← Explore all skills

OBSERVABILITY / Grafana Labs

Grafana Tempo

Local and Helm setup notes plus TraceQL for a Tempo tracing backend.

“Stand up Grafana Tempo as a cost-efficient distributed-tracing backend that only needs object storage, and write TraceQL queries against it. Covers OTLP + Jaeger + Zipkin ingestion, the distributor → live-store → block-builder → object-storage write path, metrics-generator for RED spanmetrics + service graphs, Helm tempo-distributed deployment, multi-tenant X-Scope-OrgID, TraceQL span / resource / event scopes, structural operators (>>, <<), rate() + quantile_over_time metrics, and the traces-to-logs / metrics / profiles datasource links. …”

01 / THE REASONING

Why this made the selection.

  • The file separates a localhost Docker Compose check from a Helm install and names the object-storage bucket as configuration, not as a secret in the command.
  • It is the tracing sibling of the already listed Grafana PromQL and k6 skills, at the same repository revision.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • skills/grafana-lgtm/tempo/SKILL.md (frontmatter, local workflow and Helm example)
  • README.md installation section and the grafana-lgtm skill table
  • LICENSE Apache-2.0 grant, copyright 2026 Grafana Labs
  • skills/grafana-lgtm/tempo/SKILL.md
  • README.md
  • LICENSE

Our findings

  • Local verification uses localhost:3200 and localhost:4318.
  • The Helm example adds grafana.github.io/helm-charts and sets a bucket name. It does not embed cloud credentials.
  • The troubleshooting instructions require the writer and Grafana datasource to use matching X-Scope-OrgID values when traces are missing from Explore.

Not established by this review

  • The installer was not run, and the skill was not executed against a project.
  • Referenced companion files, sibling skills and external service calls were not exhaustively executed.
  • Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Add a skill to your workflow.

Upstream setup instructions ↗

DOCUMENTED COMMAND

npx skills add grafana/skills --skill tempo

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

  1. The README documents npx skills add grafana/skills --skill <name>. The table names this skill tempo.
  2. That command does not pin revision 1ccacf29049fde66637fe01ab93a83a772da323b. Inspect the installed SKILL.md against that revision before use.
  3. Do not run the docker compose or helm install examples against a shared cluster without a separate authorisation.

Before you start

  • Node.js and npm for the documented Skills installer
  • Docker or a Kubernetes cluster only if you run the setup examples

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. Skill definition ↗Checked

    https://github.com/grafana/skills/blob/1ccacf29049fde66637fe01ab93a83a772da323b/skills/grafana-lgtm/tempo/SKILL.md

    Supports: summary, upstreamDescription, whySelected, limitations, access, review

  2. https://github.com/grafana/skills/blob/1ccacf29049fde66637fe01ab93a83a772da323b/README.md

    Supports: install, compatibility

  3. Repository licence ↗Checked

    https://github.com/grafana/skills/blob/1ccacf29049fde66637fe01ab93a83a772da323b/LICENSE

    Supports: license

  4. https://raw.githubusercontent.com/grafana/skills/1ccacf29049fde66637fe01ab93a83a772da323b/skills/grafana-lgtm/tempo/SKILL.md

    Supports: review.findings, bestFor

Evidence & Ask