This skill helps Claude build ETL pipelines with CocoIndex, a real-time data transformation framework designed for AI workloads. It covers the full workflow: writing flows that pull from sources like S3 or local files, applying transformations like chunking and embedding, then pushing to vector databases or knowledge graphs. The incremental processing model means it only touches changed data, which matters when you're syncing large document collections. Use this when you need to set up embedding pipelines, extract structured data with LLMs, or build search indexes that stay in sync with your sources. The skill walks through dependency setup, environment config with API keys, and the specific coding patterns CocoIndex uses.

skills.sh installs
281
GitHub stars
33.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add davila7/claude-code-templates --skill cocoindex --agent claude-code

Installs into .claude/skills of the current project.

Files

CocoIndex

Overview

CocoIndex is an ultra-performant real-time data transformation framework for AI with incremental processing. This skill enables building indexing flows that extract data from sources, apply transformations (chunking, embedding, LLM extraction), and export to targets (vector databases, graph databases, relational databases).

Core capabilities:

  1. Write indexing flows - Define ETL pipelines using Python
  2. Create custom functions - Build reusable transformation logic
  3. Operate flows - Run and manage flows using CLI or Python API

Key features:

  • Incremental processing (only processes changed data)
  • Live updates (continuously sync source changes to targets)
  • Built-in functions (text chunking, embeddings, LLM extraction)
  • Multiple data sources (local files, S3, Azure Blob, Google Drive, Postgres)
  • Multiple targets (Postgres+pgvector, Qdrant, LanceDB, Neo4j, Kuzu)

For detailed documentation: https://cocoindex.io/docs/ Search documentation: https://cocoindex.io/docs/search?q=url%20encoded%20keyword

When to Use This Skill

Use when users request:

Sponsors

Details

Repository
github.com/davila7/claude-code-templates
Categories
Backend & APIs, AI & Agent Building, CLI & Terminal
First seen
Jun 3, 2026

More from davila7/claude-code-templates

All 618
1rysweet avatarknowledge-extractorrysweet/amplihackExtracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. St281skills.sh installs
2patricio0312rev avatarsystem-design-generatorpatricio0312rev/skillsProduces comprehensive system architecture plans for features and products including component breakdown, data flow diagrams, system boundaries, API contracts, 280skills.sh installs
3cinience avataralicloud-ai-chatbotcinience/alicloud-skillsManage Alibaba Cloud beebot (Chatbot) via OpenAPI/SDK. Use whenever the user asks to configure, query, or troubleshoot Alibaba Cloud chatbot resources, includin279skills.sh installs
4everyinc avatarproofeveryinc/compound-engineering-pluginCreate, edit, comment on, share, and run human-in-the-loop iteration loops over markdown documents via Proof's web API. Use when asked to "proof", "share a doc"277skills.sh installs
5riba2534 avatarfeishu-cli-cardriba2534/feishu-cli构造美观、元素丰富的飞书 V2.0 交互式卡片(interactive card)。支持折叠面板、 多栏布局、图表、彩色标签、按钮组、人员卡、流式更新等 20+ 组件,内置 7 个场景模板 (通知 / 成功报告 / 告警 / 审批 / 数据大屏 / 文章摘要 / AI 流式)和配色布局规范。 当用户请求"发卡片"、"发277skills.sh installs
6secondsky avatarsveltia-cmssecondsky/claude-skillsSveltia CMS Git-backed content management (Decap/Netlify CMS successor). 5x smaller bundle (300 KB), GraphQL performance, solves 260+ issues. Use for static sit277skills.sh installs