Teaches Claude Code how to build CocoIndex data-transformation pipelines — real-time incremental processing for vector DBs and knowledge graphs.
CocoIndex is a real-time data transformation framework for AI pipelines (source → transform → vector DB / knowledge graph). This skill loads its conventions into Claude Code so the model writes idiomatic CocoIndex flows, custom functions, and CLI/API commands instead of guessing at an unfamiliar library.
Build your first CocoIndex pipeline from a local folder into a vector DB
👤 Developers evaluating CocoIndex for a RAG use case⏱ ~30 minintermediate
Wann einsetzen: You've read the CocoIndex homepage and want Claude to scaffold a working flow instead of copy-pasting tutorials.
Ablauf
Describe the pipeline
Use the cocoindex skill — scaffold a flow that watches ./docs, chunks markdown, embeds with OpenAI, writes to Qdrant.✓ Kopiert
→ 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.✓ Kopiert
→ cocoindex setup / update / eval commands in the correct order
Ergebnis: A working flow.py plus the commands to run it — no more guessing at the CocoIndex decorator surface.
Fallstricke
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
👤 Engineers extending an existing CocoIndex flow⏱ ~25 minintermediate
Wann einsetzen: Built-in transforms don't cover your parsing / enrichment step.
Ablauf
Describe the transform
With the cocoindex skill — write a @cocoindex.op.function that takes a PDF path, extracts tables, returns structured rows.✓ Kopiert
→ Idiomatic function signature with correct typed inputs/outputs
Wire it into the flow
Now plug this into my existing flow at the chunking stage.✓ Kopiert
→ Diff against current flow.py with the new op in place
Ergebnis: A custom transform that obeys CocoIndex's incremental semantics.
Fallstricke
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