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.

1.29x

Quality

—

Does it follow best practices?

Impact

100%

1.29x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable code and configs across the stack, but it is verbose with concept definitions Claude already knows, lacks validation checkpoints in its setup flow, and signals reference files that are not actually present in the bundle.

Suggestions

Remove or trim the 'Distributed Tracing Concepts' definitions (Trace/Span/Context/Tags/Logs) and the 'Purpose'/'When to Use' restatements — Claude already knows these and they pad the token budget.

Collapse the three full OpenTelemetry instrumentation examples to one canonical example plus a pointer, moving the other languages into references/instrumentation.md.

Create the referenced bundle files (references/jaeger-setup.md, references/instrumentation.md, assets/jaeger-config.yaml.template) so the signaled references resolve, and add a validation checkpoint after Jaeger setup (e.g., confirm traces appear in the Jaeger UI before proceeding).

Dimension	Reasoning	Score
Conciseness	Mostly actionable code and config, but padded with concepts Claude already knows ('Span - Single operation within a trace', the 'Purpose' and 'When to Use' restatements) and three full per-language instrumentation examples that could be tightened to one plus a reference.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance throughout — kubectl/docker-compose manifests, OpenTelemetry instrumentation in Python/Node/Go, propagation snippets, sampling configs, and concrete Jaeger queries.	3 / 3
Workflow Clarity	Content is organized topically as a catalog rather than a sequenced workflow, and the Jaeger/Tempo setup steps lack validation checkpoints (e.g., 'verify traces appear in the UI before instrumenting'), so checkpoints are only implicit.	2 / 3
Progressive Disclosure	References are signaled ('See references/jaeger-setup.md', 'assets/jaeger-config.yaml.template') but those bundle files do not exist, and large blocks that belong in references — full Tempo Kubernetes deployment, all three language examples — are inlined in SKILL.md.	2 / 3
	Total	9 / 12 Passed

Description

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.

A strong, third-person description that names specific tools and concrete actions and pairs them with an explicit, natural-language 'Use when' trigger clause. It cleanly answers what the skill does and when to invoke it with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions with specific tools — 'Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks' — listing multiple specific actions rather than vague language.	3 / 3
Completeness	Clearly answers both what (implement tracing, track requests, identify bottlenecks) and when via an explicit 'Use when...' clause, satisfying both halves.	3 / 3
Trigger Term Quality	The 'Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems' clause covers natural phrases a user would actually say, with good breadth of variations.	3 / 3
Distinctiveness Conflict Risk	The Jaeger/Tempo distributed-tracing niche with microservice-debugging triggers is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: e9f9b67

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.