Skip to content
Agentmart
Submit a tool

deduplicating-embeddings

Semantic deduplication across Excel, CSV, and SQLite sources using embeddings

Skill by Orchestra-Inc

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/orchestra-inc-deduplicating-embeddings

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Semantic deduplication across Excel, CSV, and SQLite sources using embeddings

Use cases: spreadsheets

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deduplicating-embeddings

What's inside

Skill name
deduplicating-embeddings
Description
Semantic deduplication across Excel, CSV, and SQLite sources using embeddings
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Deduplicating Embeddings Skill

Find semantically similar content across spreadsheets and databases using multilingual-e5 embeddings + FAISS + SemDeDup clustering.

## When to use

- Finding duplicate rows in Excel/CSV files
- Merging datasets with overlapping entries
- Cleaning customer lists, product catalogs, or contact databases

## Usage

```bash
# Create embedding index from CSV
agent dedupe --source data.csv --column "Company Name"

# Find duplicates across multiple files
agent dedupe --sources file1.csv file2.xlsx --threshold 0.85
```

## Supported formats
- Excel (.xlsx, .xls)
- CSV (.csv)
- SQLite (.db, .sqlite)

From Orchestra-Inc/agent-framework, MIT.

More from Orchestra-Inc/agent-framework

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 24, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Orchestra-Inc/agent-framework
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Orchestra-Inc

Cite this page

deduplicating-embeddings skill. Agent Mart. https://agentmart.dev/skills/orchestra-inc-deduplicating-embeddings (last updated 2026-10-24)