otel-queries

Guidance for querying and interpreting Copilot and agentic workflow OpenTelemetry token and execution metrics.

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/otel-queries/SKILL.md

Quality

Content

72%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.

The body is exemplary in token efficiency and structure — a short, well-sectioned set of non-obvious policy directives with no filler. Its weakness is executability: it tells Claude what to prefer and summarize but not how to parse the OTEL JSONL or in what order to investigate, leaving the workflow implicit.

Suggestions

Add a minimal executable example for the core task, e.g. a one-line jq or Python snippet reading the COPILOT_OTEL_FILE_EXPORTER_PATH JSONL and grouping token counts by model.

Sequence the investigation as ordered steps (locate export file, parse records, group by model/step/request type, report) so the workflow is explicit rather than implied.

Name the concrete JSONL fields that hold token and timing data so malformed-record handling ('Treat missing or malformed OTEL records as diagnostic data') has something actionable to check against.

Dimension	Reasoning	Score
Conciseness	The body is a lean 12 lines: one scoping sentence and four terse directives, with zero padding and no explanation of concepts Claude already knows (e.g., what OpenTelemetry is). Every token earns its place, matching the 'lean and efficient' anchor; the verbose anchors at 4 and below all describe unnecessary explanation that is absent here.	5 / 5
Actionability	The directives name concrete dimensions ('by model, agent step, and request type', 'COPILOT_OTEL_FILE_EXPORTER_PATH JSONL files') but give no executable mechanics — no jq/Python snippet for parsing the JSONL, no field names for token counts, and no output format. This is 'some concrete guidance but incomplete / missing key details'; it is above the minimal-hints anchor at 2 but below the mostly-executable anchor at 4.	3 / 5
Workflow Clarity	The bullets are preferences and policies rather than a sequenced investigation (no order such as locate export file, parse, summarize, report, and no validation checkpoints). Even under the simple-skill exception the single action is not fully unambiguous — how to summarize is unspecified — so it sits at the 'steps listed but checkpoints missing or implicit' anchor rather than 4.	3 / 5
Progressive Disclosure	The skill is under 50 lines, no bundle files (references/scripts/assets) exist, and the body is organized under a clear '# OTEL Queries' heading with a '## Guidance' section. Per the rubric's simple-skill guideline, well-organized sections with no need for external references score 5.	5 / 5
	Total	16 / 20 Passed

Description

53%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.

The description names a clear, distinctive niche and two concrete capabilities, but it reads as a label rather than an invitable trigger: it lacks any 'Use when...' guidance and omits natural synonyms like 'OTEL', 'telemetry', and 'JSONL'. Overall it sits just above the midpoint of the scale.

Suggestions

Add an explicit trigger clause, e.g. 'Use when investigating Copilot or agentic workflow token usage, execution timing, OTEL traces, or exported COPILOT_OTEL_FILE_EXPORTER_PATH JSONL files.'

Include natural synonyms and concrete artifacts users would mention: 'OTEL', 'telemetry', 'traces', 'JSONL export files'.

Convert the vague 'Guidance for...' framing into concrete third-person actions, e.g. 'Queries and summarizes token counts by model, agent step, and request type from OpenTelemetry JSONL exports.'

Dimension	Reasoning	Score
Specificity	The description names the domain ('Copilot and agentic workflow OpenTelemetry') and two concrete actions ('querying and interpreting ... token and execution metrics'), which matches the '1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because it does not list several specific actions (e.g., no mention of summarizing, parsing, or reporting), and not a 2 because it goes beyond merely naming the domain.	3 / 5
Completeness	The 'what' is clear (querying and interpreting OTEL token/execution metrics) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because the 'when' is entirely absent rather than just under-specified, and not a 2 because the 'what' is concrete.	3 / 5
Trigger Term Quality	It contains relevant keywords ('Copilot', 'OpenTelemetry', 'token', 'execution metrics', 'agentic workflow') but misses common variations and synonyms users would naturally say, such as 'OTEL', 'telemetry', 'traces', or 'JSONL'. This fits the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor at 4.	3 / 5
Distinctiveness Conflict Risk	The 'Copilot and agentic workflow OpenTelemetry token and execution metrics' niche is fairly distinct, with minor overlap risk only against general OTEL/observability skills. It is not a 5 because the generic 'Guidance for...' framing and absence of explicit triggers leave modest ambiguity against broader telemetry-analysis skills.	4 / 5
	Total	13 / 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: dotnet/maui
Path: .github/skills/otel-queries/SKILL.md
Commit: 7a5a5d6

Reviewed: 7 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.