Observe Trace
Skill ActiveTrace agent execution by collecting spans and building a trace tree for a task
To provide deep visibility into how tasks are executed across agents by collecting, structuring, and analyzing trace spans.
Features
- Collects agent execution spans
- Builds a parent-child trace tree hierarchy
- Calculates span durations and identifies critical paths
- Flags spans exceeding performance thresholds
- Synthesizes trace data into a narrative summary
Use Cases
- Understanding agent coordination across distributed tasks
- Identifying performance bottlenecks in agent workflows
- Debugging complex multi-agent execution flows
- Visualizing the timing and sequence of agent operations
Non-Goals
- Performing live debugging of agent code
- Modifying agent behavior based on trace data
- Real-time performance monitoring beyond a single task trace
Documentation
- info:Configuration & parameter referenceWhile the skill outlines steps and mentions tools, it does not explicitly document parameters or defaults for the tools it invokes, relying on the underlying tool documentation.
Versioning
- warning:Release ManagementThe `SKILL.md` frontmatter does not contain a version number, and installation instructions in the README reference `main`, making version pinning difficult.
Install
- warning:Installation instructionThe README provides installation instructions for Ruflo as a whole, but the specific installation for this individual `observe-trace` skill within Claude Code is not explicitly detailed, only implied through the marketplace/plugin commands.
Errors
- info:Actionable error messagesThe skill outlines steps but does not detail specific error handling for each step, assuming the underlying tools or Claude Code will provide messages.
Practical Utility
- info:Usage examplesWhile the skill outlines steps and mentions CLI alternatives, it does not provide explicit end-to-end runnable examples for the Claude Code plugin environment.
- info:Edge casesThe skill mentions routing conventions for tools but does not explicitly detail failure modes, symptoms, or recovery steps for edge cases like missing spans or tool errors.
Safety
- info:Halt on unexpected stateThe skill implies halting if spans are not found or tools fail, but does not explicitly list preconditions or describe recovery steps for unexpected states.
Installation
First, add the marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-observability@rufloQuality Score
Trust Signals
Similar Extensions
LangSmith Observability
99LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Use My Browser
100Use when work depends on the user's live browser session or visible rendered state rather than static fetches, especially for browser debugging contexts or DevTools-selected elements or requests, logged-in dashboards or CMS flows, localhost apps, forms, uploads, downloads, media inspection, DOM or iframe inspection, Shadow DOM, or browser failures that look like soft 404s, auth walls, anti-bot checks, or rate limits.
Ctx Doctor
100Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor
Instrument Distributed Tracing
99Instrument applications with OpenTelemetry for distributed tracing, including auto and manual instrumentation, context propagation, sampling strategies, and integration with Jaeger or Tempo. Use when debugging latency issues in distributed systems, understanding request flow across microservices, correlating traces with logs and metrics for root cause analysis, measuring end-to-end latency, or migrating from legacy tracing systems to OpenTelemetry.
Service Mesh Observability
98Implement comprehensive observability for service meshes including distributed tracing, metrics, and visualization. Use when setting up mesh monitoring, debugging latency issues, or implementing SLOs for service communication.
Node Connect
100Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.