deepeval-otel

Export raw OpenTelemetry traces from an AI application to Confident AI's Observatory. TRIGGER when the user wants to send OpenTelemetry or OTLP traces/spans from an LLM app, agent, RAG pipeline, or chatbot to Confident AI; configure the Confident AI OTLP endpoint; set confident.span.* or confident.trace.* attributes; export AI-app traces without the deepeval Python package; wire an OTLPSpanExporter, OpenTelemetry Collector, or vendor-neutral OTel SDK to Confident AI; or pick the US vs EU OTLP endpoint. Language-agnostic: the mechanism is OTLP attribute keys plus an exporter endpoint. DO NOT TRIGGER for building DeepEval pytest eval suites, datasets, goldens, metrics, or deepeval test run (use the `deepeval` skill); for instrumenting with the DeepEval SDK's @observe decorator or framework integrations (use the `deepeval-tracing` skill); or for non-AI software such as web servers, CRUD backends, or infrastructure: the confident.* attributes describe AI components only.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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 well-structured, mostly actionable overview that appropriately delegates detail to organized reference files, with a clear gated workflow. It is held back from top marks by a missing referenced template file, some redundant restatement of the same constraints, and a verify step without an explicit recovery loop.

Suggestions

Add the missing `templates/confident_otel_setup.py` (referenced in the Workflow, Templates table, and endpoint-and-exporter.md) or remove the references — a navigation path that 404s undermines progressive disclosure and actionability.

State the "AI applications only" and "HTTP-only" rules once authoritatively (e.g. in Core Principles) and trim their restatement in the intro, Scope, Prerequisites, and How It Works to tighten conciseness.

Turn the final workflow step into an explicit feedback loop: "Verify traces appear in Observatory; if absent, confirm the region endpoint, the `x-confident-api-key` header, and that only AI spans are on the Confident AI pipeline."

Dimension	Reasoning	Score
Conciseness	Mostly lean and it does not explain OTel basics Claude already knows, but the "AI applications only" and "HTTP only" constraints are restated 4–5 times across the intro, Scope, Prerequisites, How It Works, and Core Principles, which is over-emphasis that could be trimmed.	4 / 5
Actionability	Concrete guidance throughout — exact endpoint URLs, the `x-confident-api-key` header, exact `confident.*` attribute keys, and a well-pointed reference containing full executable Python — but the body has no inline copy-paste snippet and names a template file (`templates/confident_otel_setup.py`) that does not exist.	4 / 5
Workflow Clarity	A clear 8-step numbered sequence with an explicit stop-gate in step 1 ("If it has none of these, stop") and a verify step in step 8, but the verify step lacks an explicit failure-recovery loop ("if traces don't appear, check X").	4 / 5
Progressive Disclosure	A clear overview delegating detail to four real, one-level-deep reference files via References and Templates tables, but `templates/confident_otel_setup.py` is referenced in three places and is absent from the bundle, a broken navigation path.	4 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplar description: concrete actions, explicit trigger and anti-trigger clauses, synonym coverage, and clear disambiguation from sibling skills, all in third-person/imperative voice. Every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Export raw OpenTelemetry traces", "configure the Confident AI OTLP endpoint", "set confident.span.* or confident.trace.* attributes", "wire an OTLPSpanExporter, OpenTelemetry Collector, or vendor-neutral OTel SDK", "pick the US vs EU OTLP endpoint" — giving comprehensive coverage of the task.	5 / 5
Completeness	Explicitly answers both: what ("Export raw OpenTelemetry traces from an AI application to Confident AI's Observatory") and when ("TRIGGER when the user wants to send OpenTelemetry or OTLP traces/spans..." plus "DO NOT TRIGGER for...").	5 / 5
Trigger Term Quality	Covers the natural terms a user would say — "OpenTelemetry or OTLP traces/spans", "LLM app, agent, RAG pipeline, or chatbot", "Confident AI", "US vs EU OTLP endpoint" — with synonyms (OTel/OTLP, traces/spans, LLM/agent/RAG/chatbot) comprehensively represented.	5 / 5
Distinctiveness Conflict Risk	Clear niche (vendor-neutral OTLP export to Confident AI) with explicit disambiguation against the sibling `deeveval` and `deeveval-tracing` skills via DO NOT TRIGGER clauses, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: confident-ai/deepeval
Path: skills/deepeval-otel/SKILL.md
Commit: 077c81b

Reviewed: 3 days 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.