otel-semantic-conventions
OpenTelemetry Semantic Conventions expert. Use when selecting, applying, or reviewing telemetry attributes. Triggers on tasks involving attribute selection, semantic convention compliance, attribute migration, or custom attribute decisions. Covers the attribute registry, naming patterns, attribute placement, and versioning. For span names, span kinds, and span status codes, see the otel-instrumentation skill.
99
100%
Does it follow best practices?
Impact
98%
1.22xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 clearly defines its scope within the OpenTelemetry domain, lists concrete actions and coverage areas, provides explicit trigger conditions, and even draws a clear boundary with a related skill to minimize conflict. It uses proper third-person voice throughout and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: selecting, applying, reviewing telemetry attributes, attribute migration, custom attribute decisions. Also specifies concrete domains covered: attribute registry, naming patterns, attribute placement, and versioning. | 3 / 3 |
Completeness | Clearly answers both 'what' (selecting, applying, reviewing telemetry attributes; covers registry, naming patterns, placement, versioning) and 'when' ('Use when selecting, applying, or reviewing telemetry attributes. Triggers on tasks involving attribute selection, semantic convention compliance, attribute migration, or custom attribute decisions.'). Also includes explicit boundary guidance pointing to a related skill. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'telemetry attributes', 'semantic convention', 'attribute migration', 'attribute registry', 'naming patterns', 'versioning', 'OpenTelemetry'. These are terms practitioners naturally use when working in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in OpenTelemetry semantic conventions and attributes. Explicitly delineates its boundary from the related 'otel-instrumentation' skill by noting that span names, span kinds, and span status codes belong elsewhere, reducing conflict risk. | 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 a high-quality skill that efficiently covers OpenTelemetry semantic conventions with concrete examples, clear decision workflows, and well-structured progressive disclosure. It respects Claude's intelligence by avoiding explanations of basic concepts while providing precise, actionable guidance for attribute selection, placement, and validation. The content is well-organized with appropriate separation between the overview and detailed rule files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude understands OpenTelemetry concepts without explaining what telemetry or attributes are. Every section serves a clear purpose — the rules table, selection steps, and examples all earn their place without padding. | 3 / 3 |
Actionability | Provides concrete, executable code examples for correct vs incorrect attribute selection, resource vs span placement, and cardinality violations. The 5-step selection process gives specific, actionable guidance with clear decision criteria rather than vague descriptions. | 3 / 3 |
Workflow Clarity | The 'How to select the right attribute' section provides a clear 5-step sequential workflow for attribute selection decisions. For this type of skill (decision-making guidance rather than destructive operations), the sequence is well-ordered with clear decision points at each step. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, a well-organized rules table pointing to one-level-deep rule files (attributes.md, versioning.md, dash0.md), clear external documentation links, and inline examples for quick reference. Navigation is intuitive and references are clearly signaled. | 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.
- Repository
- dash0hq/agent-skills
- Commit
e73252a
- 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.