Skip to main content

Iterative Retrieval

Skill Verified Active

Iterative retrieval — 4-stage loop (DISPATCH→EVALUATE→REFINE→LOOP) to pinpoint relevant information in the code base. Up to 3 rounds.

Purpose

To efficiently and accurately pinpoint relevant information within large codebases by employing a structured, iterative search and refinement process.

Features

  • 4-stage iterative retrieval loop (DISPATCH, EVALUATE, REFINE, LOOP)
  • Multiple search strategies (Glob, Grep, AST)
  • Relevance-based evaluation and refinement of search queries
  • Up to 3 rounds of iterative search for precise results
  • Output includes resolved information and unresolved issues

Use Cases

  • Finding specific functions or classes in a large, unfamiliar codebase
  • Locating the source of a bug or a particular piece of logic
  • Understanding the implementation details of a feature by iteratively refining search
  • Gathering information for code reviews or refactoring efforts

Non-Goals

  • Replacing standard code search tools entirely
  • Performing code modifications or refactoring directly
  • Providing a full code analysis beyond information retrieval

Workflow

  1. Extract search keywords from requirements.
  2. Choose a search strategy (Glob, Grep, AST) and launch searches.
  3. Evaluate search results on a 0-1 relevance scale.
  4. Refine search strategy based on evaluation.
  5. Loop until enough information is found, rounds reach 3, or all aspects are covered.

Practical Utility

  • info:Usage examplesWhile the overall VibeGuard project has extensive examples, this specific skill's SKILL.md lacks concrete end-to-end examples of its iterative retrieval process.

Installation

npx skills add majiayu000/vibeguard

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

Verified
97 /100
Analyzed about 19 hours ago

Trust Signals

Last commitabout 22 hours ago
Stars8
LicenseMIT
Status
View Source

Similar Extensions

Lean Ctx

100

Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.

Skill
yvgude

Manus

100

Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.

Skill
sanjay3290

Risk Management

100

Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt", "position size", "lot size", "confidence", "revenge trading", "overtrading", "discipline".

Skill
mnemox-ai

Setup Gbrain

100

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)

Skill
garrytan

Skill Creator

100

Guide for creating effective skills

Skill
bobmatnyc

Understand Dashboard

100

Launch the interactive web dashboard to visualize a codebase's knowledge graph

Skill
Lum1104

© 2025 SkillRepo · Find the right skill, skip the noise.