refactor

Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval. Triggers on "/refactor", "restructure vault".

Quality

81%

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

77%

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

A highly actionable, well-sequenced workflow with strong validation feedback loops, but it carries some padded rationale and is monolithic rather than progressively disclosed across reference files.

Suggestions

Trim the Philosophy and /architect-relationship paragraphs to a one-line rationale; the cascade concept is demonstrated by the dimension-to-artifact table without motivational prose.

Move the Phase 2 dimension-to-artifact mapping table and the Phase 5 validation-checks table into a reference file (e.g. references/cascade-mapping.md) and link to it, reducing the monolithic SKILL.md body.

Add a couple of natural trigger variations to the description (e.g. 'reorganize vault', 'config drift') to broaden trigger-term coverage beyond '/refactor' and 'restructure vault'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tables and executable code, but the Philosophy section and the /architect relationship rationale explain motivation Claude could infer, fitting the score-2 anchor of mostly efficient with some unnecessary explanation.	2 / 3
Actionability	It provides copy-paste-ready bash, grep, and sed snippets, concrete file paths, and dimension-to-artifact mapping tables, matching the score-3 anchor of fully executable commands and specific examples.	3 / 3
Workflow Clarity	The five phases are clearly sequenced with an approval checkpoint before execution and an explicit Phase 5 validation block plus batch-level validate-after-each-batch guidance, satisfying the score-3 anchor for destructive/batch operations.	3 / 3
Progressive Disclosure	The file is well-sectioned into phases but is a single 440-line monolith with no bundle reference files, so detail that could be split (dimension mapping, validation checks) stays inline, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 actions and includes explicit trigger guidance, giving it high completeness and distinctiveness. Its only weak spot is trigger-term coverage, which lists just two phrases.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval' — matching the score-3 anchor of several specific concrete actions rather than a single vague domain reference.	3 / 3
Completeness	It explicitly states both what it does and when to use it via the explicit 'Triggers on "/refactor", "restructure vault"' clause, satisfying the score-3 requirement for an explicit trigger rather than capping at 2.	3 / 3
Trigger Term Quality	It includes relevant triggers ('/refactor', 'restructure vault') but offers only two phrases and misses common variations like 'reorganize vault' or 'config drift', fitting the score-2 anchor of some relevant keywords with missing variations.	2 / 3
Distinctiveness Conflict Risk	The vault-restructuring niche with config.yaml/derivation.md comparison and a distinct '/refactor' slash command gives it a clear trigger unlikely to collide with other skills, matching the score-3 anchor.	3 / 3
	Total	11 / 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: agenticnotetaking/arscontexta
Path: skill-sources/refactor/SKILL.md
Commit: 2acfd5c

Reviewed: 3 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.