otel-instrumentation

Provides guidance on OpenTelemetry SDK setup, custom instrumentation, and sending data to Honeycomb. Trigger phrases: "instrument my app", "add tracing", "set up OpenTelemetry", "configure OTel", "add custom spans", "add attributes to spans", "send traces to Honeycomb", "set up OTLP", "configure sampling", "add span events", "add span links", "set up tracing for [any language]", "configure the OTel Collector", or any request about OpenTelemetry SDK setup, custom instrumentation, or sending data to Honeycomb.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable reference body that leverages real bundle files for depth, held back slightly by verbosity in a few inline sections and the absence of an explicit validation workflow for setup. Progressive disclosure is exemplary.

Suggestions

Tighten or move the exception/Logs-API and LogRecordProcessor compatibility prose into custom-instrumentation.md to reduce inline token load.

Add an explicit setup verification checkpoint (e.g., 'send a test span, confirm it appears via the production-investigation/query-patterns skill before proceeding') to give the workflow a validation loop.

Either reference python.md in the body or remove the unreferenced orphan from ./references/ to keep the bundle index consistent.

Dimension	Reasoning	Score
Conciseness	The ~340-line body is mostly practical and Honeycomb-specific (no padding with basics Claude knows), but inline prose on exception/Logs-API mechanics, the LogRecordProcessor compatibility layer, and sampling-narrative could be tightened or pushed into references, leaving it longer than an overview should be.	2 / 3
Actionability	Concrete, copy-paste-ready guidance throughout — exact env vars and headers, executable Go/Python snippets, a query recipe ("WHERE error = true AND exception.slug does-not-exist"), and specific SDK method names per language.	3 / 3
Workflow Clarity	Sections are sensibly ordered (setup → instrument → what to instrument → events → sampling → layering) and "Common Pitfalls" flags the silent-auth-failure gotcha, but there is no explicit validate→fix→retry sequence or checkpoint for the setup/instrumentation workflow.	2 / 3
Progressive Disclosure	SKILL.md serves as an overview with clearly signaled, one-level-deep references (sdk-setup-by-language, custom-instrumentation, wide-event-attributes, architectural-patterns, lambda, collector-config, local-collector-debug-test) — all of which exist in ./references/ — and an organized Additional Resources index.	3 / 3
	Total	10 / 12 Passed

Description

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.

The description is third-person, specific, and covers both capabilities and explicit natural-language triggers, with a well-scoped niche that minimizes conflict risk. It hits the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "OpenTelemetry SDK setup, custom instrumentation, and sending data to Honeycomb" — plus a long list of specific operations (custom spans, attributes, span events, span links, OTLP, sampling, Collector).	3 / 3
Completeness	Explicitly answers both what ("Provides guidance on OpenTelemetry SDK setup, custom instrumentation, and sending data to Honeycomb") and when (a dedicated "Trigger phrases:" list plus "or any request about..."), exceeding the explicit-trigger bar.	3 / 3
Trigger Term Quality	Broad coverage of phrases a user would naturally say — "instrument my app", "add tracing", "set up OpenTelemetry", "configure OTel", "send traces to Honeycomb", "set up tracing for [any language]" — plus the catch-all "any request about OpenTelemetry SDK setup".	3 / 3
Distinctiveness Conflict Risk	A clear niche — OpenTelemetry instrumentation for Honeycomb — with distinct, domain-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: honeycombio/agent-skill
Commit: 189553c

Reviewed: 1 day 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.