qdrant-monitoring · qdrant — Claude Code skill: Qdrant observability setup
A skill that routes Qdrant monitoring questions to the right guidance file, whether you are wiring up Prometheus or chasing a stuck optimizer.
npx skills add qdrant/skills --skill qdrant-monitoring -a claude-codeWhat qdrant-monitoring does
The skill is a router, not a configurator. It matches your symptom against a table and sends the agent to read one file: setup/SKILL.md for Prometheus, Grafana, alerting, log centralization and Hybrid Cloud metrics, or debugging/SKILL.md for a stuck optimizer, growing memory, slow requests and health checks. Two matching rows mean both files get read.
It never touches your cluster. The allowed tools are Read, Grep and Glob, so answers come from the skill's own files instead of the model guessing at Qdrant internals. That matters when you are debugging production and a wrong guess costs you time.
Before tuning anything, the skill points you at the metric reference — sensible, because picking metrics blind is how you end up adjusting the wrong knob. Install for Claude with npx skills add qdrant/skills --skill qdrant-monitoring -a claude-code; the file lands at ~/.claude/skills/qdrant-monitoring/SKILL.md.
What it helps with
- set up Prometheus and Grafana for Qdrant
- pick which metrics are worth tracking
- figure out why the optimizer is stuck
- trace growing memory in production
- wire up alerts and log centralization
Example prompts for the agent
- How do I monitor Qdrant?
- The optimizer is stuck and never finishes — what should I check?
- Qdrant memory keeps growing, help me debug it
How to install qdrant-monitoring
1Skills CLI (Vercel)
npx skills add qdrant/skills --skill qdrant-monitoring -a claude-code2Manually: put the files in place
~/.claude/skills/qdrant-monitoring/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/qdrant-monitoring/
1Skills CLI (Vercel)
npx skills add qdrant/skills --skill qdrant-monitoring -a codex2Manually: put the files in place
.agents/skills/qdrant-monitoring/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add qdrant/skills --skill qdrant-monitoring -a cursor2Manually: put the files in place
.cursor/skills/qdrant-monitoring/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install qdrant/skills qdrant-monitoring2Manually: put the files in place
.github/skills/qdrant-monitoring/SKILL.md1Skills CLI (Vercel)
npx skills add qdrant/skills --skill qdrant-monitoring -a gemini-cli2Platform CLI
gemini skills install https://github.com/qdrant/skills --path skills/qdrant-monitoringManually: put the files in place
.devin/skills/qdrant-monitoring/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add qdrant/skills --skill qdrant-monitoring -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 qdrant-monitoring
How do I install qdrant-monitoring in Claude?
Run npx skills add qdrant/skills --skill qdrant-monitoring -a claude-code. The skill ends up at ~/.claude/skills/qdrant-monitoring/SKILL.md.
What does qdrant-monitoring do?
It maps your symptom — setup or debugging — to the matching skill file and answers from that file. It also links to the Qdrant metric reference.
Which tools can the skill use?
Only Read, Grep and Glob. It reads skill and project files; it does not run commands or change your configuration.
Source text
SKILL.md · Apache-2.0
--- name: qdrant-monitoring description: "Guides Qdrant monitoring and observability setup. Use when someone asks 'how to monitor Qdrant', 'what metrics to track', 'is Qdrant healthy', 'optimizer stuck', 'why is memory growing', 'requests are slow', 'set up alerts', 'cluster health check', or needs to set up Prometheus, Grafana, health checks, or log centralization. Also use when debugging production issues that require metric analysis." allowed-tools: - Read - Grep - Glob --- # Qdrant Monitoring Route first, then answer. Match the user's symptom in the table, `Read` that file, and answer from it. Do not answer from this page alone: it contains routing only, not the guidance. If two rows match, read both. | The user says | Read | |---|---| | Want to set up Prometheus, Grafana, or health checks | `setup/SKILL.md` | | Need to know which metrics to track | `setup/SKILL.md` | | Setting up alerting, log centralization, or Hybrid Cloud metrics | `setup/SKILL.md` | | Optimizer stuck or running forever | `debugging/SKILL.md` | | Memory keeps growing in production | `debugging/SKILL.md` | | Requests are slow and I need to find out why | `debugging/SKILL.md` | | Is Qdrant healthy right now | `debugging/SKILL.md` | Qdrant monitoring tracks performance and health, and catches issues before they become outages. See the metric reference before tuning anything: [Monitoring docs](https://skills.qdrant.tech/md/documentation/ops-monitoring/monitoring/)
© qdrant · Apache-2.0 · qdrant/skills
Similar skills
Everything for DevOps and infrastructure →qdrant-monitoring by other authors comes first.
