CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

codebase-cleanup-refactor-clean

Refactor code with clean code principles, SOLID design patterns, and modern software engineering practices to improve quality, maintainability, and performance. Use when cleaning up or restructuring existing code.

Quality

69%

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/codebase-cleanup-refactor-clean/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

A lean, well-sectioned instruction-only skill with sensible safety constraints and a defined output format, and no padding that explains known concepts. Its weaknesses are abstract, non-executable instructions, implicit validation checkpoints without feedback loops, and a Resources reference to a playbook file that is missing from the bundle.

Suggestions

Fix the broken reference: resources/implementation-playbook.md does not exist in the bundle — either add the playbook file (typically under references/) or remove the two pointers to it.

Make Instructions executable: specify how to identify refactor candidates (duplication, long functions, high coupling), and give the concrete validation command(s) to run per step instead of the generic "Validate with tests and targeted regression checks".

Convert the flat instruction bullets into a sequenced workflow with explicit validation gates (e.g. "after each step, run the test suite; fix and re-run before proceeding") to add the missing feedback loop for batch code changes.

DimensionReasoningScore

Conciseness

Quote: "You are a code refactoring expert specializing in clean code principles..." and "The user needs help refactoring code to make it cleaner, more maintainable...". The body is short and assumes Claude's knowledge (never explains SOLID or refactoring concepts), but the persona opener and the Context/Requirements sections largely restate the frontmatter description — minor trimmable padding matching anchor 4 rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Quotes: "Identify high-impact refactor candidates and risks", "Validate with tests and targeted regression checks", "If detailed patterns are required, open resources/implementation-playbook.md". Some concrete guidance structures the task, but no step carries criteria, commands, or examples, and the deferred detail points to a file absent from the bundle — incomplete guidance fitting anchor 3 rather than anchor 4's mostly-executable level.

3 / 5

Workflow Clarity

Quotes: "Identify high-impact refactor candidates" → "Break work into small, testable steps" → "Apply changes" → "Validate with tests and targeted regression checks". A logical sequence with validation mentioned exists, but checkpoints are implicit rather than explicit gates and there is no validate-fix-retry feedback loop for batch code changes, matching anchor 3 ("sequence present but checkpoints missing or implicit").

3 / 5

Progressive Disclosure

Quote: "resources/implementation-playbook.md for detailed patterns and examples". Sections are well organized and the single reference is clearly signaled in a dedicated Resources section, but that file does not exist in the bundle (no resources/, references/, scripts/, or assets/ directories exist), leaving the promised detail unreachable — more than anchor 4's "minor organization gaps", though above anchor 2's buried-reference/inlined-content problems.

3 / 5

Total

13

/

20

Passed

Description

66%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.

A solid, honest third-person description that explicitly states what the skill does and when to use it, with reasonably natural trigger terms. Its main weaknesses are thin concrete-action coverage (one broad action plus methodology labels) and a broad middle section that blurs its niche against similar code-quality skills.

Suggestions

Replace the single broad action with several concrete ones, e.g. "Remove duplication, extract and simplify functions, apply SOLID principles, reduce coupling" instead of just "Refactor code".

Add natural trigger variations users actually say, such as "technical debt", "code smells", "legacy code", or "improve code quality", to the Use-when clause.

Sharpen the "when" clause (e.g. "Use when the user asks to clean up, refactor, or restructure existing code") to reduce overlap with code-review and general code-improvement skills.

DimensionReasoningScore

Specificity

Quotes: "Refactor code", "cleaning up or restructuring existing code", "SOLID design patterns". It names the domain with one broad action, where "cleaning up" and "restructuring" are near-synonyms rather than distinct capabilities and "SOLID design patterns" is a methodology label, not the several specific concrete actions anchor 4 requires.

3 / 5

Completeness

Quotes: "Refactor code with clean code principles... to improve quality, maintainability, and performance" (what) and "Use when cleaning up or restructuring existing code" (when). Both are explicit, but the "when" is a single general condition matching anchor 4's "'when' could be more explicit or specific" rather than anchor 5's concrete trigger phrases.

4 / 5

Trigger Term Quality

Quotes: "Refactor code", "clean code", "cleaning up", "restructuring existing code". Good natural keyword coverage matching anchor 4, but common variations users say ("technical debt", "code smells", "tidy up", "improve code quality") are missing, short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Quotes: "cleaning up or restructuring existing code" is somewhat specific, but broad phrases like "modern software engineering practices" and "improve quality, maintainability, and performance" leave overlap risk with adjacent code-review and code-cleanup skills, fitting anchor 3 ("could still overlap with similar skills").

3 / 5

Total

14

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

rmyndharis/antigravity-skills

Path

skills/codebase-cleanup-refactor-clean/SKILL.md

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.