Skip to main content
affpapa.org
RU EN
skill

cocoindex — Claude Code skill: what it does, how to install

Helps build Python ETL pipelines with CocoIndex, manage incremental data syncs, and export embeddings into vector databases.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --skill development/cocoindex
Open on GitHub

What cocoindex does

This skill guides Claude Code in writing data ingestion pipelines with CocoIndex. It assists with building Python flows that pull records from local files or S3 buckets. From there, the flow handles document chunking, embedding generation, and exporting directly into target stores such as Qdrant or LanceDB.

Workflows rely on Python functions decorated with @cocoindex.flow_def. Data processing happens incrementally. CocoIndex updates only modified records instead of rebuilding entire indices.

A Postgres instance is mandatory for internal state tracking via COCOINDEX_DATABASE_URL. Pipelines relying on local embedding models also require optional extras such as cocoindex[embeddings] or cocoindex[colpali].

What it helps with

  • build incremental data processing pipelines for vector search
  • chunk documents and calculate text embeddings in Python
  • export extracted graph entities to Neo4j or Kuzu
  • sync updated files from object storage into Qdrant or pgvector

Example prompts for the agent

  • Create a CocoIndex flow that reads markdown files and outputs embeddings to LanceDB
  • Write an incremental ETL pipeline to extract metadata with an LLM and save to Neo4j
  • Help me configure a live indexing flow from an S3 bucket into Qdrant

How to install cocoindex

1claude-code-templates

npx claude-code-templates@latest --skill development/cocoindex

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill cocoindex -a claude-code

3Manually: put the files in place

~/.claude/skills/cocoindex/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cocoindex/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about cocoindex

How do I install cocoindex in Claude Code?

Run npx claude-code-templates@latest --skill development/cocoindex. You can also install it via the skills CLI with npx skills add davila7/claude-code-templates --skill cocoindex -a claude-code.

What does the cocoindex skill do?

It provides templates and patterns for building AI data transformation flows using the CocoIndex library. It covers data extraction, LLM parsing, and target vector database indexing.

What prerequisites are required to run CocoIndex flows?

A Postgres instance configured via COCOINDEX_DATABASE_URL is required for internal storage. Workflows with local embedding models will also require extra dependencies like cocoindex[embeddings].

Similar skills

All skills for AI and ML →
skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 350,300installs

From the same set804

The whole set →
mlops-weights-and-biases Use this skill to connect ML training workflows with Weights & Biases for run tracking, metric review, and hyperparameter searches. 63installs clerk-auth Provides patterns to set up Clerk authentication, configure route protection middleware, and handle server components in Next.js App Router. 62installs rag-faiss This skill covers FAISS indexing and nearest-vector search. Use it for RAG workflows that rely on similarity rather than metadata filters. 62installs fine-tuning-llama-factory Guides fine-tuning workflows with LLaMA-Factory, covering no-code WebUI setups and QLoRA quantization. Useful when training open-source models like Llama, Qwen, or Gemma. 62installs interview-prep-generator Turns your resume into STAR stories, likely questions and talking points for a specific role. Handy before a job interview. 61installs gws-modelarmor-create-template A slash command that has Claude create a Google Model Armor template in GCP, either from the jailbreak preset or from your own JSON filter config. 61installs clinical-decision-support Creates clinical decision documents with cohort analysis, biomarker links, evidence grading, and treatment algorithms. Built for research and drug development work. 60installs inference-serving-llama-cpp This skill guides local LLM inference with llama.cpp on CPUs, Apple Silicon, and AMD or Intel GPUs. It fits setups where CUDA is unavailable. 60installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor