Database Observability
grafana/skills
Set up Grafana Cloud Database Observability for MySQL and PostgreSQL — enables pgstatstatements / Performance Schema, creates a least-privilege monitoring user, configures the…
Monitor robot fleet telemetry via Azure IoT Operations, drift detection, Grafana dashboards, and Fabric analytics
Install Fleet Intelligence
$ npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/physical-ai-toolchain fleet-intelligence --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/microsoft/physical-ai-toolchain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/fleet-intelligence .claude/skills/fleet-intelligence && rm -rf skills-srcUse ~/.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/
Install the "fleet-intelligence" agent skill from https://github.com/microsoft/physical-ai-toolchain/tree/main/.github/skills/fleet-intelligence into .claude/skills/fleet-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-intelligence", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/microsoft/physical-ai-toolchain/tree/main/.github/skills/fleet-intelligenceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/physical-ai-toolchain fleet-intelligence --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/physical-ai-toolchain.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/fleet-intelligence .agents/skills/fleet-intelligence && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fleet-intelligence" agent skill from https://github.com/microsoft/physical-ai-toolchain/tree/main/.github/skills/fleet-intelligence into .agents/skills/fleet-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-intelligence", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/physical-ai-toolchain fleet-intelligence --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/physical-ai-toolchain.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/fleet-intelligence .cursor/skills/fleet-intelligence && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fleet-intelligence" agent skill from https://github.com/microsoft/physical-ai-toolchain/tree/main/.github/skills/fleet-intelligence into .cursor/skills/fleet-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-intelligence", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/microsoft/physical-ai-toolchain.git --path .github/skills/fleet-intelligence--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/physical-ai-toolchain fleet-intelligence --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/physical-ai-toolchain.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/fleet-intelligence .gemini/skills/fleet-intelligence && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fleet-intelligence" agent skill from https://github.com/microsoft/physical-ai-toolchain/tree/main/.github/skills/fleet-intelligence into .gemini/skills/fleet-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-intelligence", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install microsoft/physical-ai-toolchain fleet-intelligenceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/physical-ai-toolchain.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/fleet-intelligence .github/skills/fleet-intelligence && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fleet-intelligence" agent skill from https://github.com/microsoft/physical-ai-toolchain/tree/main/.github/skills/fleet-intelligence into .github/skills/fleet-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-intelligence", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/physical-ai-toolchain fleet-intelligence --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/physical-ai-toolchain.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/fleet-intelligence .opencode/skills/fleet-intelligence && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fleet-intelligence" agent skill from https://github.com/microsoft/physical-ai-toolchain/tree/main/.github/skills/fleet-intelligence into .opencode/skills/fleet-intelligence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-intelligence", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
fleet-intelligence- GitHub stars
- 122
- Token cost
- ~598 tokens
- SKILL.md length
- 170 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Monitor robot fleet telemetry via Azure IoT Operations, drift detection, Grafana dashboards, and Fabric analytics
- Works in 4 steps: Deploy IoT Operations → Deploy telemetry pipeline → Deploy dashboards → …
- Tasks that involve GitOps
- SKILL.md covers Prerequisites, Setup Workflow, Telemetry Schemas and Drift Detection, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Fleet Intelligence is an agent skill from microsoft/physical-ai-toolchain, published by the product's own GitHub organization. Monitor robot fleet telemetry via Azure IoT Operations, drift detection, Grafana dashboards, and Fabric analytics
Its SKILL.md is about 600 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 DevOps & Cloud, covering GitOps and Monitoring and alerting. It works with Microsoft Azure, Grafana and Microsoft Sentinel. The licence is MIT.
When your agent uses it
- Tasks that involve GitOps
- Tasks that involve Monitoring and alerting
Example prompts
- “/fleet-intelligence”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 5d38197. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Fleet Intelligence loads about 598 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 170 words of instructions outside code blocks.
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 passed
The automated check found no risky patterns in SKILL.md.
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 microsoft/physical-ai-toolchain at commit 5d38197, republished under its MIT licence (© microsoft). 170 words, ~598 tokens.
Download SKILL.mdSave it as
.claude/skills/fleet-intelligence/SKILL.md (or your agent's skills folder).- name
- fleet-intelligence
- description
- Monitor robot fleet telemetry via Azure IoT Operations, drift detection, Grafana dashboards, and Fabric analytics
Fleet Intelligence
Monitor and analyze deployed robot fleet telemetry — IoT Operations data collection, Grafana dashboards, drift detection, and Fabric Real-Time Intelligence analytics.
Prerequisites
| Requirement | Purpose |
|---|---|
| Azure IoT Operations | Edge telemetry collection |
| Azure Event Hubs | Cloud telemetry ingestion |
| Grafana | Fleet dashboards and alerting |
| Microsoft Fabric | Real-Time Intelligence KQL analytics |
az CLI | Azure authentication |
kubectl | Cluster access for IoT Operations |
Setup Workflow
Deploy fleet intelligence components in order:
Step 1 — Deploy IoT Operations
fleet-intelligence/setup/deploy-iot-operations.shStep 2 — Deploy telemetry pipeline
fleet-intelligence/setup/deploy-telemetry-pipeline.shStep 3 — Deploy dashboards
fleet-intelligence/setup/deploy-dashboards.shStep 4 — Deploy Fabric Real-Time Intelligence
fleet-intelligence/setup/deploy-fabric-rti.shTelemetry Schemas
| Schema | Path | Description |
|---|---|---|
| Policy Execution | telemetry/schemas/policy-execution.schema.json | Inference metrics and action outputs |
| Robot Health | telemetry/schemas/robot-health.schema.json | Hardware status and connectivity |
Drift Detection
Drift detection monitors deployed policies for performance degradation. When drift exceeds configured thresholds, retraining triggers initiate automated training pipelines.
| Component | Path | Description |
|---|---|---|
| Detection | drift/detection/ | Statistical tests against training baselines |
| Alerting | drift/alerting/ | Threshold evaluation and notification routing |
| Triggers | drift/triggers/ | Automated retraining pipeline launching |
Key Files
| File | Description |
|---|---|
fleet-intelligence/README.md | Domain overview |
fleet-intelligence/telemetry/routing/edge-to-eventhub.yaml | Edge-to-cloud routing config |
fleet-intelligence/dashboards/grafana/fleet-overview.json | Grafana dashboard definition |
fleet-intelligence/dashboards/fabric/fleet-kql-queries.kql | Fabric KQL analytics queries |
© microsoft, MIT. 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 .github/skills/fleet-intelligence of microsoft/physical-ai-toolchain.
Open the folder on GitHubat commit 5d38197
Compare with similar skills
Fleet Intelligence 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fleet Intelligence this skillmicrosoft/physical-ai-toolchain | 122 | — | ~598 | Automated safety check: Pass | MIT | |
| Database Observabilitygrafana/skills | 278 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Infrastructuregrafana/skills | 278 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Mimirgrafana/skills | 278 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| ML AIgrafana/skills | 278 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Private Connectivitygrafana/skills | 278 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Infrastructure
grafana/skills
Ship Kubernetes, host, container, and cloud-provider telemetry into Grafana Cloud — k8s-monitoring Helm chart for K8s clusters (metrics + logs + traces + events + cost), Alloy…
- Official
Mimir
grafana/skills
Stand up Grafana Mimir for horizontally scalable, multi-tenant, long-term Prometheus + OTLP metrics storage.
- Official
ML AI
grafana/skills
Turn on AI + ML features in Grafana Cloud — Grafana Assistant (NL → PromQL/LogQL/TraceQL, dashboard build, incident investigation, MCP integration), Dynamic Alerting (Prophet forecasting + DBSCAN…
- Official
Private Connectivity
grafana/skills
Set up private network connectivity to Grafana Cloud — AWS PrivateLink, Azure Private Link, GCP Private Service Connect, and Private Data Source Connect (PDC).
- Official
Tempo
grafana/skills
Stand up Grafana Tempo as a cost-efficient distributed-tracing backend that only needs object storage, and write TraceQL queries against it.
More from microsoft/physical-ai-toolchain
- Official
Osmo Lerobot Training
microsoft/physical-ai-toolchain
Submit, monitor, analyze, and evaluate LeRobot imitation learning training jobs on OSMO with Azure ML MLflow integration and inference evaluation - Brought to you by microsoft/physical-ai-toolchain
- Official
Azureml K3s Compute Target Setup
microsoft/physical-ai-toolchain
Set up a K3s cluster on an NVIDIA GPU host, connect it to Azure Arc, and configure Azure ML to use it as a Kubernetes compute target.
- Official
Environment Deployment
microsoft/physical-ai-toolchain
Generate, transfer, and consume environment-specific Azure, AKS, OSMO, ACR, and Azure ML deployment bundles.
- Official
Fleet Deployment
microsoft/physical-ai-toolchain
Deploy trained robot policies to edge fleets via FluxCD GitOps, image automation, and deployment gating
- Official
Infrastructure
microsoft/physical-ai-toolchain
Deploy and manage Azure infrastructure for the Physical AI Toolchain including Terraform IaC, Kubernetes setup, GPU configuration, and network topology
- Official
Synthetic Data
microsoft/physical-ai-toolchain
Generate synthetic training data using NVIDIA Cosmos world foundation models for SDG pipelines
Related
Works with
Categories
Questions about Fleet Intelligence
What does Fleet Intelligence do?
Monitor robot fleet telemetry via Azure IoT Operations, drift detection, Grafana dashboards, and Fabric analytics. Fleet Intelligence is an agent skill from microsoft/physical-ai-toolchain, published by the product's own GitHub organization.
When should I use Fleet Intelligence?
Fleet Intelligence fits situations like: tasks that involve GitOps; tasks that involve Monitoring and alerting.
How do I install Fleet Intelligence in Claude Code?
Run `npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a claude-code`. Or copy the skill folder (.github/skills/fleet-intelligence in microsoft/physical-ai-toolchain) into .claude/skills/fleet-intelligence in your project. Claude Code loads it when a task matches its description.
How do I install Fleet Intelligence in Codex?
Run `npx skills add microsoft/physical-ai-toolchain --skill fleet-intelligence -a codex`. Or copy the skill folder (.github/skills/fleet-intelligence in microsoft/physical-ai-toolchain) into .agents/skills/fleet-intelligence in your project. Codex loads it when a task matches its description.
Can I use Fleet Intelligence 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 microsoft/physical-ai-toolchain --skill fleet-intelligence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fleet-intelligence, .gemini/skills/fleet-intelligence, .github/skills/fleet-intelligence and .opencode/skills/fleet-intelligence in your project.
What does Fleet Intelligence need to run?
SKILL.md names no scripts, command-line tools or credentials: Fleet Intelligence is instructions for the agent only.
Does Fleet Intelligence access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Fleet Intelligence safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Fleet Intelligence use?
Fleet Intelligence is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Fleet Intelligence use?
About 598 tokens (SKILL.md is roughly 2.4k 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 Fleet Intelligence?
Skills that share tags, products or a category with Fleet Intelligence: Database Observability (grafana/skills, 278 stars), Infrastructure (grafana/skills, 278 stars), Mimir (grafana/skills, 278 stars) and ML AI (grafana/skills, 278 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Fleet Intelligence?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/physical-ai-toolchain, which has 122 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 6, 2026.
Source: microsoft/physical-ai-toolchain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.