genai:semantic-conventions
OpenTelemetry GenAI semantic conventions for agent instrumentation - the standard attributes for LLM observability
npx skills add majiayu000/claude-skill-registry --skill genai-semantic-conventions --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# OpenTelemetry GenAI Semantic Conventions Reference for instrumenting agents with OpenTelemetry GenAI semantic conventions. **Spec**: https://opentelemetry.io/docs/specs/semconv/gen-ai/ ## Architecture ``` Agent (gen_ai.* only) → OTEL Collector → Transform → Phoenix (llm.*) + MLflow (mlflow.trace.*) ``` Agents emit **only** `gen_ai.*` attributes. The OTEL Collector transforms these to: - **OpenInference format** (`llm.*`) for Phoenix - **MLflow metadata** (`mlflow.trace.*`) for MLflow session tracking ## Core Attributes ### Request Attributes (on LLM call spans) | Attribute | Type | Description | Example | |-----------|------|-------------|---------| | `gen_ai.system` | string | GenAI provider/system | `openai`, `anthropic`, `langchain` | | `gen_ai.request.model` | string | Model requested | `gpt-4`, `claude-3-opus` | | `gen_ai.request.max_tokens` | int | Max tokens to generate | `1024` | | `gen_ai.request.temperature` | float | Sampling temperature | `0.7` | | `gen_ai.request.top_p` | float | Nucleus sampling | `0.9` | ### Response Attributes | Attribute | Type | Description | Example | |-----------|------|-------------|---------| | `gen_ai.response.model` | string | Model that r
- Architecture
- Core Attributes
- Request Attributes (on LLM call spans)
- Response Attributes
- Conversation/Session Attributes
- Agent Attributes (custom, for A2A agents)
- Python Usage
- Auto-instrumentation (Recommended)
- Manual Span Attributes
- Adding to Existing Span
- OTEL Collector Transforms
- GenAI → OpenInference (Phoenix)
- GenAI → MLflow
- Span Naming Conventions
What does the genai:semantic-conventions skill do?
OpenTelemetry GenAI semantic conventions for agent instrumentation - the standard attributes for LLM observability
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill genai-semantic-conventions --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.