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.

48

Quality

52%

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/code-refactoring-refactor-clean/SKILL.md

The canonical home for this skill is code-refactoring-refactor-clean in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-structured into clear sections with a sensible sequenced workflow and verification checkpoints, but it carries minor redundancy (repeating the description) and its single external reference points to a non-existent `resources/` path rather than the expected `references/` bundle layout.

Suggestions

Remove the verbatim repeat of the description on line 11 and trim the "Context" section to eliminate redundancy.

Make the external reference resolvable: use `references/implementation-playbook.md` and add the file under `references/`, or remove the pointer if no such bundle is intended.

Add one concrete worked example of an incremental refactor slice (before/after) to lift actionability beyond high-level directives.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence, but it repeats the description verbatim on line 11 and includes a "Context" section ("The user needs help refactoring code...") that restates known intent, fitting the "mostly efficient but includes some unnecessary explanation" anchor.

3 / 5

Actionability

Instructions give concrete directives ("Assess code smells, dependencies, and risky hotspots", "Apply changes in small slices and keep behavior stable") but stop at high-level guidance with no specific techniques, commands, or worked examples, matching the "some concrete guidance but incomplete" anchor; absence of code is acceptable for an instruction-only skill.

3 / 5

Workflow Clarity

A clear ordered sequence is present (assess → plan → apply in small slices → update tests and verify regressions) with explicit verification steps ("verify regressions", "ensure tests pass") in Instructions and Safety, fitting the "clear sequence with most checkpoints present" anchor; the destructive-operation cap does not apply because validation steps are present.

4 / 5

Progressive Disclosure

Good section structure (Use when / Do not use / Instructions / Safety / Output Format / Resources) with a clearly signaled one-level-deep reference to the playbook, but the referenced path is `resources/implementation-playbook.md` while no bundle directory exists and the expected layout is `references/`, a minor organization gap that keeps it below 5.

4 / 5

Total

14

/

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 clearly states the domain and core actions but is written in second person ("You are a code refactoring expert"), which violates the third-person-voice rule and incurs a specificity penalty, and it omits any explicit "Use when..." trigger guidance, capping completeness at 3.

Suggestions

Rewrite in third person: e.g. "Analyzes and refactors code to improve quality, maintainability, and performance using clean-code and SOLID principles."

Add an explicit trigger clause, e.g. "Use when refactoring tangled or hard-to-maintain code, reducing duplication, or improving testability."

Include natural synonym triggers users actually say ("clean up", "restructure", "simplify code") to broaden keyword coverage.

DimensionReasoningScore

Specificity

Quotes "code refactoring expert specializing in clean code principles, SOLID design patterns" names the domain with actions "Analyze and refactor the provided code", which anchors at 3, but the second-person voice ("You are a code refactoring expert") triggers the mandatory -1 specificity penalty, dropping it to 2.

2 / 5

Completeness

Has a clear "what" ("Analyze and refactor the provided code to improve its quality, maintainability, and performance") but no "Use when..." trigger clause, so per the guideline a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Natural keywords present ("refactor", "refactoring", "clean code") but missing common variations/synonyms users say like "clean up", "tidy", or "restructure", matching the anchor for some relevant keywords with missing synonyms.

3 / 5

Distinctiveness Conflict Risk

Refactoring/clean-code/SOLID is a somewhat specific niche, but the broad tail "modern software engineering best practices" creates overlap risk with general coding skills, fitting the "somewhat specific but could still overlap" anchor rather than the clearly-distinct level 4.

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.