Name: grove-create
Rating: 96 (1 reviews)
Author: mongodb

grove-create

Create a new tested code example in the Grove platform. Use when the user asks to "create a code example", "add a new example", "scaffold a Grove example", "new tested example for docs", "create an example for [language]", or wants to add a tested, snippeted code example for MongoDB documentation. Covers Python (PyMongo), Go, Java (Sync Driver), JavaScript (Node.js Driver), C#, and Mongosh (MongoDB Shell).

2.70x

Quality

—

Does it follow best practices?

Impact

100%

2.70x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality procedural skill: lean for its complexity, highly actionable, with a well-sequenced 12-step workflow and explicit validation/retry feedback loops. Progressive disclosure is handled well, with language-specific detail correctly pushed to real, clearly-signaled reference files.

Dimension	Reasoning	Score
Conciseness	The body is long but proportional to genuine complexity (7 languages, 12 steps), and it assumes Claude's competence throughout without explaining concepts Claude already knows (MongoDB, Bluehawk, test frameworks); it earns a 3 rather than a 2 because the length reflects dense procedural content rather than padding.	3 / 3
Actionability	It provides exact base-directory paths, a per-language location table, concrete decision rules, and a copy-paste-ready reviewer subagent prompt with specific commands, satisfying 'fully executable guidance'; it is not a 2 because no key details are left abstract or pseudocode.	3 / 3
Workflow Clarity	Twelve explicitly sequenced steps include validation checkpoints and a feedback loop in Step 11 (run test, report failure without fixing, re-run for idempotency, snip, retry max 3), matching the level-3 anchor for clear sequence with error-recovery loops.	3 / 3
Progressive Disclosure	Language-specific detail is split into real one-level-deep references (all eight referenced references/*.md files exist) that are clearly signaled inline, while the body stays an overview of routing and cross-cutting process; it is not a 2 because content is appropriately externalized rather than inlined.	3 / 3
	Total	12 / 12 Passed

Description

90%

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 with explicit trigger terms, a clear 'Use when' clause, and a well-bounded niche. Its only weakness is specificity: it centers on one action (create) rather than enumerating several concrete operations.

Dimension	Reasoning	Score
Specificity	It names the domain concretely ('Create a new tested code example in the Grove platform') and lists six covered languages, but it describes essentially a single action rather than the 'multiple specific concrete actions' the level-3 anchor requires.	2 / 3
Completeness	It answers both 'what' ('Create a new tested code example in the Grove platform') and 'when' with an explicit 'Use when the user asks to...' clause, matching the level-3 anchor.	3 / 3
Trigger Term Quality	It quotes natural phrases a user would actually say ('create a code example', 'add a new example', 'scaffold a Grove example', 'new tested example for docs', 'create an example for [language]'), giving strong coverage of likely trigger language.	3 / 3
Distinctiveness Conflict Risk	The Grove/MongoDB-tested-example niche is specific and the triggers are distinctive, making it unlikely to fire for unrelated skills; it would not score lower because the scope is clearly bounded to a named platform and doc workflow.	3 / 3
	Total	11 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: mongodb/docs
Commit: e765459

Reviewed: about 20 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.