grove-test

Create or fix tests for existing Grove code examples. Use when the user asks to "add a test", "create a test", "fix this test", "update the test", "the test doesn't match the output", "test is failing", or wants to add test coverage for an existing example or fix a broken test.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

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 test-authoring workflow with strong sequencing and explicit validation/feedback loops. The main weakness is progressive disclosure: a long monolithic body with no own-bundle references, where some content could be factored into reference files.

Suggestions

Factor the Step 0 handoff envelope schemas and the Step 5 comparison-API table into a references/ file (e.g. references/handoff.md and references/comparison-api.md), keeping SKILL.md as a concise overview with clearly signaled one-level-deep links.

Move the per-language Expect API specifics already delegated to conventions-{language}.md into a short pointer table in SKILL.md so the body stays a lean overview.

Consider pulling the runtime-issue heuristic list (ECONNREFUSED, MongoServerSelectionError, etc.) into a small referenced troubleshooting note to further trim the top-level body.

Dimension	Reasoning	Score
Conciseness	The body is procedural and specific throughout with no generic concept explanations (no "what a test is" padding); even the verbose handoff schema is explicitly framed as a reference payload, so every section earns its place.	3 / 3
Actionability	Provides an executable command (`cd code-example-tests/{driver-dir} && npm test -- -t '{test name}'`), a concrete decision table of Expect methods, and a real error walkthrough — copy-paste ready guidance rather than abstractions.	3 / 3
Workflow Clarity	Steps 0–8 are explicitly sequenced with validation checkpoints (Step 0 version/shape checks, Step 7 run-and-loop with a hard "max 3 attempts then stop and report" feedback loop), matching the top anchor.	3 / 3
Progressive Disclosure	The skill is a single ~270-line file with no bundle of its own; references to other skills' files (conventions-{language}.md, /grove-run Step 3) are clearly signaled and one level deep, but the bulk of the content (handoff schemas, comparison-API table) is inline and could be split out.	2 / 3
	Total	11 / 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 concise, third-person, and answers both what and when with natural trigger phrases. It carves out a clear, low-conflict niche relative to sibling grove skills.

Dimension	Reasoning	Score
Specificity	Names the domain ("existing Grove code examples") and multiple concrete actions ("Create or fix tests"), matching the anchor for listing specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("Create or fix tests for existing Grove code examples") and when (a literal "Use when the user asks..." clause with enumerated triggers), satisfying the top anchor.	3 / 3
Trigger Term Quality	Quotes exact natural phrases users would say ("add a test", "create a test", "fix this test", "update the test", "the test doesn't match the output", "test is failing"), giving strong coverage of real trigger language.	3 / 3
Distinctiveness Conflict Risk	The Grove-test niche is clearly scoped, and the body's "Do NOT use when" list distinguishes it from /grove-create, /grove-run, and /grove-migrate, making wrong-skill triggering unlikely.	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: mongodb/docs
Commit: e765459

Reviewed: about 23 hours 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.