llmobs-testing

Use when writing, modifying, or debugging tests for an LLMObs plugin in dd-trace-js. Triggers: "write LLMObs tests", "test an LLMObs plugin", "assertLlmObsSpanEvent", "useLlmObs", "getEvents", any MOCK_* matcher ("MOCK_STRING" / "MOCK_NOT_NULLISH" / "MOCK_NUMBER" / "MOCK_OBJECT"), "VCR cassette", "vcr proxy", "127.0.0.1:9126", "record a cassette", "test:llmobs:plugins".

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

93%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 tight, highly actionable skill body that front-loads the key decision (response source per surface) and backs it with executable commands, paths, and code while offloading depth to four real reference files. The only gap is an explicit validate-fix-retry loop in the test-writing workflow.

Dimension	Reasoning	Score
Conciseness	Lean and dense throughout: assumes Claude knows JS/testing concepts and spends every token on non-obvious operational detail (port numbers, cassette paths, matcher semantics) without explaining what spans or VCR are, matching the lean 5-anchor.	5 / 5
Actionability	Fully executable guidance: exact commands (docker compose up -d testagent), precise paths and baseURLs, copy-paste error-handling code, and concrete matcher semantics covering the common cases.	5 / 5
Workflow Clarity	The basic test flow and file-organization steps are clearly sequenced with a terminal validation step (assertLlmObsSpanEvent) and an error-pinning feedback path, but it lacks an explicit validate-fix-retry checklist loop that would lift it to 5.	4 / 5
Progressive Disclosure	Clear overview in SKILL.md with four well-signaled one-level-deep references, all of which are real files in ./references/, with detail appropriately split out and easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

95%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.

A strong, specific description that clearly states its narrow domain and packs it with concrete, natural trigger terms including exact commands and helper names. The only minor gap is that the three actions are variations of a single testing task rather than comprehensive multi-action coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (LLMObs plugin testing in dd-trace-js) with three specific actions (writing, modifying, debugging tests), but the actions are variations of one testing task rather than broad multi-action coverage, leaving minor gaps versus the comprehensive 5-anchor.	4 / 5
Completeness	Explicitly answers both what (writing/modifying/debugging LLMObs plugin tests) and when ("Use when..." clause with concrete trigger phrases), matching the 5-anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms and exact strings: "write LLMObs tests", "test an LLMObs plugin", "VCR cassette", "record a cassette", "test:llmobs:plugins", plus specific helper and matcher names users would cite.	5 / 5
Distinctiveness Conflict Risk	Clear niche with highly distinct triggers (specific helper names like assertLlmObsSpanEvent, port 127.0.0.1:9126, MOCK_* matchers) that are unlikely to fire for any other skill.	5 / 5
	Total	19 / 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: DataDog/dd-trace-js
Path: .agents/skills/llmobs-testing/SKILL.md
Commit: 27ffef2

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.