Agent skill

Company Brain Company QA

by topoteretes in topoteretes/cognee

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.

Apache-2.0Auto-check: notesSales & Support

Install Company Brain Company QA

skills CLI
$ npx skills add topoteretes/cognee --skill company-brain-company-qa -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install topoteretes/cognee company-brain-company-qa --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/company-brain-company-qa .claude/skills/company-brain-company-qa && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
company-brain-company-qa
GitHub stars
32k
Token cost
~750 tokens
SKILL.md length
374 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

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.

  • Works in 6 steps: Work out the sources. Ask the user for… → Run → Run the same command without --check,… → …
  • Someone wants to connect their companys database
  • SKILL.md covers Steps, Rules and Clean up
  • Calls uv

What it does

Company Brain Company QA is an agent skill from topoteretes/cognee. 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.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support, covering Customer support and SQL. It works with SQL. The repository describes itself as: Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free. The licence is Apache-2.0.

When your agent uses it

  • Someone wants to connect their companys database
  • Tickets and docs
  • Is handling something across them

Example prompts

  • “/company-brain-company-qa”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Work out the sources. Ask the user for the ones they want: a database URL (and tables),
  2. Run
  3. Run the same command without --check, adding the user's question as
  4. The answer is everything after [ask] A:. Give it to the user. The [ingest] lines
  5. Later questions don't need the sources again
  6. If a script fails, company_qa.py exits 1 with a line naming what went wrong. Run

What it can do on your machine

Read from SKILL.md and the folder at commit 0ec7a9f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Company Brain Company QA loads about 750 tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 374 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~750

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:44
    question, and don't print `.env` or a database URL's password.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from topoteretes/cognee at commit 0ec7a9f, republished under its Apache-2.0 licence (© topoteretes). 374 words, ~750 tokens.

Download SKILL.mdSave it as .claude/skills/company-brain-company-qa/SKILL.md (or your agent's skills folder).
name
company-brain-company-qa
description
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.

Company brain: company Q&A

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.

Steps

  1. Work out the sources. Ask the user for the ones they want: a database URL (and tables), one or more ticket export files (JSON or CSV), a docs folder. If they have none, or want to see it work first, pass no sources: the run then uses the sample company (the [setup] line says so). Tell the user the answer comes from sample data.
  2. Run 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.
    • Exit 0: go to step 3.
    • Exit 2: each [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.
  3. Run the same command without --check, adding the user's question as --ask "...". On the sample with no --ask, it asks a question that needs all three sample sources.
  4. The answer is everything after [ask] A:. Give it to the user. The [ingest] lines say which sources went in.
  5. Later questions don't need the sources again: uv run python examples/cookbooks/company_brain/company_qa/scripts/ask.py "...".
  6. If a script fails, 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.
Show full SKILL.md (91 more words)Show less

Rules

  • The sources are the user's company data. Don't quote them beyond what answers the question, and don't print .env or a database URL's password.
  • Every run uses LLM credits, so ingest only when the user asked for it.
  • A sample run forgets the cookbook's dataset 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.
  • Don't pass --ui unless the user asked to browse the graph: it keeps running until Ctrl+C.

Clean up

bash
uv run cognee-cli forget --dataset company_qa

© topoteretes, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/company-brain-company-qa of topoteretes/cognee.

Open the folder on GitHubat commit 0ec7a9f

Compare with similar skills

Company Brain Company QA next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Company Brain Company QA compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Company Brain Company QA this skilltopoteretes/cognee32k—~750Automated safety check: NotesApache-2.0
Debugging ExperimentsPostHog/posthog40k—~5.4kAutomated safety check: PassCustom licence
Sf Datacloud RetrieveJaganpro/sf-skills424—~1.4kAutomated safety check: PassMIT
Triaging Warehouse Sync TicketsPostHog/posthog40k—~6.3kAutomated safety check: WarnCustom licence
Suede RevopsJasonColapietro/suede-creator-skills127—~3.8kAutomated safety check: PassMIT
Database QueryEXboys/evotown647—~425Automated safety check: PassMIT

Similar skills

  • Debugging Experiments

    PostHog/posthog

    Official

    Debug and support PostHog Experiments (A/B tests) for a customer looking at their own results.

    40k GitHub stars~5.4k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Sf Datacloud Retrieve

    Jaganpro/sf-skills

    Salesforce Data Cloud Retrieve phase. An agent skill from Jaganpro/sf-skills.

    424 GitHub stars~1.4k tokensUpdated 5 mo ago
    Sales & SupportAuto-check passed
  • Official

    Debug a customer's data warehouse source, schema, or table from a support ticket, using PostHog's own production data.

    40k GitHub stars~6.3k tokensUpdated yesterday
    DatabasesAuto-check: warnings
  • Suede Revops

    JasonColapietro/suede-creator-skills

    Suede-owned revenue-operations discipline. An agent skill from JasonColapietro/suede-creator-skills.

    127 GitHub stars~3.8k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Database Query

    EXboys/evotown

    通过 Evotown Database MCP Proxy 对已注册的业务数据库执行只读 SQL 查询。当用户需要查 CRM、订单、报表等结构化数据时使用;禁止直连数据库或写入 SQL。

    647 GitHub stars~425 tokensUpdated 27 days ago
    Sales & SupportAuto-check passed
  • Pg Data

    tyrchen/geektime-bootcamp-ai

    Generate safe, read-only PostgreSQL queries from natural language.

    236 GitHub stars~2.8k tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed

More from topoteretes/cognee

All 19 skills in this repo
  • Cognee CLI Memory Commands

    topoteretes/cognee

    Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.

    32k GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check: notes
  • Cognee Community Packages

    topoteretes/cognee

    Guide to using and contributing cognee community packages: database adapters, data-source connectors, custom tasks and retrievers, and Keywords AI observability.

    32k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed
  • Cognee Custom Graph Models

    topoteretes/cognee

    Defines the shape of cognee's knowledge graph with graph_model: DataPoint node classes, identity and index fields, typed edges and fixes for duplicated nodes.

    32k GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check passed
  • Cognee Custom Pipelines

    topoteretes/cognee

    Shows how to write custom cognee tasks, chain them into pipelines, store custom DataPoints and run enrichment over the existing graph.

    32k GitHub stars~2.8k tokensUpdated 2 days ago
    Auto-check passed
  • Cognee Docker Setup

    topoteretes/cognee

    Runs the Cognee AI memory platform in Docker, from a one-file prebuilt image to a full compose stack with UI, MCP server, Postgres and Neo4j.

    32k GitHub stars~901 tokensUpdated 2 days ago
    Auto-check: notes
  • Cognee Forget

    topoteretes/cognee

    Removes data from cognee memory with forget(), finding the right dataset and document first and choosing between one document, a dataset or only the graph and vector memory.

    32k GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Company Brain Company QA

What does Company Brain Company QA do?

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. Company Brain Company QA is an agent skill from topoteretes/cognee. 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.

When should I use Company Brain Company QA?

Company Brain Company QA fits situations like: someone wants to connect their companys database; tickets and docs; is handling something across them.

How do I install Company Brain Company QA in Claude Code?

Run `npx skills add topoteretes/cognee --skill company-brain-company-qa -a claude-code`. Or copy the skill folder (.agents/skills/company-brain-company-qa in topoteretes/cognee) into .claude/skills/company-brain-company-qa in your project. Claude Code loads it when a task matches its description.

How do I install Company Brain Company QA in Codex?

Run `npx skills add topoteretes/cognee --skill company-brain-company-qa -a codex`. Or copy the skill folder (.agents/skills/company-brain-company-qa in topoteretes/cognee) into .agents/skills/company-brain-company-qa in your project. Codex loads it when a task matches its description.

Can I use Company Brain Company QA in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add topoteretes/cognee --skill company-brain-company-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/company-brain-company-qa, .gemini/skills/company-brain-company-qa, .github/skills/company-brain-company-qa and .opencode/skills/company-brain-company-qa in your project.

What does Company Brain Company QA need to run?

Going by SKILL.md and its folder, Company Brain Company QA needs the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Company Brain Company QA access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Company Brain Company QA safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Company Brain Company QA use?

Company Brain Company QA is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Company Brain Company QA use?

About 750 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Company Brain Company QA?

Skills that share tags, products or a category with Company Brain Company QA: Debugging Experiments (PostHog/posthog, 40k stars), Sf Datacloud Retrieve (Jaganpro/sf-skills, 424 stars), Triaging Warehouse Sync Tickets (PostHog/posthog, 40k stars) and Suede Revops (JasonColapietro/suede-creator-skills, 127 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Company Brain Company QA?

topoteretes (a GitHub organization) maintains it in topoteretes/cognee, which has 31,919 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 9, 2026.

Source: topoteretes/cognee on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.