CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-cleanup-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.

45

Quality

47%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/codebase-cleanup-refactor-clean/SKILL.md

The canonical home for this skill is codebase-cleanup-refactor-clean in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 cleanly sectioned into use/avoid/context/instructions/safety/output, but it duplicates the frontmatter description, offers only high-level refactor guidance, and points to a playbook file that is not present in the bundle. Validation is mentioned but lacks an explicit feedback-loop checkpoint.

Suggestions

Remove the verbatim repetition of the frontmatter description from the body's opening paragraph and tighten the 'Context' section to eliminate redundancy.

Name concrete refactor techniques (e.g. extract method, inline variable, extract class) or link to a working example so the guidance is actionable rather than directional.

Make the validation step an explicit checkpoint with a feedback loop ('run tests; if any fail, fix and re-run until green before proceeding') and either provide resources/implementation-playbook.md or remove the broken reference.

DimensionReasoningScore

Conciseness

The body is mostly efficient and section-organized, but repeats the frontmatter description verbatim as the opening paragraph and includes a padded 'Context' restating the same intent, fitting anchor 3.

3 / 5

Actionability

Instructions give directional steps ('Identify high-impact refactor candidates', 'Break work into small, testable steps', 'Validate with tests') but name no concrete refactor patterns or examples, leaving guidance incomplete per anchor 3.

3 / 5

Workflow Clarity

A rough sequence exists (identify -> break down -> apply -> validate) and a validation step is present, but there is no explicit checkpoint or feedback loop (validate -> fix -> re-validate), matching anchor 3.

3 / 5

Progressive Disclosure

Sections are reasonably organized and a one-level reference is signaled in the Resources section, but the referenced path 'resources/implementation-playbook.md' does not exist in the bundle (no references/scripts/assets dirs) and uses a non-standard folder name, creating a navigation defect per anchor 3.

3 / 5

Total

12

/

20

Passed

Description

45%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 states a clear 'what' (analyze and refactor code) but omits any explicit 'when' trigger guidance and uses second-person voice, both of which limit its score. It is distinguishable but generic enough to risk overlap with related skills.

Suggestions

Rewrite in third person and append an explicit trigger clause, e.g. 'Use when the user asks to clean up, refactor, or reduce duplication in an existing codebase.'

Add concrete action verbs and natural synonyms users say ('clean up', 'simplify', 'remove duplication', 'pay down tech debt') to improve specificity and trigger coverage.

Sharpen the niche to reduce conflict risk, e.g. call out large-codebase accumulated-debt cleanup rather than general refactoring.

DimensionReasoningScore

Specificity

Names the domain (clean code, SOLID, refactoring) and two concrete actions ('Analyze and refactor the provided code'), matching anchor 3, but reduced by 1 for the second-person voice ('You are a code refactoring expert') per the rubric's voice penalty.

2 / 5

Completeness

Clearly states what it does ('Analyze and refactor the provided code to improve its quality, maintainability, and performance') but has no 'Use when...' clause or explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant keywords ('code refactoring', 'clean code', 'SOLID design patterns') a developer might say, but misses common variations like 'clean up code', 'simplify', or 'remove duplication', fitting anchor 3.

3 / 5

Distinctiveness Conflict Risk

The refactoring/clean-code niche is somewhat specific but overlaps broadly with code-review and simplify skills and lacks a distinguishing trigger, matching anchor 3.

3 / 5

Total

11

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.