rag-system-builder-advanced-reranking

Sub-skill of rag-system-builder: Advanced: Reranking.

5 stars

Best use case

rag-system-builder-advanced-reranking is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Sub-skill of rag-system-builder: Advanced: Reranking.

Teams using rag-system-builder-advanced-reranking should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/advanced-reranking/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/_archive/data/documents/rag-system-builder/advanced-reranking/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/advanced-reranking/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How rag-system-builder-advanced-reranking Compares

Feature / Agentrag-system-builder-advanced-rerankingStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Sub-skill of rag-system-builder: Advanced: Reranking.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Advanced: Reranking

## Advanced: Reranking


Add a reranking step for improved precision:

```python
from sentence_transformers import CrossEncoder

class Reranker:
    def __init__(self, model_name='cross-encoder/ms-marco-MiniLM-L-6-v2'):
        self.model = CrossEncoder(model_name)

    def rerank(self, query, candidates, top_k=5):
        """Rerank candidates using cross-encoder."""
        pairs = [(query, c['text']) for c in candidates]
        scores = self.model.predict(pairs)

        for i, score in enumerate(scores):
            candidates[i]['rerank_score'] = float(score)

        reranked = sorted(candidates, key=lambda x: x['rerank_score'], reverse=True)
        return reranked[:top_k]

# Usage in RAG pipeline
def query_with_rerank(self, question, initial_k=20, final_k=5):
    # First pass: retrieve more candidates
    candidates = semantic_search(self.db_path, question, self.model, top_k=initial_k)

    # Second pass: rerank for precision
    reranked = self.reranker.rerank(question, candidates, top_k=final_k)

    return reranked
```

Related Skills

repo-ecosystem-hygiene

5
from vamseeachanta/workspace-hub

Interpret the daily read-only repo ecosystem hygiene audit and route remediation through approved workflows.

provider-session-ecosystem-audit-and-exporters

5
from vamseeachanta/workspace-hub

Build and maintain cross-provider session-log audits for Codex, Codex, Hermes, and Gemini, including exporter design, normalization, and behavioral verification.

ecosystem-terminology

5
from vamseeachanta/workspace-hub

Canonical names, abbreviations, and relationship vocabulary for the workspace-hub ecosystem. Load this when naming repos, modules, machines, files, or expanding acronyms to ensure consistency across humans and agents. type: reference

llm-wiki-ecosystem-gap-to-issues

5
from vamseeachanta/workspace-hub

Review the workspace-hub LLM-wiki/document-intelligence ecosystem, identify high-leverage gaps, and create grounded GitHub feature issues without duplicating existing work.

hermes-ecosystem-integration

5
from vamseeachanta/workspace-hub

Wire Hermes into workspace-hub ecosystem — multi-repo skills, config sync, session export to learning pipeline, memory cross-pollination, skill patch tracking, and cross-machine health checks.

systematic-debugging

5
from vamseeachanta/workspace-hub

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

mcp-builder

5
from vamseeachanta/workspace-hub

Guide for building high-quality Model Context Protocol (MCP) servers that allow LLMs to interact with external services. Use when creating new MCP integrations, tools, or servers for Codex or other AI systems.

rag-system-builder

5
from vamseeachanta/workspace-hub

Build Retrieval-Augmented Generation (RAG) Q&A systems with Codex or OpenAI. Use for creating AI assistants that answer questions from document collections, technical libraries, or knowledge bases.

knowledge-base-builder

5
from vamseeachanta/workspace-hub

Build searchable knowledge bases from document collections (PDFs, Word, text files). Use for creating technical libraries, standards repositories, research databases, or any large document collection requiring full-text search.

interactive-dashboard-builder

5
from vamseeachanta/workspace-hub

Create self-contained HTML/JavaScript dashboards with Chart.js, filters, and professional styling

skill-ecosystem-curation

5
from vamseeachanta/workspace-hub

Class-level skill ecosystem curation: housekeeping, deduplication/collision reconciliation, archival, and consolidation governance.

provider-session-ecosystem-audit

5
from vamseeachanta/workspace-hub

Audit Codex/Codex/Hermes/Gemini session logs, normalize provider-specific quirks, and wire recurring exports/reporting for ongoing ecosystem health checks.