Loading
Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together. Use
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add topoteretes/cognee --skill company-brain-company-qa -a cursor -y
Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together. Use when someone wants to connect their company's database, tickets and docs, or asks who owns, decided or is handling something across them. Runs locally; reads the sources, writes only to cognee's memory.
Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together. Use when someone wants to connect their company's database, tickets and docs, or asks who owns, decided or is handling something across them. Runs locally; reads the sources, writes only to cognee's memory.
Runs the company brain cookbook in examples/cookbooks/company_brain/company_qa/. It
remembers a SQL database, a ticket export and a docs folder in the cognee dataset
company_qa, extracts them with one graph model so the same person, team or project
becomes one node, then answers a question across them. Setup, the scripts and what each
one does are in the cookbook's
README.md.
Run every command from the repo root.
[setup] line says so). Tell the user the answer comes from sample data.uv run python examples/cookbooks/company_brain/company_qa/company_qa.py --check
with the sources (--database URL [--tables a,b] --tickets FILE [FILE ...] --docs FOLDER), or
none for the sample.
[setup] MISSING: line names one fix. Don't create credentials yourself.
Tell the user which line to fix, using the README's "What it needs" table, and stop.--check, adding the user's question as
--ask "...". On the sample with no --ask, it asks a question that needs all three
sample sources.[ask] A:. Give it to the user. The [ingest] lines
say which sources went in.uv run python examples/cookbooks/company_brain/company_qa/scripts/ask.py "...".company_qa.py exits 1 with a line naming what went wrong. Run
that script from examples/cookbooks/company_brain/company_qa/scripts/ on its own to
look closer..env or a database URL's password.company_qa before it ingests (the [clear]
line). On the user's own data, pass --clear only when they asked to start over: it
forgets everything the dataset holds.--ui unless the user asked to browse the graph: it keeps running until
Ctrl+C.uv run cognee-cli forget --dataset company_qa