o11y-dev/opentelemetry-skill
Expert OpenTelemetry guidance for collector configuration, pipeline design, and production telemetry instrumentation. Use when configuring collectors, designing pipelines, instrumenting applications, implementing sampling, managing cardinality, securing telemetry, writing OTTL transformations, or setting up AI coding agent observability (Claude Code, Codex, Gemini CLI, GitHub Copilot).
99
100%
Does it follow best practices?
Impact
98%
8.16xAverage score across 4 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 a strong skill description that clearly defines its domain (OpenTelemetry), lists specific concrete capabilities, and provides an explicit 'Use when...' clause with comprehensive trigger terms. It uses proper third-person voice and covers both general OTel use cases and a distinctive niche (AI coding agent observability). The description is concise yet thorough, making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: collector configuration, pipeline design, instrumentation, sampling, cardinality management, securing telemetry, OTTL transformations, and AI coding agent observability. These are all distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (expert OpenTelemetry guidance for collector configuration, pipeline design, and production telemetry instrumentation) and 'when' with an explicit 'Use when...' clause listing eight specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'OpenTelemetry', 'collector', 'pipeline', 'instrumentation', 'sampling', 'cardinality', 'OTTL', and specific AI agent names (Claude Code, Codex, Gemini CLI, GitHub Copilot). These are terms practitioners naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in OpenTelemetry specifically. The combination of OTel-specific terminology (OTTL, collector, pipeline, cardinality) and the AI coding agent observability angle makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-crafted skill that demonstrates expert-level understanding of both OpenTelemetry and effective skill authoring. It balances comprehensive coverage with token efficiency through its trigger-based progressive disclosure system, provides fully executable configurations and commands, and includes robust validation workflows with error recovery tables. The pre-flight checklist and eval-critical response minimums ensure Claude handles common scenarios correctly without needing to load reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is dense and efficient. Every section earns its place — core principles are terse bullet points, the baseline config includes only essential comments, and the trigger table avoids verbose explanations. It assumes Claude's competence throughout (no explaining what OTLP or gRPC are). | 3 / 3 |
Actionability | The skill provides a complete, copy-paste-ready production baseline YAML config, executable validation commands (both local and container-based), live verification commands, and a concrete error recovery table with specific fixes. The pre-flight checklist and eval-critical response minimums give precise, actionable guidance for specific scenarios. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced: validate before deploying (with two methods), verify live pipelines (health check → logs → metrics), and error recovery with symptom-cause-fix mapping. The existing config review mode provides a systematic 9-point audit checklist. Validation checkpoints are explicit and feedback loops are present (e.g., OTTL error recovery guidance). | 3 / 3 |
Progressive Disclosure | The skill uses an explicit trigger-based progressive disclosure table mapping keywords to 12 reference files, keeping the main SKILL.md as a routing overview with guardrails and defaults. References are one level deep and clearly signaled. The content is well-structured with distinct sections (principles, pre-flight, config review, baseline, validation, anti-patterns). | 3 / 3 |
Total | 12 / 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