SKILL.md frontmatter wrong

Open the file and verify name / description are populated. Re-clone if partial.

cocoindex-claude (Claude Skill) — 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Drop-in knowledge of CocoIndex flow definitions, sources, and sinks
Guidance on writing custom transformation functions correctly
Claude picks the right CLI vs programmatic API based on task
Understands incremental processing semantics so it doesn't suggest full rebuilds
Official — authored by the CocoIndex team

라이브 데모

실제 사용 모습

cocoindex-claude-skill.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: cocoindex-claude

Build your first CocoIndex pipeline from a local folder into a vector DB

👤 Developers evaluating CocoIndex for a RAG use case ⏱ ~30 min intermediate

언제 쓸까: You've read the CocoIndex homepage and want Claude to scaffold a working flow instead of copy-pasting tutorials.

흐름

Describe the pipeline

Use the cocoindex skill — scaffold a flow that watches ./docs, chunks markdown, embeds with OpenAI, writes to Qdrant.✓ 복사됨

→ Claude generates a flow.py with @cocoindex.flow_def and the right source/transform/export calls
Run and verify

Now show me the exact CLI commands to build, run, and incrementally update this flow.✓ 복사됨

→ cocoindex setup / update / eval commands in the correct order

결과: A working flow.py plus the commands to run it — no more guessing at the CocoIndex decorator surface.

함정

Claude invents APIs that don't exist in CocoIndex — Explicitly prompt 'use only APIs documented in the cocoindex skill' — hallucination drops when the skill is in scope

함께 쓰기: filesystem

Write a custom CocoIndex transform function

👤 Engineers extending an existing CocoIndex flow ⏱ ~25 min intermediate

언제 쓸까: Built-in transforms don't cover your parsing / enrichment step.

흐름

Describe the transform

With the cocoindex skill — write a @cocoindex.op.function that takes a PDF path, extracts tables, returns structured rows.✓ 복사됨

→ Idiomatic function signature with correct typed inputs/outputs
Wire it into the flow

Now plug this into my existing flow at the chunking stage.✓ 복사됨

→ Diff against current flow.py with the new op in place

결과: A custom transform that obeys CocoIndex's incremental semantics.

함정

Function returns non-deterministic output, breaking incremental processing — Skill reminds Claude that transforms must be pure — if you hit this, re-read the incremental section

조합

다른 MCP와 조합해 10배 효율

cocoindex-claude-skill + filesystem

Let Claude actually write the flow.py file to disk, not just print it in chat

Scaffold the CocoIndex flow and save it to ./pipelines/docs_to_qdrant.py.✓ 복사됨

cocoindex-claude-skill + postgres

Pipe CocoIndex output into a Postgres vector store and query it from the same session

Build the flow targeting pgvector, then run a retrieval query against it.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출
scaffold_flow	source type + sink type + transform steps	Starting a new pipeline
write_custom_op	function intent + input/output types	Built-in transforms aren't enough
cli_guidance	task (setup / update / eval / drop)	You're unsure whether to rebuild or incrementally update

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: Modest — skill loads reference material only when relevant
금액: Free — skills are local files
팁: CocoIndex itself is free; costs come from your embedding model and vector DB, not this skill.

보안

권한, 시크릿, 파급범위

자격 증명 저장: No credentials — pure prompts

데이터 외부 송신: None from the skill itself. Your pipeline calls whichever embedding / DB services you configure.

문제 해결

자주 발생하는 오류와 해결

Wrong trigger keywords — Claude writes generic Python instead of CocoIndex

Mention CocoIndex explicitly, or say 'scaffold a cocoindex flow_def'.

대안

cocoindex-claude 다른 것과 비교

대안	언제 쓰나	단점/장점
LlamaIndex skills	You want LlamaIndex's retrieval abstractions instead of CocoIndex's transform-centric model	Different mental model — LlamaIndex is retrieval-first, CocoIndex is pipeline-first
Hand-written Python	You need one-off processing and don't want incremental state	No incremental rebuilds, no framework conventions

cocoindex-claude