opentelemetry-instrumentation
Instruments Java, Python, Node.js, .NET, and Go applications with OpenTelemetry SDKs to send traces, metrics, and logs to Coralogix. Use for SDK-side OTel setup, OTLP exporter env vars, Coralogix resource attributes, APM transaction samplers, Kubernetes Operator injection, or debugging missing traces, metrics, logs, or no telemetry from an application. Not for OTel Collector config (use opentelemetry-collector), OTTL authoring (use opentelemetry-ottl), eBPF instrumentation, or Lambda layers.
89
85%
Does it follow best practices?
Impact
100%
1.85xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 an excellent skill description that excels across all dimensions. It provides highly specific capabilities, rich natural trigger terms spanning multiple languages and technologies, explicit 'use for' and 'not for' guidance, and clear boundary delineation with related skills. It serves as a strong example of how to write a skill description for a technical domain with adjacent/overlapping tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: instrumenting applications with OpenTelemetry SDKs, sending traces/metrics/logs, SDK-side OTel setup, OTLP exporter env vars, Coralogix resource attributes, APM transaction samplers, Kubernetes Operator injection, and debugging missing telemetry. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (instruments applications with OpenTelemetry SDKs to send telemetry to Coralogix) and 'when' ('Use for SDK-side OTel setup, OTLP exporter env vars...'). Also explicitly states when NOT to use it with references to alternative skills, which further strengthens the 'when' guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: specific languages (Java, Python, Node.js, .NET, Go), 'OpenTelemetry', 'OTel', 'OTLP', 'traces', 'metrics', 'logs', 'Coralogix', 'missing traces', 'no telemetry', 'Kubernetes Operator injection', 'APM'. These are terms practitioners naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive — explicitly carves out its niche by naming what it does NOT cover (OTel Collector config, OTTL authoring, eBPF, Lambda layers) and even points to the correct alternative skills. This makes conflict with related skills extremely unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured routing/orchestration skill that excels at workflow clarity and progressive disclosure — it clearly tells Claude which reference files to load and in what order for different scenarios. Its main weakness is the lack of any inline executable code examples; all concrete implementation is deferred to reference files. There is moderate redundancy between sections that could be tightened to improve token efficiency.
Suggestions
Add at least one minimal executable code example inline (e.g., a complete env var export block for one language) so the skill has actionable content even without loading reference files.
Consolidate the endpoint format rules — the per-language URI scheme requirements appear in both 'Auth, endpoint, and required attributes' and 'High-Signal Answer Rules'; merge into one authoritative location and reference it from the other.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the endpoint format rules for each language are repeated in both 'Auth, endpoint, and required attributes' and 'High-Signal Answer Rules'. The 'When to Use This Skill' table and 'Progressive Loading Rule' section also overlap significantly. Some explanatory text (e.g., describing what APM features degrade) could be tightened. | 2 / 3 |
Actionability | The skill provides specific env var names, endpoint URL patterns, and resource attribute requirements, which is concrete guidance. However, it contains no executable code examples — no copy-paste-ready snippets for any language. All actual code is deferred to reference files that aren't provided. The 'High-Signal Answer Rules' are meta-instructions about what to include in answers rather than directly executable guidance. | 2 / 3 |
Workflow Clarity | The workflow section clearly sequences three distinct paths (new setup, code review, debugging) with explicit file-loading order. The 'Progressive Loading Rule' provides a numbered sequence. Validation paths are explicitly stated (Traces → Explore → Tracing, Metrics → Grafana, Logs → Logs). The skill includes clear scope boundaries and escalation rules for out-of-scope requests. | 3 / 3 |
Progressive Disclosure | The skill is an excellent overview/router that clearly signals one-level-deep references to language-specific files, endpoint config, troubleshooting, and output templates. The 'When to Use This Skill' table and 'Progressive Loading Rule' make navigation intuitive. References are well-organized and clearly named. However, no bundle files were provided to verify the referenced files exist, so scoring based on the structure as designed. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- Repository
- coralogix/cx-skills
- Commit
6b2e359
- 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.