grove-migrate

Migrate existing untested code into the Grove test suite. Use when the user asks to "migrate this code", "convert to Grove", "make this testable", "move this example to the test suite", "add tests for this existing code", "migrate the code on this page", or wants to convert documentation code examples that currently live outside of Grove into properly tested, snippeted examples. Supports both page-level migration (scan an RST page for all code) and snippet-level migration (convert a single code block).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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, highly actionable 12-step migration workflow with explicit validation and error-recovery loops. The main weaknesses are minor content duplication (partial-file-include guidance appears twice) and that the referenced reference files are not present in the skill bundle, which leaves the progressive-disclosure navigation unverifiable.

Suggestions

Dedupe the partial-file-include (:start-after:/:end-before: → :snippet-start:/:snippet-end:) guidance, which is repeated in Step 7 and the Edge Cases section, into a single location.

Ensure the referenced files (references/page-scanning.md, references/data-adaptation.md, references/extension-handoff.md) actually ship in the skill bundle so the one-level-deep navigation resolves.

Tighten Step 7's infrastructure-change list, which currently re-explains each :replace:/:remove: rationale that is already covered in Step 8's numbered application steps.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural with little beginner-concept padding (no "what is a test suite" exposition), but partial-file-include guidance is repeated in Step 7 and Edge Cases and a few sections could be tightened. It is not a 5 because of that duplicated content and length; not a 3 because the writing assumes Claude's competence rather than over-explaining.	4 / 5
Actionability	Provides concrete, executable guidance throughout — a language-to-suite-directory table, named Bluehawk tags (:snippet-start:, :replace:, :uncomment:, :remove:), a copy-paste-ready reviewer subagent prompt, and a concrete RST literalinclude example for the docs update. It is not a 4 because specific examples cover the common cases with fill-in-the-blank commands rather than leaving gaps.	5 / 5
Workflow Clarity	A clearly sequenced Step 0–12 workflow with an explicit validation checkpoint in Step 11 (reviewer runs the test twice for idempotency plus the snip command) and a feedback loop (fix and re-launch, max 3 attempts, then stop and report). It is not a 4 because validation and error-recovery are explicit rather than merely present.	5 / 5
Progressive Disclosure	The body acts as an overview and clearly signals one-level-deep references for detail (references/page-scanning.md, references/data-adaptation.md, references/extension-handoff.md, plus per-language CLAUDE.md files), but those references/*.md files are not present in the bundle, so navigation cannot be verified. It is not a 5 because the referenced reference files are absent from the bundle; not a 3 because signaling is clear and detail is split out rather than inlined.	4 / 5
	Total	18 / 20 Passed

Description

96%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 well-crafted description that names concrete actions, supplies many natural trigger phrases, and explicitly covers both what the skill does and when to use it. The only soft spot is minor overlap risk with sibling grove testing/creation skills, which the body's "Do NOT use when" section resolves but the description alone does not.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Migrate existing untested code into the Grove test suite", "scan an RST page for all code", "convert a single code block", and converting doc examples "into properly tested, snippeted examples" — giving comprehensive coverage of the migration workflow. It is not a 4 because the actions span both migration modes with specifics rather than having only minor gaps.	5 / 5
Completeness	Explicitly answers both "what" (migrate untested code into the Grove test suite, page-level and snippet-level) and "when" with concrete "Use when the user asks to ..." trigger phrases. It is not a 4 because both halves are explicit and concrete rather than having a vaguely specified "when".	5 / 5
Trigger Term Quality	Provides six natural trigger phrases users would actually say ("migrate this code", "convert to Grove", "make this testable", "move this example to the test suite", "add tests for this existing code", "migrate the code on this page") with synonym-level variation. It is not a 4 because the coverage of natural phrasings is comprehensive rather than missing a few common terms.	5 / 5
Distinctiveness Conflict Risk	The "migrate existing untested code" framing carves a clear niche distinct from sibling grove-create/grove-test skills, but triggers like "make this testable" and "add tests for this existing code" carry minor overlap risk with grove-test. It is not a 5 because that closely-related family introduces some conflict risk; not a 3 because the migration framing is clearly more specific than broad overlap.	4 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: mongodb/docs
Path: .claude/skills/grove-migrate/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.