refactor

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

Quality

61%

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

66%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.

The body is a thorough, well-sequenced refactoring procedure with strong validation and recovery loops, but it is a monolithic wall of text with no progressive disclosure and a broken script reference.

Suggestions

Move the REFACTOR_TEMPLATE and the Team Mode addendum into separate reference files (e.g. references/refactor-template.md, references/team-mode.md) and link to them from SKILL.md.

Either bundle scripts/ast_grep_helper.py or replace the invocations with the plain `sg` CLI commands already shown so no referenced file is missing.

Trim the repeated 'this section wins' override sentences to a single statement near the compatibility table.

Dimension	Reasoning	Score
Conciseness	The ~770-line body is mostly efficient procedural guidance rather than concept padding, but it is long and repeats itself (the 'if a code block below conflicts, this section wins' override appears three times) and could be tightened.	3 / 5
Actionability	It gives concrete LSP calls, ast-grep/sg commands, TodoWrite lists, git commit snippets, and agent-spawn examples; minor gaps are that the core examples use OpenCode-only tools flagged 'do not call literally' and reference a non-existent scripts/ast_grep_helper.py.	4 / 5
Workflow Clarity	Phases 0-6 are explicitly sequenced with an intent-gate checklist, per-step lsp_diagnostics/test/typecheck verification, a STOP-REVERT-DIAGNOSE failure recovery protocol, and abort conditions — full feedback loops for a destructive operation.	5 / 5
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ absent) yet the body inlines large blocks that belong in separate files (the REFACTOR_TEMPLATE and team-mode addendum) and references scripts/ast_grep_helper.py, which does not exist.	2 / 5
	Total	14 / 20 Passed

Description

56%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.

The description pairs an explicit, well-chosen trigger list with a thin, buzzword-tinged capability statement. Trigger quality and distinctiveness are solid, but it never says what the skill actually does.

Suggestions

Replace 'Intelligent refactor command' with concrete actions, e.g. 'Analyzes code, maps dependencies, plans and executes refactors with LSP and AST-grep, verifying tests after each step.'

Drop the buzzword 'Intelligent' and keep the trigger list, which is the strongest part of the description.

Dimension	Reasoning	Score
Specificity	The description names the domain ('refactor command') but lists zero concrete actions, and 'Intelligent' is vague buzzword fluff rather than a capability statement.	2 / 5
Completeness	The 'when' is explicit via the Triggers clause, but the 'what' is weak ('Intelligent refactor command' conveys no concrete behavior), so it does not reach the both-clear level of 4.	3 / 5
Trigger Term Quality	'Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize' gives good natural-keyword coverage including a synonym pair (refactor/refactoring), though a few phrasings users might say are absent.	4 / 5
Distinctiveness Conflict Risk	The trigger set is firmly a refactoring niche (refactor, restructure, extract) with only minor overlap risk from generic terms like 'cleanup' and 'simplify'.	4 / 5
	Total	13 / 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
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: 10f9558

Reviewed: 10 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.