refactor

Intelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/omo/skills/refactor/SKILL.md

Quality

Content

77%

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

The body is a highly actionable, well-sequenced refactoring workflow with strong validation feedback loops, but it is monolithic and verbose, inlining a long compatibility preamble and Team Mode addendum that could be externalized.

Suggestions

Move the Codex/OpenCode tool-compatibility preamble and the REFACTOR_TEAM_MODE_ADDENDUM into separate reference files (e.g. references/harness-compat.md, references/team-mode.md) and link to them from the main body to improve progressive disclosure.

Trim repeated override caveats (e.g. 'If a code block below conflicts with this section, this section wins' appears multiple times) to a single authoritative statement to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The ~600-line body is operational rather than padded with known concepts, but it is verbose: repeated 'this section wins' caveats, a long tool-surface compatibility preamble, and an inlined Team Mode addendum that re-explains tool usage Claude already knows.	2 / 3
Actionability	It provides concrete, copy-paste-ready examples throughout (LspGotoDefinition, sg --pattern/--rewrite, TodoWrite, git commit, team config JSON) with clearly marked placeholders like [TARGET] and [agent_1_id].	3 / 3
Workflow Clarity	A clearly sequenced 6-phase workflow with explicit per-phase todo markers and mandatory validate-then-fix-then-retry checkpoints ('Post-Step Verification (MANDATORY)', 'STOP AND FIX', abort conditions).	3 / 3
Progressive Disclosure	No bundle files exist and the entire skill is a monolithic single-file ~600-line document; the Team Mode addendum and harness-compatibility preamble are inline content that would benefit from being split into separate reference files.	2 / 3
	Total	10 / 12 Passed

Description

72%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has strong, natural trigger terms and a distinct niche, but its capability statement is generic and padded with the empty modifier 'Intelligent' rather than enumerating concrete refactoring actions.

Suggestions

Replace 'Intelligent refactor command' with concrete capabilities, e.g. 'Extract methods, rename symbols, split modules, and restructure code with LSP and AST-grep verification.'

Keep the trigger list but reframe action words as capabilities so the 'what' is as explicit as the 'when'.

Dimension	Reasoning	Score
Specificity	The description names the refactoring domain and surfaces action words (extract, restructure, simplify) but frames them as triggers rather than concrete capabilities, and 'Intelligent' is an unsupported buzzword.	2 / 3
Completeness	It states what ('refactor command') and provides an explicit 'Triggers:' when-clause, but the 'what' side is thin and padded with the vague adjective 'Intelligent'.	2 / 3
Trigger Term Quality	The trigger list 'refactor, refactoring, cleanup, restructure, extract, simplify, modernize' covers natural verb/noun variations a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Refactoring is a clear niche with distinct triggers unlikely to fire for unrelated skills, though 'cleanup' has minor overlap with lint/format skills.	3 / 3
	Total	10 / 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
skill_md_line_count	SKILL.md is long (777 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/refactor/SKILL.md
Commit: 895b70c

Reviewed: 4 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.