metrics-queries

How to query OpenTelemetry metrics datasets in Honeycomb correctly. Metrics datasets follow different rules from trace/event datasets — many operations (bare COUNT, RATE_SUM, RATE_AVG, RATE_MAX, CONCURRENCY) are forbidden, temporal aggregation is automatic, and each metric has its own attributes. Use this skill when querying a metrics dataset (gauges, counters, histograms, sums), asking about temporal aggregation (RATE, INCREASE, SUMMARIZE, LAST), finding the metrics dataset or discovering metric names and attributes, debugging unexpected metrics query results, or querying infrastructure metrics like CPU, memory, disk I/O, or network stats. Do NOT use for instrumenting metrics (use otel-instrumentation), querying event datasets with "metrics" in their name, or conceptual questions (use observability-fundamentals).

1.68x

Quality

96%

Does it follow best practices?

Impact

96%

1.68x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

92%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, actionable skill body: executable JSON examples, validated discovery workflows, and clean progressive disclosure into real reference files. The only weakness is mild redundancy between the forbidden-operations table and the Common Pitfalls section.

Suggestions

Trim Common Pitfalls #1 and #2, which restate the forbidden-operations table verbatim — link to that table or keep only the remediation guidance ('use a calculated field with RATE($metric)') to improve conciseness.

The 'Granularity for Metrics' section's RATE_SUM note references an event-dataset operation that is already forbidden on metrics; tighten this to avoid re-explaining a case the skill already rules out.

Dimension	Reasoning	Score
Conciseness	Dense, Honeycomb-specific operational knowledge with no generic-concept padding, but the Common Pitfalls section (#1 COUNT, #2 RATE_AVG/RATE_SUM/RATE_MAX) restates the forbidden-operations table, which could be trimmed. Not a 5 because of that minor redundancy; not a 3 because the body overwhelmingly assumes Claude's competence.	4 / 5
Actionability	Fully executable copy-paste JSON for calculated_fields, calculations, and formulas across common cases (utilization, tail ratio, error rate), plus concrete API calls with parameters (get_environment, get_dataset_columns with metric_name).	5 / 5
Workflow Clarity	Numbered discovery workflows carry explicit validation checkpoints ('Always verify via get_environment or get_dataset_columns', 'Validate before querying'), and the Common Pitfalls section functions as a debugging checklist for unexpected results.	5 / 5
Progressive Disclosure	Clear overview with deep material appropriately split into one-level-deep, well-signaled reference files (temporal-aggregation.md, metrics-query-examples.md, metric-types.md), all of which exist in ./references/, plus cross-references to sibling skills.	5 / 5
	Total	19 / 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 excellent description: concise yet comprehensive, with concrete actions, natural trigger terms, explicit what/when guidance, and strong boundary marking that distinguishes it from sibling skills. No meaningful gaps to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — querying metrics datasets, finding the dataset, discovering metric names and attributes, debugging unexpected results, and querying infrastructure metrics (CPU, memory, disk I/O, network) — giving comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly states what it does ('How to query OpenTelemetry metrics datasets in Honeycomb correctly') and when to use it ('Use this skill when querying a metrics dataset...'), with concrete trigger phrases and a 'Do NOT use for' boundary.	5 / 5
Trigger Term Quality	Comprehensive natural terms including metric-type synonyms (gauges, counters, histograms, sums), temporal-aggregation function names (RATE, INCREASE, SUMMARIZE, LAST), and concrete infrastructure phrases users actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Honeycomb metrics datasets) with explicit redirects to sibling skills (otel-instrumentation, observability-fundamentals) and disambiguation from event datasets with 'metrics' in their name, 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: honeycombio/agent-skill
Path: honeycomb/skills/metrics-queries/SKILL.md
Commit: 41214b7

Reviewed: 5 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.