
Langfuse Integration Page
If you maintain Langfuse docs and need to add a new integration page, this handles the entire scaffold. It writes the Jupyter notebook with the correct metadata block and STEPS_START wrapper, updates the routes JSON, and tries to grab the partner logo. The skill knows the four integration categories (model providers, frameworks, gateways, other) and the four instrumentation patterns (OpenInference, OpenAI drop-in, framework-native, OTEL direct), so it asks you the right questions up front and picks the matching template. It won't run the 10-minute build script for you, but everything it produces is ready for nbconvert once you do. Useful when you have working code or partner docs and just want them turned into the house format without touching JSON by hand.
- GitHub stars
- 210
- last updated
- Jun 11, 2026
Install
$ npx -y skills add langfuse/langfuse-docs --skill langfuse-integration-page --agent claude-codeInstalls into .claude/skills of the current project.
Files
Langfuse integration page creator
This skill scaffolds a new integration page for the langfuse-docs site. Integration pages live as Jupyter notebooks in cookbook/integration_<slug>.ipynb and are converted to MDX by scripts/update_cookbook_docs.sh using the mapping in cookbook/_routes.json. Getting the notebook metadata block, the STEPS_START/STEPS_END wrapper, and the routes entry right is the whole job — once those are correct, the build does the rest.
What to produce
Three things, always, in the user's langfuse-docs checkout:
- A new notebook at
cookbook/integration_<slug>.ipynbthat matches the house template (see "Notebook structure" below). - A new entry appended to
cookbook/_routes.jsonpointing at the notebook and the targetdocsPath. - A best-effort logo download into
public/images/integrations/<slug>_icon.<ext>. If fetching fails, leave a TODO for the user.
Do not run scripts/update_cookbook_docs.sh yourself — that regenerates many files and is slow (~10 min build). The user runs it when they're ready.
Step 1 — Gather what you need, up front
Sponsors
Details
- Repository
- github.com/langfuse/langfuse-docs
- Categories
- Backend & APIs, Documentation, Data Science & ML, Automation & Workflows
- License
- MIT
- First seen
- Jun 11, 2026