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

70%

Does it follow best practices?

Impact

100%

1.29x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/observability-monitoring/skills/distributed-tracing/SKILL.md

The canonical home for this skill is distributed-tracing in wshobson/agents

Quality

Content

57%Weight 40%Scale 1-5

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

A content-rich, highly actionable skill body that suffers from verbosity and weak progressive disclosure: it inlines large amounts of code that belong in (non-existent) reference files and lacks an explicit validated workflow for its k8s deployment steps.

Suggestions

Move the full Kubernetes/Docker manifests and per-language instrumentation code into the referenced files (references/jaeger-setup.md, references/instrumentation.md, assets/jaeger-config.yaml.template) and actually create those files, keeping SKILL.md as a concise overview.

Add an explicit step-by-step workflow with validation checkpoints (e.g. deploy Jaeger → verify UI at :16686 → instrument → confirm traces appear) rather than only topical sections.

Trim the "Distributed Tracing Concepts" section that explains Trace/Span/Tags/Logs Claude already knows, and remove the redundant restatement of the description as the opening line.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable code, but the "Distributed Tracing Concepts" section over-explains Trace/Span/Context/Tags/Logs that Claude already knows, and ~450 lines of inline content across three languages plus full manifests could be tightened or split out.	3 / 5
Actionability	Provides concrete, copy-paste-ready code for kubectl/k8s, Docker Compose, and Python/Node/Go instrumentation plus propagation, sampling, and Jaeger queries, with only minor gaps (e.g. the Node.js handler references `trace` without importing it).	4 / 5
Workflow Clarity	Content is organized topically (setup → instrument → propagate → sample → analyze) but lacks an explicit sequenced workflow, and the k8s deployment batch operations have no validation checkpoints, capping this at 3 per the destructive/batch guideline.	3 / 5
Progressive Disclosure	References are clearly signaled one level deep ("Reference: See references/jaeger-setup.md" plus a Reference Files section), but those referenced files do not exist and bulk content (full manifests, three-language instrumentation) is inlined rather than split out.	3 / 5
	Total	13 / 20 Passed

Description

83%Weight 40%Scale 1-5

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, well-structured description that clearly conveys both capabilities and trigger conditions in concise third-person voice. Minor improvements possible by expanding the action list and adding a few more natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks") but does not enumerate the full breadth (setup, instrumentation, sampling, analysis), leaving minor coverage gaps.	4 / 5
Completeness	It explicitly states both what it does ("Implement distributed tracing ... track requests ... identify performance bottlenecks") and when to use it ("Use when debugging microservices, analyzing request flows, or implementing observability") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like "debugging microservices", "analyzing request flows", and "implementing observability" are present, with good coverage though a few common variants (e.g. "tracing", "Jaeger", "Tempo" as standalone trigger words) are absent from the when-clause.	4 / 5
Distinctiveness Conflict Risk	The Jaeger/Tempo and request-tracing niche is clearly distinct with minimal conflict risk, though "implementing observability for distributed systems" is broad enough to overlap slightly with metrics/logging skills.	4 / 5
	Total	17 / 20 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
Path: tests/ext_conformance/artifacts/agents-wshobson/observability-monitoring/skills/distributed-tracing/SKILL.md
Commit: 6453c0b

Reviewed: about 9 hours 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.