distributed-tracing
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.
Install with Tessl CLI
npx tessl i github:Dicklesworthstone/pi_agent_rust --skill distributed-tracing91
Quality
86%
Does it follow best practices?
Impact
100%
1.29xAverage score across 3 eval scenarios
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels across all dimensions. It uses third person voice, lists specific tools and actions, includes natural trigger terms that users would actually say, and has an explicit 'Use when...' clause with clear trigger scenarios. The specificity of naming Jaeger and Tempo creates strong distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'implement distributed tracing', 'track requests across microservices', 'identify performance bottlenecks'. Names specific tools (Jaeger, Tempo) and concrete use cases. | 3 / 3 |
Completeness | Clearly answers both what ('implement distributed tracing with Jaeger and Tempo to track requests and identify bottlenecks') and when ('Use when debugging microservices, analyzing request flows, or implementing observability'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'distributed tracing', 'Jaeger', 'Tempo', 'microservices', 'request flows', 'observability', 'performance bottlenecks', 'debugging'. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on distributed tracing with specific tools (Jaeger, Tempo). The combination of tracing, microservices, and named observability tools creates distinct triggers unlikely to conflict with general debugging or monitoring skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive distributed tracing skill with excellent actionability through complete, executable code examples across multiple languages and deployment configurations. The main weaknesses are unnecessary conceptual explanations that Claude already knows and missing validation checkpoints in the setup workflows. The progressive disclosure and organization are well done with appropriate external references.
Suggestions
Remove the 'Distributed Tracing Concepts' section entirely - Claude understands traces, spans, and context propagation without explanation
Add validation steps after deployments, e.g., 'Verify Jaeger is running: kubectl get pods -n observability | grep jaeger' and 'Access UI at http://localhost:16686 to confirm traces are appearing'
Trim the 'Best Practices' list to only non-obvious items - items like 'propagate context across all service boundaries' are implicit in the instrumentation examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations (e.g., the 'Distributed Tracing Concepts' section explains basic concepts Claude already knows like what traces and spans are). The content is generally useful but could be tightened by removing conceptual explanations and focusing purely on implementation. | 2 / 3 |
Actionability | Provides fully executable code examples across multiple languages (Python, Node.js, Go), complete Kubernetes manifests, Docker Compose configurations, and specific query examples. All code is copy-paste ready with proper imports and configuration. | 3 / 3 |
Workflow Clarity | While setup steps are provided, there are no explicit validation checkpoints or feedback loops. For example, after deploying Jaeger, there's no 'verify deployment succeeded' step. The troubleshooting section exists but isn't integrated into the workflow as validation steps. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate references to external files (references/jaeger-setup.md, references/instrumentation.md, assets/jaeger-config.yaml.template), and related skills linked at the end. Content is organized logically from setup to instrumentation to analysis. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.