search-relevance-engineering

v0.1.2

Search & Relevance Engineering specialist team — agents (search-relevance-lead, relevance-tuning-analyst, indexing-mapping-specialist, query-performance-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A search team for a relevance engineer or platform lead accountable for search quality, latency, and conversion — it measures relevance with NDCG/MRR, treats analyzer/mapping decisions as relevance decisions, builds a judgment list before tuning, and validates online with A/B. Inherits ravenclaude-core protocols.

Claude Code5 Skills

By Matt CorbettLicense: MIT7 GitHub starsUpdated last week

Directory evidence

Runtimes: Claude Code
Parsed components: 5 skill or MCP entries
Source updated: Sep 15, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install search-relevance-engineering for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install search-relevance-engineering@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/mcorbett51090/RavenClaude

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/search-relevance-engineering/.

Plugin files

plugins/search-relevance-engineering/

├── .claude-plugin/plugin.json
├── skills/build-judgment-list/SKILL.md
├── skills/fix-analyzer/SKILL.md
├── skills/measure-relevance/SKILL.md
├── skills/set-latency-budget/SKILL.md
└── skills/validate-online/SKILL.md

Included Skills5

build-judgment-listskills/build-judgment-list/SKILL.md

Build graded relevance judgments (explicit or click-derived) and an offline harness before tuning. Reach for this when there's no eval.

fix-analyzerskills/fix-analyzer/SKILL.md

Root-cause a relevance bug in tokenization/analysis/mapping before touching the ranking formula. Reach for this on a no-match or wrong-match bug.

measure-relevanceskills/measure-relevance/SKILL.md

Compute NDCG, MRR, and precision@k against the judgment list with a baseline. Reach for this before any tuning.

set-latency-budgetskills/set-latency-budget/SKILL.md

Set a p95 latency budget, decompose per-stage latency, and tune relevance within it. Reach for this on a speed/capacity question.

validate-onlineskills/validate-online/SKILL.md

Confirm an offline relevance win with an online A/B on CTR/conversion before declaring victory. Reach for this after an offline gain.

Plugin manifests1

plugins/search-relevance-engineering/.claude-plugin/plugin.json

{
  "name": "search-relevance-engineering",
  "version": "0.1.2",
  "description": "Search & Relevance Engineering specialist team — agents (search-relevance-lead, relevance-tuning-analyst, indexing-mapping-specialist, query-performance-specialist), skills, templates, commands, an advisory hook, best-practice rules, and a research-grounded knowledge bank. A search team for a relevance engineer or platform lead accountable for search quality, latency, and conversion — it measures relevance with NDCG/MRR, treats analyzer/mapping decisions as relevance decisions, builds a judgment list before tuning, and validates online with A/B. Inherits ravenclaude-core protocols.",
  "author": {
    "name": "Matt Corbett"
  },
  "homepage": "https://github.com/mcorbett51090/RavenClaude",
  "license": "MIT",
  "keywords": [
    "search-relevance",
    "ranking",
    "ndcg",
    "mrr",
    "analyzer",
    "mapping",
    "judgment-list",
    "ab-testing"
  ],
  "requires": {
    "plugins": [
      "ravenclaude-core@>=0.7.0"
    ]
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[search-relevance-engineering on Agent Plugins Marketplace](https://pluginsmp.com/plugins/search-relevance-engineering)