oma-refactor

Behavior-preserving refactoring specialist - plans and executes safe incremental restructuring with code smell / SATD / hotspot targeting, characterization-test safety nets, metric and coverage gates, and refactor-only commits. Use for refactor, refactoring, code smell, technical debt, legacy code modernization, extract method, hotspot, and characterization test work.

Quality

88%

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

81%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 well-structured, competent refactoring playbook with a strong validated workflow and concrete tooling, assuming Claude's knowledge of advanced refactoring concepts. The main gaps are mild redundancy between the Structural Flow and Canonical workflow sections and unverified external reference files.

Suggestions

Collapse the 'Structural Flow' and 'Canonical workflow path' sections into a single canonical sequence to remove the overlap and tighten conciseness.

Verify or include the referenced bundle files (resources/definition.md, measurement.md, governance.md) so the progressive-disclosure pointers resolve to real artifacts.

Move the detailed Guardrails list into resources/definition.md (or a dedicated guardrails file) and keep only the inviolable invariants inline, reducing body length.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — it uses domain terms (Mikado, Hyrum, Goodhart, Rule of Three, SATD) without explaining them — but the Structural Flow and Canonical workflow path sections overlap, and the Guardrails restate flow constraints, so minor trimming is possible.	4 / 5
Actionability	Concrete tools and commands are named (Serena `find_symbol`/`rename_symbol`, `uvx lizard` / `uvx radon`, jscodeshift/ast-grep codemods, `refactor:` commit type), giving mostly executable guidance; git forensics commands and the tool registry are deferred to referenced files, leaving minor gaps.	4 / 5
Workflow Clarity	A clear six-scene sequence (PREPARE -> FINALIZE) with an explicit VERIFY checkpoint per transformation, a Mikado revert feedback loop on repeated failure, and a failure/recovery table provides explicit validation steps and error-recovery loops as the top anchor requires.	5 / 5
Progressive Disclosure	Structure is good with a dedicated References section and one-level-deep pointers (`resources/definition.md`, `measurement.md`, `governance.md`, shared core files), but no bundle files are present in the skill directory to verify those references, and some inline material (guardrails, duplicated workflow) could be better split, so it sits just below the top anchor.	4 / 5
	Total	17 / 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 strong, specific description that names concrete refactoring actions and provides a rich 'Use for' trigger clause with natural synonyms. The only weakness is minor overlap risk with adjacent oma skills for broad clean-up requests, which the body (not the description) disambiguates.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'plans and executes safe incremental restructuring', 'code smell / SATD / hotspot targeting', 'characterization-test safety nets', 'metric and coverage gates', 'refactor-only commits' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	It explicitly answers both 'what' (the dash-listed capabilities: restructuring, targeting, safety nets, gates, commits) and 'when' via a concrete 'Use for ...' trigger clause with specific phrases.	5 / 5
Trigger Term Quality	The 'Use for' clause covers comprehensive natural terms including synonyms and variants: 'refactor, refactoring, code smell, technical debt, legacy code modernization, extract method, hotspot, and characterization test', which are phrases users would actually say.	5 / 5
Distinctiveness Conflict Risk	The 'behavior-preserving refactoring' niche is clearly distinct with dedicated triggers, but there is minor overlap risk with closely related skills (debug, qa, architecture) for generic 'clean up / modernize code' requests; a 5 would require minimal conflict risk, and the description alone does not fully separate those boundaries.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: .agents/skills/oma-refactor/SKILL.md
Commit: 032c988

Reviewed: 2 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.