CtrlK
BlogDocsLog inGet started
Tessl Logo

code-refactoring-refactor-clean

You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/code-refactoring-refactor-clean/SKILL.md

The canonical home for this skill is jbvc/code-refactoring-refactor-clean

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The body is concise and well-organized with clear use/non-use sections, but it stays at the directive level without executable code or explicit validation checkpoints, and its single referenced bundle file does not actually exist. Strengthening actionability and fixing the broken reference would lift the weakest dimensions.

Suggestions

Add at least one concrete, executable example (e.g. a small before/after refactor snippet or a command like running the test suite after each slice).

Make the validation loop explicit: 'run tests; if failing, fix and re-run; only proceed when green' rather than the implicit Safety note.

Fix the broken reference — create resources/implementation-playbook.md or correct the path so the signaled progressive-disclosure file actually exists.

DimensionReasoningScore

Conciseness

The body is lean: short bulleted sections, no padding, no explanation of concepts Claude already knows, and every line earns its place; the brief restatement of the persona is the only mild excess.

3 / 3

Actionability

It lists useful directive steps ('Assess code smells', 'Apply changes in small slices') but provides no concrete code, commands, or worked example — it describes the process rather than giving executable guidance, matching the score-2 anchor.

2 / 3

Workflow Clarity

The Instructions are sequenced but there are no explicit validation checkpoints; the Safety note 'ensure tests pass' is implicit rather than a structured validate->fix->retry loop, so per the rubric this stays at 2.

2 / 3

Progressive Disclosure

It signals a one-level-deep reference (resources/implementation-playbook.md) for detail, which is good structure, but that referenced file does not exist in the bundle — the path is also inconsistent (body says 'resources/' while the path uses 'resources/'), so navigation is not cleanly realized.

2 / 3

Total

9

/

12

Passed

Description

50%

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 clearly names the refactoring/clean-code domain and its goals, but it reads as a capability statement with no explicit 'Use when...' trigger guidance and only moderately natural trigger terms. Specificity and completeness are capped by the absence of concrete actions and an explicit when-clause.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers such as 'reduce duplication', 'simplify tangled code', or 'pay down technical debt'.

Replace abstract goals ('improve quality, maintainability, performance') with concrete refactoring actions like 'extract methods, split large classes, remove duplication, simplify conditionals'.

Trim jargon ('SOLID design patterns') in favor of phrasings users actually say to reduce overlap with general coding skills.

DimensionReasoningScore

Specificity

Names the domain and some concrete actions ('refactor the provided code to improve its quality, maintainability, and performance') but these are abstract goals rather than the multiple specific refactor actions (e.g. extract method, reduce duplication) seen at the top anchor.

2 / 3

Completeness

It clearly states what the skill does but the 'when' is never explicit in the description — there is no 'Use when...' clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Terms like 'refactoring', 'clean code', 'SOLID', and 'code smells' are relevant, but the description lacks the common variations a user would naturally say (e.g. 'reduce duplication', 'simplify code', 'technical debt') and leans on jargon rather than natural phrasing.

2 / 3

Distinctiveness Conflict Risk

It targets a reasonably distinct niche (refactoring/clean code) but the phrasing is broad enough that it could overlap with general coding or code-review skills; triggers are not sharp enough to fully separate it.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-skills
Reviewed

Table of Contents

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.