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

83%

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

Quality

Content

81%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 thorough, well-structured multi-step skill with strong workflow sequencing and validation loops plus concrete per-language commands. Conciseness and progressive disclosure are good rather than excellent due to a verbose handoff section and reliance on sibling-skill reference files.

Suggestions

Tighten Step 0's handoff section: collapse the version-check and shape-check example messages into a compact schema/error template rather than full quoted blocks, and consider moving the full JSON envelope into a reference file.

Make the Expect/conventions references self-contained to this skill (or ship a local references/conventions-{language}.md) so navigation stays one level deep within the skill's own bundle.

Concretize the remaining abstract directives in Fix Mode (e.g., "Investigate the cause") with a short diagnostic checklist of steps to run before touching the output file.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it never explains what a test or a database is — but the Step 0 handoff section (version-check messages, full JSON envelope) is somewhat heavy and could be trimmed, keeping it just below the 'lean, every token earns its place' 5-anchor.	4 / 5
Actionability	It provides copy-paste per-language test commands, concrete decision tables for file placement and validation approaches, and a worked fix walkthrough, but a few directives like "Investigate the cause before updating the output file" stay abstract, leaving minor gaps versus the fully executable 5-anchor.	4 / 5
Workflow Clarity	Steps 0–8 are explicitly sequenced with validation checkpoints — run the test to verify, loop back max 3 attempts, stop and report after 3 failures, and "Do not modify the example file without checking with the user first" — matching the clear-sequence-with-explicit-validation-and-feedback-loops 5-anchor.	5 / 5
Progressive Disclosure	The body is a well-organized overview with one-level-deep, clearly signaled references to conventions files ("See the 'Comparison API' section in ...conventions-{language}.md") and sibling skills; it sits at 4 rather than 5 because some references point into another skill's references directory rather than a self-contained bundle, and no bundle files are shipped with this skill.	4 / 5
	Total	17 / 20 Passed

Description

86%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, third-person description that cleanly answers both what and when with rich, natural trigger phrases. The only gap is that specificity lists just two actions and distinctiveness relies on the body for sibling-skill boundaries.

Dimension	Reasoning	Score
Specificity	The description names the domain ("existing Grove code examples") and two concrete actions ("Create or fix tests"), but offers no further action breakdown, matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor at 4.	3 / 5
Completeness	It explicitly states both what ("Create or fix tests for existing Grove code examples") and when ("Use when the user asks to...") with concrete trigger phrases, matching the 5-anchor exactly.	5 / 5
Trigger Term Quality	It enumerates natural phrases users actually say — "add a test", "create a test", "fix this test", "update the test", "the test doesn't match the output", "test is failing", "fix a broken test" — giving comprehensive synonym/variation coverage as the 5-anchor requires.	5 / 5
Distinctiveness Conflict Risk	The "Grove code examples" niche and specific triggers make it mostly distinct with only minor overlap risk against sibling grove-create/grove-run/grove-migrate skills; it stops short of 5 because the description itself carries no negative-boundary carve-out to separate those closely related skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mongodb/docs
Path: .claude/skills/grove-test/SKILL.md
Commit: d9cb237

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.