PlugWiki

distributed-tracing Skill (wshobson) for Claude: What It Does and How to Install It

Helps Claude set up Jaeger and Tempo tracing so you can follow a request across microservices and find slow steps.

Installs
11K
on skills.sh
Stars
42.1K
on GitHub
Files
1
besides SKILL.md
Updated
Oct 2026
last repo commit

This skill is a tracing guide for Claude, from wshobson's agents collection. It covers trace and span concepts, Jaeger and Tempo setup, OpenTelemetry for Python (Flask), Node.js (Express) and Go, context propagation, sampling and trace analysis.

SKILL.md holds the purpose, ten best practices, a log-correlation example and troubleshooting for missing traces and high overhead. Worked setups are in references/details.md. It loads when you debug microservice latency, analyze request flows or add observability to a distributed system.

Good for

  • Engineers debugging latency across microservices
  • Teams adding OpenTelemetry to Python, Node.js or Go services
  • Platform teams standing up Jaeger or Tempo
  • Anyone tracing where a request fails

Install distributed-tracing

Claude Code

  1. 1

    Copy this prompt.

    Install the distributed-tracing skill in Claude Code. Run this command:

/plugin marketplace add wshobson/agents
/plugin install observability-monitoring@claude-code-workflows

Then check that it loaded and tell me how to use it.
  2. 2

    Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole observability-monitoring plugin: 4 agents, 2 commands and 4 skills (counted from the plugin folder in the repo tree, which has no hooks or MCP config files). The skills-only routes install just this skill, with no agents or commands. The skill is a guide. The Jaeger and Tempo examples assume a Kubernetes cluster or Docker if you run them.

From the project README. Source.

What's in the skill

When it loads

Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks. Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems.

Sections in SKILL.md

  1. Purpose
  2. When to Use
  3. Detailed patterns and worked examples
  4. Best Practices
  5. Integration with Logging
  6. Correlated Logs
  7. Troubleshooting
  8. Related Skills

Key facts

Author
wshobson (repo owner)
License
MIT
Installs on skills.sh
10,956 (Nov 2, 2026)
GitHub stars
42,081 for the whole wshobson/agents repo (Nov 2, 2026)
Last repo commit
Oct 30, 2026
What it includes
2 files including SKILL.md: references/details.md (no scripts)
Needs
A Jaeger or Tempo backend to send traces to. The examples run it on Kubernetes or with Docker Compose
Part of
The observability-monitoring plugin (version 1.2.4) in wshobson/agents. Counted from the plugin folder: 4 agents, 2 commands and 4 skills
Works in
Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot and Pi, per the README. Skills-only installers ask which tool you use

What it includes

  • Traces, spans, context, tags and logs

    Explains how one request becomes a trace made of spans, with context passed between services (references/details.md).

    Read · Tracing concepts

  • Kubernetes operator and Docker Compose examples

    Shows kubectl commands that install the Jaeger operator and an instance, and a Docker Compose file for the Jaeger all-in-one image.

    Runs code · Jaeger setup

  • OpenTelemetry for Python (Flask), Node.js (Express) and Go

    Example code that creates spans, sets attributes and exports them to Jaeger.

    Write · Instrumentation

  • traceparent headers, inject helpers for Python and Node.js

    Shows how to pass trace context in HTTP requests between services.

    Write · Context propagation

  • Kubernetes ConfigMap and Deployment with S3 storage

    A Grafana Tempo example that accepts Jaeger and OTLP traces and stores them in an S3 bucket.

    Runs code · Tempo setup

  • Probabilistic, rate-limiting and trace-ID-ratio samplers

    Examples for sampling 1% of traces, at most 100 traces per second, or a parent-based ratio.

    Write · Sampling

  • Jaeger queries for slow requests and errors

    Query examples for duration over 1s and for error spans, plus the service dependency graph.

    Read · Trace analysis

  • Ten rules, log correlation, fixes for missing traces

    SKILL.md lists ten best practices, a Python example that adds trace_id to log lines, and checks for missing traces or high overhead.

    Read · Best practices and troubleshooting

From the official docs

Permissions

Medium risk

What it can do

  • Read your data
  • Create and change things
  • Delete things
  • Read-only mode

Watch out for

  • The examples create resources in a Kubernetes cluster

    references/details.md runs kubectl create namespace, kubectl create -f on a Jaeger operator release URL and kubectl apply on a Jaeger manifest. Check your kubectl context and read the manifest before approving. github.com

  • The Tempo example points at an S3 bucket

    The Tempo ConfigMap uses an S3 backend with the bucket name tempo-traces. Replace it with your own bucket before applying. github.com

  • Span tags can carry user identifiers

    SKILL.md suggests tags such as user_id and request_id. Decide which identifiers you want stored in your tracing backend. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details
Turning on read-onlyNo read-only mode. Review commands before they run.
Talks togithub.com (the Jaeger operator manifest in the kubectl example). Whichever Jaeger collector or Tempo endpoint you configure
Sign-in and keysSKILL.md and references/details.md do not mention API keys or accounts. The Tempo example names an S3 bucket.
Scopes

  • Claude can write instrumentation code and config files in your project when you ask

  • The examples in references/details.md include kubectl and Docker Compose commands for Jaeger and Tempo

Questions

What does the distributed-tracing skill do?

It gives Claude a guide to tracing requests across microservices with Jaeger and Tempo. Claude uses it to add OpenTelemetry to services, set up a tracing backend and find slow or failing requests.

How do I install distributed-tracing?

Use the install box at the top of this page. It lists the plugin route and two skills-only commands: npx skills add wshobson/agents --skill distributed-tracing and gh skill install wshobson/agents distributed-tracing (GitHub CLI 2.90 or later), which skip the plugin's agents and commands.

Does it install Jaeger or Tempo for me?

No. Installing the skill adds guidance only. If you ask Claude to deploy a backend, it can follow the kubectl and Docker Compose examples in references/details.md, so check each command and your cluster context first.

Which languages does it cover?

The worked examples are Python with Flask, Node.js with Express and Go. All three use OpenTelemetry.

Is this skill from Anthropic?

No. It is in wshobson/agents, a community collection. The skill sits in the observability-monitoring plugin there.

Should I install the whole observability-monitoring plugin?

Only if you want the rest. The README documents a plugin route for Claude Code and Codex. The plugin folder holds 4 agents, 2 commands and 4 skills (distributed-tracing, grafana-dashboards, prometheus-configuration, slo-implementation), and the repo tree shows no hooks or MCP config files in it. The install box offers the plugin and skills-only commands.

Does it cover metrics and dashboards too?

Not itself. SKILL.md lists prometheus-configuration for metrics, grafana-dashboards for visualization and slo-implementation for latency SLOs as related skills. They are separate skills in the same repo, and this one does not require them.

Does it work in Codex or Cursor?

The README documents Codex CLI as a plugin route and a skills-only install. For Cursor it points to a plugin marketplace and its setup docs, which we did not check, so follow the README there.

Is it safe?

The folder holds SKILL.md and one reference file and bundles no scripts. The reference file contains kubectl commands that create resources in a Kubernetes cluster, so review them before Claude runs any. Keep Claude permission prompts on for shell commands.

Information

updated Nov 2, 2026

Repository
wshobson/agents
Folder
plugins/observability-monitoring/skills/distributed-tracing

wshobson/agentsskills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 4
  1. distributed-tracing SKILL.md · github.com
  2. wshobson/agents README · github.com
  3. observability-monitoring plugin.json · github.com
  4. distributed-tracing details.md · github.com

Updated Nov 2, 2026.