CtrlK
BlogDocsLog inGet started
Tessl Logo

gitnexus-refactoring

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"

73

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a strong, safety-conscious refactoring guide with executable tool calls, explicit validation loops, and clear checklists. The main weaknesses are a few abstract steps in the Extract/Split checklists and some dense prose in the repo-binding section.

Suggestions

Make the Extract Module and Split Function checklists more concrete by adding example tool calls (e.g., context/impact invocations with real parameters) alongside the abstract steps like "Define new module interface".

Tighten the "Bind the repository first" paragraph into bullet form so the repo-binding safety rules scan faster without losing the rationale.

Consider splitting the Tools reference signatures and Risk Rules table into a separate REFERENCE.md if the skill grows, to keep SKILL.md as an overview.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence (no generic refactoring primer), but the "Bind the repository first" prose is dense and could be tightened in a few places without losing the safety rationale.

4 / 5

Actionability

Tool calls (rename, impact, detect_changes, cypher) are concrete and copy-paste ready, but the Extract/Split checklists include abstract steps like "Define new module interface" and "Group callees by responsibility" that are not executable.

4 / 5

Workflow Clarity

Clear numbered workflow (0–4) plus per-refactor checklists with explicit validation checkpoints (preview → review paths → apply → detect_changes → run tests) and feedback loops for the destructive dry_run:false step.

5 / 5

Progressive Disclosure

Well-organized into clear sections (When to Use, Bind repo, Workflow, Checklists, Tools, Risk Rules, Example) with no nested references; no bundle files exist, and the self-contained structure is appropriate, though the Tools/Risk Rules block could conceptually be split.

4 / 5

Total

17

/

20

Passed

Description

100%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 is exemplary: it names concrete actions, supplies natural user-facing trigger phrases, covers both what and when, and occupies a distinct niche. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "rename, extract, split, move, or restructure code" — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what (rename/extract/split/move/restructure code safely) and when ("Use when the user wants to...") with concrete trigger phrases, in third person.

5 / 5

Trigger Term Quality

Examples quote the exact natural phrases users say ("Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"), with strong synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Refactoring is a clear, well-scoped niche with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
abhigyanpatwari/GitNexus
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.