Run an end-to-end ingestion test using a real transcript. Do the following:

1. Check if `tests/fixtures/` has a transcript beyond `sample.vtt`. If so, use it. If not, use `tests/fixtures/sample.vtt`.

PublishedJun 7, 2026

Loading actions...

5 minBeginnerprompt4 files

Skill content

Main instructions and any bundled files for this skill.

markdown

Additional Files (3)

Run an end-to-end ingestion test using a real transcript. Do the following:

Check if tests/fixtures/ has a transcript beyond sample.vtt. If so, use it. If not, use tests/fixtures/sample.vtt.
Ask the user: which ingestion mode? (a) call the API directly via curl/httpx, or (b) run the pipeline functions directly in Python.
Run the ingestion against the selected transcript. Report: chunks created, embeddings stored, any errors.
After ingestion, run a test query against the ingested meeting. Ask: "What were the main topics discussed?" Report the answer and the retrieved chunk count.
Summarise: did it work end-to-end? Any issues found?

Mark this as @pytest.mark.expensive behaviour — it calls live APIs (OpenAI embeddings, Supabase storage).

View Original Source

Related Skills

General

PromptBeginner5 minmarkdown

Untitled Skill

193

Jan 12, 2026

General

PromptBeginner5 minmarkdown

Frontend Typescript Linting.mdc

TypeScript and ESLint rules that MUST be followed when creating, modifying, or reviewing any file under apps/frontend/, including .ts, .tsx, .js, and .jsx files. Also apply when discussing frontend li...

160

Feb 15, 2026

General

PromptBeginner5 minmarkdown

2. Apply Deepthink Protocol (reason about dependencies

risks

126

Jan 15, 2026