grove-maintain

Audit, upgrade, and maintain Grove test suites. Use when the user asks to "audit the test suite", "find untested examples", "upgrade dependencies", "check suite health", "find dead code", "clean up the test suite", "maintain Grove", "what examples are missing tests", or wants to analyze and improve the overall health of a Grove test suite.

0.96x

Quality

92%

Does it follow best practices?

Impact

80%

0.96x

Average score across 1 eval scenario

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 highly actionable, well-sequenced maintenance workflow with strong validation checkpoints across all three modes. Its main weakness is progressive disclosure: a large skill with no bundle files inlines reference material that would benefit from being split into references/.

Suggestions

Extract the per-language command tables (dependency check, formatter, release-notes locations, ping one-liners) into a references/ file (e.g. references/language-commands.md) and have SKILL.md point to it, leaving the body as a mode overview.

Tighten editorial asides like 'Skipping this step is the single biggest time-sink in practice' to factual guidance so conciseness reaches a 5.

Consider moving the detailed Spot-Check/Freeform pattern lists into a references file so the core audit/cleanup workflow stays scannable.

Dimension	Reasoning	Score
Conciseness	Largely lean and token-dense (command tables, exact patterns) with operational asides that earn their place, but a few editorial sentences ('single biggest time-sink in practice') could be trimmed. Not a 5 because of those minor over-explanation instances; not a 3 because the prose conveys non-obvious operational wisdom rather than concepts Claude already knows.	4 / 5
Actionability	Fully executable per-language commands (npm outdated, pip list --outdated, go list -m -u all, etc.), exact grep/glob patterns, copy-paste DB ping one-liners, and concrete file paths cover the common cases.	5 / 5
Workflow Clarity	Sequenced Step 0-6 workflows with explicit validation checkpoints (preflight baseline, wall-clock comparison, 'if unreachable, stop') and feedback loops (regenerate snippets, re-run to confirm); destructive cleanup is gated on user approval, satisfying the validation cap.	5 / 5
Progressive Disclosure	No bundle files exist and substantial reference-style content (per-language command tables, release-note locations, formatter commands) is inlined in SKILL.md rather than split into references/. Not a 4 because content that belongs in separate files is inline; not a 2 because section structure and mode separation are clear and external CLAUDE.md pointers are signaled.	3 / 5
	Total	17 / 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.

A strong description that crisply states the skill's purpose and provides abundant natural trigger phrases. It clearly answers both what the skill does and when to invoke it, with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('Audit, upgrade, and maintain') that map directly to the skill's modes, giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (audit/upgrade/maintain Grove test suites) and 'when' via a concrete 'Use when...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Lists eight natural trigger phrases users would actually say ('audit the test suite', 'find untested examples', 'find dead code', etc.) with synonym coverage.	5 / 5
Distinctiveness Conflict Risk	'Grove test suites' is a clear, specific niche and the triggers are scoped to maintenance, minimizing overlap with sibling grove-* skills.	5 / 5
	Total	20 / 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-maintain/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.