check-integration — Claude Code skill: setup check
Checks Nowledge Mem, identifies the active agent, and points to the right connector path. Use it when memory tools fail or setup needs repair.
npx skills add nowledge-co/community --skill check-integration -a claude-codeWhat check-integration does
The skill runs nmem --json status to test whether Nowledge Mem can be reached. It separates a local desktop setup from a remote machine, then guides the matching CLI path. For a remote setup, it can direct the user to install nmem-cli, configure the server URL and API key, and run the status check again.
It also identifies the agent in use and ranks the available connection paths: a native connector, Universal Agent Plugin, direct MCP, or a reusable skill package. The result includes the behavior to expect after setup, such as automatic startup, model-guided memory actions, and thread capture. Remote standalone CLI setup requires Python 3.11+.
What it helps with
- verify that Nowledge Mem is reachable
- diagnose failing memory tools
- identify the current AI agent
- choose a connector path
- configure a Mem server URL and API key
Example prompts for the agent
- Check whether Nowledge Mem is working and explain the result of
nmem --json status. - Detect the agent I am using and recommend the best Nowledge Mem connector.
- Inspect the memory setup and help repair it if the tools are unavailable.
How to install check-integration
1Skills CLI (Vercel)
npx skills add nowledge-co/community --skill check-integration -a claude-code2Manually: put the files in place
~/.claude/skills/check-integration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/check-integration/
1Skills CLI (Vercel)
npx skills add nowledge-co/community --skill check-integration -a codex2Manually: put the files in place
.agents/skills/check-integration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add nowledge-co/community --skill check-integration -a cursor2Manually: put the files in place
.cursor/skills/check-integration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install nowledge-co/community check-integration2Manually: put the files in place
.github/skills/check-integration/SKILL.md1Skills CLI (Vercel)
npx skills add nowledge-co/community --skill check-integration -a gemini-cli2Platform CLI
gemini skills install https://github.com/nowledge-co/community --path nowledge-mem-agent-plugin/skills/check-integrationManually: put the files in place
.devin/skills/check-integration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add nowledge-co/community --skill check-integration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about check-integration
How do I install check-integration in Claude Code?
Run npx skills add nowledge-co/community --skill check-integration -a claude-code, then check ~/.claude/skills/check-integration/SKILL.md.
What does check-integration do?
It checks Nowledge Mem, detects the active agent, and guides the appropriate connector setup. It also explains what memory behavior to expect after installation.
What is required for a remote Nowledge Mem setup?
A remote setup uses the standalone nmem-cli package, Python 3.11+, a Mem server URL, and an API key. The skill then reruns the status check.