┘ │
│ │
│ 最多3次循环,然后继续 │
└─────────────────────────────────────────────┘
初始的广泛查询以收集候选文件:
// 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);
评估检索到的内容的相关性:
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:
根据评估结果更新搜索条件:
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)
};
}
使用优化后的条件重复(最多 3 个周期):
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;
}
任务:"修复身份验证令牌过期错误"
循环 1:
分发:在 src/** 中搜索 "token"、"auth"、"expiry"
评估:找到 auth.ts (0.9)、tokens.ts (0.8)、user.ts (0.3)
优化:添加 "refresh"、"jwt" 关键词;排除 user.ts
循环 2:
分发:搜索优化后的关键词
评估:找到 session-manager.ts (0.95)、jwt-utils.ts (0.85)
优化:上下文已充分(2 个高相关文件)
结果:auth.ts、tokens.ts、session-manager.ts、jwt-utils.ts
任务:"为API端点添加速率限制"
周期 1:
分发:在 routes/** 中搜索 "rate"、"limit"、"api"
评估:无匹配项 - 代码库使用 "throttle" 术语
优化:添加 "throttle"、"middleware" 关键词
周期 2:
分发:搜索优化后的术语
评估:找到 throttle.ts (0.9)、middleware/index.ts (0.7)
优化:需要路由模式
周期 3:
分发:搜索 "router"、"express" 模式
评估:找到 router-setup.ts (0.8)
优化:上下文已足够
结果:throttle.ts、middleware/index.ts、router-setup.ts
在智能体提示中使用:
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
continuous-learning 技能 - 适用于随时间改进的模式agents/)development
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
development
Use when multiple consumers and providers must evolve an API or event schema without field drift, integration surprises, or one side silently redefining the interface.
tools
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô compute status, or validate GPU nodes.
data-ai
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.