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).
95
92%
Does it follow best practices?
Impact
100%
2.70xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly communicates what the skill does, when to use it, and what it covers. It uses third person voice, provides multiple natural trigger phrases, and is specific enough to be easily distinguishable from other skills. The inclusion of supported languages adds valuable specificity without being overly verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists a concrete action ('Create a new tested code example in the Grove platform') and specifies the supported languages (Python/PyMongo, Go, Java, JavaScript/Node.js, C#, Mongosh). This is highly specific about what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (create a new tested code example in the Grove platform for MongoDB documentation) and 'when' (explicit 'Use when...' clause with multiple trigger phrases). Both dimensions are thoroughly addressed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases: 'create a code example', 'add a new example', 'scaffold a Grove example', 'new tested example for docs', 'create an example for [language]'. These are phrases users would naturally say, and the language names serve as additional trigger terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific platform (Grove), a specific domain (MongoDB documentation), and a specific task (tested, snippeted code examples). The combination of 'Grove platform' and 'MongoDB documentation' makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for a complex multi-language code example creation workflow. The 12-step process is clearly sequenced with appropriate validation checkpoints, user confirmation gates, and error recovery loops. The skill effectively uses progressive disclosure by referencing per-language convention files and related skills rather than inlining everything. Minor verbosity in routing logic and data strategy prompts prevents a perfect conciseness score.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lengthy (~300 lines) but most content is genuinely necessary for a complex multi-step, multi-language workflow. Some sections could be tightened — e.g., the Mongosh vs JavaScript and C# vs EF Core routing explanations are somewhat verbose, and the data strategy prompt template could be shorter. However, it largely avoids explaining things Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete directory paths, specific file naming patterns, exact table mappings for all 7 language suites, precise commands for verification, and references to real template files (e.g., `examples/example-stub.js`). The subagent prompt in Step 11 is copy-paste ready with clear placeholders. Every step tells Claude exactly what to do. | 3 / 3 |
Workflow Clarity | The 12-step workflow is clearly sequenced with explicit validation checkpoints: Step 2 requires user confirmation before proceeding, Step 4 checks for existing examples, Step 11 launches a verification subagent with a retry loop (max 3 attempts), and idempotency is verified by running tests twice. Error recovery paths are well-defined (fix → re-launch reviewer → stop after 3 failures). | 3 / 3 |
Progressive Disclosure | The skill references per-language convention files (`references/conventions-{language}.md`), Bluehawk tag reference (`references/bluehawk-tags.md`), language-specific CLAUDE.md files, and related skills (`/grove-test`, `/grove-run`, `/grove-migrate`, etc.) — all one level deep. The main body serves as a clear orchestration overview without inlining detailed reference material. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- mongodb/docs
- Commit
5985af5
- Reviewed
Table of Contents
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.