AGENT SKILL

iterative-retrieval

Pattern for progressively refining context retrieval to solve the subagent context problem. Use when a subagent lacks the context it needs and retrieval must be refined across passes.

License 许可
MIT
所属仓库
siddu1004/SFP
最近更新
2026-11-09
Stars
★ 5
Forks
0

01 前言 Front Matter

name
iterative-retrieval
metadata
{ "origin": "ECC" }
description
Pattern for progressively refining context retrieval to solve the subagent context problem. Use when a subagent lacks the context it needs and retrieval must be refined across passes.

03 SKILL.md 正文

Iterative Retrieval Pattern

Solves the "context problem" in multi-agent workflows where subagents don't know what context they need until they start working.

When to Activate

  • Spawning subagents that need codebase context they cannot predict upfront
  • Building multi-agent workflows where context is progressively refined
  • Encountering "context too large" or "missing context" failures in agent tasks
  • Designing RAG-like retrieval pipelines for code exploration
  • Optimizing token usage in agent orchestration

The Problem

Subagents are spawned with limited context. They don't know:

  • Which files contain relevant code
  • What patterns exist in the codebase
  • What terminology the project uses

Standard approaches fail:

  • Send everything: Exceeds context limits
  • Send nothing: Agent lacks critical information
  • Guess what's needed: Often wrong

The Solution: Iterative Retrieval

A 4-phase loop that progressively refines context:

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

Phase 1: DISPATCH

Initial broad query to gather candidate files:

// 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);

Phase 2: EVALUATE

Assess retrieved content for relevance:

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)
  }));
}

Scoring criteria:

  • High (0.8-1.0): Directly implements target functionality
  • Medium (0.5-0.7): Contains related patterns or types
  • Low (0.2-0.4): Tangentially related
  • None (0-0.2): Not relevant, exclude

Phase 3: REFINE

Update search criteria based on evaluation:

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)
  };
}

Phase 4: LOOP

Repeat with refined criteria (max 3 cycles):

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;
}

Practical Examples

Example 1: Bug Fix Context

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

Example 2: Feature Implementation

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

Integration with Agents

Use in agent prompts:

When retrieving context for this task:
1. Start with broad keyword search
2. Evaluate each file's relevance (0-1 scale)
3. Identify what context is still missing
4. Refine search criteria and repeat (max 3 cycles)
5. Return files with relevance >= 0.7

Best Practices

  1. Start broad, narrow progressively - Don't over-specify initial queries
  2. Learn codebase terminology - First cycle often reveals naming conventions
  3. Track what's missing - Explicit gap identification drives refinement
  4. Stop at "good enough" - 3 high-relevance files beats 10 mediocre ones
  5. Exclude confidently - Low-relevance files won't become relevant

Related

  • The Longform Guide - Subagent orchestration section
  • continuous-learning skill - For patterns that improve over time
  • Agent definitions bundled with ECC (manual install path: agents/)

04 同仓库更多 Skills

siddu1004
siddu1004/SFP

scientific-schematics

Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

★ 5
siddu1004
siddu1004/SFP

polyhaven-texture-apply

Apply realistic PBR textures from PolyHaven to any Blender object. Supports metals, wood, concrete, fabric, and more. Trigger when asked to texture an object, apply a material from PolyHaven, make something look like metal/wood/marble, or change object surface.

★ 5
siddu1004
siddu1004/SFP

polyhaven-studio-setup

Set up a professional product photography studio in Blender using PolyHaven HDRIs and PBR ground materials. Trigger when asked to create a studio setup, add HDRI lighting, set up product photography, or create a showroom scene.

★ 5
siddu1004
siddu1004/SFP

polyhaven-scene-builder

Build complete product scenes using PolyHaven assets — HDRI environment, textured ground/pedestal, and optional props from the 3D model library. Trigger when asked to build a product scene, create a showcase setup, add a pedestal, or compose a product shot.

★ 5
siddu1004
siddu1004/SFP

polyhaven-material-swap

Cycle through multiple PolyHaven materials on a product and render each variant. Great for showing color/finish options. Trigger when asked to show material variants, swap textures, create color options, show finish comparisons, or render product in different materials.

★ 5
siddu1004
siddu1004/SFP

polyhaven-hdri-showcase

Render the same product across multiple HDRI environments and output a comparison grid. Trigger when asked to compare lighting setups, test different environments, show product in multiple settings, or create an HDRI comparison.

★ 5