refactoring

Refactor existing packages toward the standard service/adapter pattern. Use when restructuring a domain package, splitting a monolithic package, or removing anti-patterns.

Quality

90%

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

80%Weight 40%Scale 1-3

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

A well-structured, actionable refactoring guide with strong conciseness and concrete commands. Its main gap is the absence of an explicit validation feedback loop in the workflow, and it relies on a single inline file rather than progressively disclosing detail via references.

Suggestions

Add an explicit feedback loop to the workflow, e.g. after 'Run tests: make test' add 'If tests fail: review the failure, fix the moved types/wiring, and re-run until green' to earn the workflow_clarity top anchor.

Move the per-package issue tables (High/Medium/Low Priority) into a references file (e.g. references/packages.md) and link to it from SKILL.md, keeping the body as an overview — this improves progressive disclosure for a 90+ line skill.

Add a short 'Validation checklist' (imports resolved, wire regenerated, make test green, behavior preserved) to give the multi-step refactor an explicit completion gate.

Dimension	Reasoning	Score
Conciseness	Lean body with no padding of concepts Claude already knows; the package tables and pattern diagram are domain-specific knowledge that earns its tokens rather than generic explanation.	3 / 3
Actionability	Concrete, executable guidance — specific commands ('make generate', 'make test'), concrete file paths ('app/common/<domain>.go', 'cmd/*/wire.go', 'adapter/mapping.go'), and a step-by-step procedure rather than abstract direction.	3 / 3
Workflow Clarity	A clear 9-step sequence with a final verification step ('Run tests: make test') is present, but there is no explicit error-recovery feedback loop (validate -> fix -> re-run), which the rubric expects for batch/destructive operations like a cross-codebase refactor.	2 / 3
Progressive Disclosure	Well-organized into clear sections with one well-signaled one-level reference ('See the /service skill'), but at ~92 lines the content is entirely inline in a single file with no bundle files to progressively split detail into.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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: concise, concrete, and complete with an explicit 'Use when' trigger clause. It clearly scopes the skill and distinguishes it from generic code-assistance skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Refactor existing packages toward the standard service/adapter pattern' plus 'restructuring a domain package, splitting a monolithic package, or removing anti-patterns' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Refactor existing packages toward the standard service/adapter pattern') and when (an explicit 'Use when restructuring a domain package, splitting a monolithic package, or removing anti-patterns' clause).	3 / 3
Trigger Term Quality	Includes natural terms a developer would actually say ('refactor', 'restructure', 'split', 'monolithic package', 'anti-patterns') with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	A narrow, well-defined niche (refactoring packages toward a specific service/adapter pattern) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: openmeterio/openmeter
Path: .agents/skills/refactoring/SKILL.md
Commit: 1cdc2cb

Reviewed: 9 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.