
Qdrant monitoring
Guides setting up and debugging Qdrant monitoring with metrics, probes and alerts
- Scripts
- None
- Platforms
- Claude Code, Codex, Cursor
- GitHub stars
- 41.3K
- Last commit
- today
- License
- MIT
- Listing updated
- 1 day ago
Similar skills
About Qdrant monitoring
Qdrant monitoring is an open-source agent skill for knowledge and memory. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.
This skill helps an agent work through Qdrant observability, starting by deciding whether the user needs to set up monitoring for a deployment or diagnose a live problem. It points to the Qdrant monitoring documentation for the available metrics and routes the agent to two linked guides: one covering Prometheus scraping, health probes, Hybrid Cloud specifics, alerting and log centralization, and another covering diagnosis of issues such as a stuck optimizer, growing memory and slow requests using metric analysis.
The skill is instruction-only. It ships a single SKILL.md with no scripts, and it is limited to reading and searching files with Read, Grep and Glob, so it guides analysis rather than querying a live cluster. Expect to supply your deployment context and access to the relevant metrics or configuration files for the agent to reason over.
When your agent uses it
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', or needs to set up Prometheus, Grafana, or health checks. Also use when debugging production issues that require metric analysis.
From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.
What it can access
- Instructions only, no scripts(see the files on GitHub)
- Asks for: Read, Grep, Glob(see the files on GitHub)
- License: MIT(see the files on GitHub)
From a static check of its 1 file (1 KB) on GitHub on 19 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.
Check another skill before you install it.
Install
Copy the skill folder to ~/.claude/skills/qdrant-monitoring to use it in all your projects:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/qdrant-monitoring &&
cp -R "$tmp/skills/qdrant-monitoring" ~/.claude/skills/qdrant-monitoring &&
rm -rf "$tmp"For one project only, put the folder in .claude/skills/qdrant-monitoring inside it instead.
Copy the skill folder to ~/.agents/skills/qdrant-monitoring to use it in every repository:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/qdrant-monitoring &&
cp -R "$tmp/skills/qdrant-monitoring" ~/.agents/skills/qdrant-monitoring &&
rm -rf "$tmp"For one repository only, put the folder in .agents/skills/qdrant-monitoring inside it instead.
Copy the skill folder to ~/.cursor/skills/qdrant-monitoring to use it in every project:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/qdrant-monitoring &&
cp -R "$tmp/skills/qdrant-monitoring" ~/.cursor/skills/qdrant-monitoring &&
rm -rf "$tmp"For one project only, put the folder in .cursor/skills/qdrant-monitoring inside it instead.
Run in a terminal (add --scope workspace to install it for the current workspace only):
gemini skills install https://github.com/github/awesome-copilot.git --path skills/qdrant-monitoringOr copy the folder to ~/.gemini/skills/qdrant-monitoring yourself.
For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/qdrant-monitoring:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/qdrant-monitoring &&
cp -R "$tmp/skills/qdrant-monitoring" ~/.copilot/skills/qdrant-monitoring &&
rm -rf "$tmp"For one project only, put the folder in .github/skills/qdrant-monitoring inside it instead.
Get the folder:
git clone --depth 1 https://github.com/github/awesome-copilot.gitThen copy awesome-copilot/skills/qdrant-monitoring into your agent's skills folder as qdrant-monitoring. Agents that support SKILL.md read one folder per skill.
What it does
- Monitoring setup guidance
- Covers Prometheus scraping, health probes, and alerting for a Qdrant deployment.
- Hybrid Cloud considerations
- Includes setup notes specific to Qdrant Hybrid Cloud deployments.
- Log centralization
- Points to guidance on collecting Qdrant logs in a central place.
- Metric-driven debugging
- Uses metric analysis to investigate active production problems.
- Optimizer and memory diagnosis
- Covers troubleshooting a stuck optimizer and growing memory use.
- Slow request investigation
- Guides finding the cause of slow Qdrant requests through metrics.
Good for
- Set up Prometheus scraping for a Qdrant cluster
- Check whether a Qdrant instance is healthy
- Find out why Qdrant memory keeps growing
- Investigate why the Qdrant optimizer appears stuck
- Work out why Qdrant requests have become slow
Qdrant monitoring FAQ
What does this skill need to run?
It uses only Read, Grep and Glob tools and includes no scripts, so it works by reading files and reasoning over the content you provide.
When does the agent use it?
It triggers on requests about monitoring Qdrant, choosing metrics, checking health, setting up Prometheus, Grafana or health checks, and debugging production issues that need metric analysis.
Does it change anything in my system?
The skill's allowed tools are read-only (Read, Grep, Glob), so it does not declare any tools that write or modify files.
How do I install Qdrant monitoring in Claude Code?
Copy the skill folder from GitHub to ~/.claude/skills/qdrant-monitoring to use it in all your projects, or to .claude/skills/qdrant-monitoring in one project.
Does Qdrant monitoring run scripts?
No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.
Which AI agents can use Qdrant monitoring?
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.
What are the best alternatives to Qdrant monitoring?
The closest alternatives to Qdrant monitoring are Qdrant monitoring setup, Qdrant monitoring debugging, Qdrant scaling data volume, Qdrant search speed optimization and Qdrant performance optimization.
Where this comes from
- Description: from the skill's own SKILL.md.
More from github/awesome-copilot

A DevOps checklist for deploys, Docker, Kubernetes, CI/CD, rollback and mobile releases
- Open source
- 41.3K GitHub stars
- Cloud and infrastructure

Guides Qdrant scaling when data outgrows a node: tenants, time windows or sharding
- Open source
- 41.3K GitHub stars
- Knowledge and memory

Explains Qdrant's per-shard query subsampling for large limits across many auto-shards
- Open source
- 41.3K GitHub stars
- Knowledge and memory

Creates, exports and appends to Arize evaluation datasets using the ax command line
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling

Creates Arize LLM-as-judge evaluators and runs them on traces or experiment results
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling

Runs a model over an Arize dataset, saves the results as an experiment and compares runs
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling



