refactoring-analysis

Audits a codebase for refactoring opportunities using Martin Fowler's code smell and technique catalog — long functions, duplication, high coupling, complex conditionals, primitive obsession — and writes a prioritized report to docs/_refacs/. Use when auditing code quality, planning a refactoring sprint, or reviewing architectural health; not for style/formatting, performance, or security audits.

Quality

94%

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

96%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 tightly structured, actionable skill with explicit per-step completion gates and a verification checklist step. The only gap is a reference to a non-existent checklists/analysis-checklist.md file.

Suggestions

Add the missing checklists/analysis-checklist.md file referenced in step 7, or repoint step 7 to an existing checklist path.

Optionally confirm the SOLID-pass applicability gate (step 5) mirrors the gate text in references/solid-ddd-context.md to avoid drift.

Dimension	Reasoning	Score
Conciseness	Lean 8-step body with crisp 'Done when' checkpoints, no concept re-explanation, no padding; every step earns its tokens and assumes Claude's competence.	5 / 5
Actionability	Concrete executable guidance throughout: file:line ranges, severity tiers, impact x frequency / effort ranking, the docs/_refacs/<YYYYMMDD>-<slug>.md output path, and named bundle references; absence of code is not penalized for this actionable instruction-only skill.	5 / 5
Workflow Clarity	Eight clearly numbered steps each with an explicit 'Done when' checkpoint, capped by a verification step that walks checklists/analysis-checklist.md and ships 'only once every item passes'.	5 / 5
Progressive Disclosure	Well-split one-level-deep references (code-smells-catalog.md, refactoring-techniques.md, solid-ddd-context.md, refactoring-report-template.md) signaled at the right steps, but step 7 references checklists/analysis-checklist.md which is not present in the bundle.	4 / 5
	Total	19 / 20 Passed

Description

92%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, specific description with clear what/when guidance and helpful negative scoping. Minor room only in trigger-term synonym coverage (e.g., 'tech debt').

Dimension	Reasoning	Score
Specificity	Names concrete actions (audit for refactoring opportunities, write a prioritized report to docs/_refacs/) plus a specific smell catalog (long functions, duplication, high coupling, complex conditionals, primitive obsession), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what (audit + prioritized report) and when (Use when auditing code quality, planning a refactoring sprint, or reviewing architectural health), with concrete trigger phrases and explicit exclusions.	5 / 5
Trigger Term Quality	Good natural trigger phrases ('auditing code quality', 'planning a refactoring sprint', 'reviewing architectural health') but misses common synonyms like 'tech debt'; no file-extension triggers apply.	4 / 5
Distinctiveness Conflict Risk	Martin Fowler's refactoring catalog plus the docs/_refacs/ output form a clear niche, and the explicit 'not for style/formatting, performance, or security audits' exclusion minimizes conflict risk.	5 / 5
	Total	19 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: compozy/compozy
Path: .agents/skills/refactoring-analysis/SKILL.md
Commit: 1881a9f

Reviewed: ~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.