CtrlK
BlogDocsLog inGet started
Tessl Logo

safe-refactoring

Execute behavior-preserving or intentionally scoped refactors safely. Use this for multi-file renames, component/service extraction, state-management changes, API migrations, concurrency refactors, or any request where unrelated user work and subtle contracts must be preserved.

67

Quality

80%

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 ./ruoyi-modules/ruoyi-chat/src/main/resources/coding-harness/skills/safe-refactoring/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 an efficient, well-sequenced instruction set for safe refactoring with explicit validation and a feedback loop, respecting Claude's intelligence without padding. It is highly actionable as procedural guidance and clearly structured, with only minor room for executable command examples and optional deeper-reference pointers.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: every line is an actionable directive with no padded explanations of what refactoring is or how tools work, and every token earns its place.

5 / 5

Actionability

Guidance is concrete and directive ("Use expected content hashes", "Run the smallest fast check that catches syntax/type errors") with specific check types named, but it provides procedural instructions rather than copy-paste executable code or commands, leaving minor gaps.

4 / 5

Workflow Clarity

Three clearly sequenced phases (Before mutation, Mutation rules, Verification loop) with explicit validation checkpoints and a feedback loop ("If verification fails, retain the diagnostic evidence, correct the implementation, and repeat"), plus a completion report that requires evidence — appropriate for a destructive/batch-capable skill.

5 / 5

Progressive Disclosure

Content is well-organized into clear sections of appropriate length with no nested or buried references and no bundle files to misroute; it is a single self-contained overview, which is well-structured though it has no references to point to deeper material.

4 / 5

Total

18

/

20

Passed

Description

75%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 strong: it uses third person, states both what it does and when to use it, and enumerates concrete refactor types as triggers. It is concise and distinct, with only minor gaps in synonym coverage and explicitness of the when-clause.

Suggestions

Add a few natural synonyms/shorthand triggers (e.g., "rename", "move code", "split module") to broaden trigger-term coverage.

Tighten the when-clause by separating "use when" triggers from the scope-preservation constraint so the trigger guidance reads more explicitly.

DimensionReasoningScore

Specificity

Names several concrete refactor types (multi-file renames, component/service extraction, state-management changes, API migrations, concurrency refactors) but stops short of listing the actual operations performed, leaving minor coverage gaps relative to a fully comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ("Execute behavior-preserving or intentionally scoped refactors safely") and when ("Use this for...") with concrete triggers, but the when-clause is a single enumeration that could be slightly more explicit about scope boundaries.

4 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ("multi-file renames", "API migrations", "refactors") with good coverage, though it lacks a few common synonyms or shorthand variations like "rename" or "move code".

4 / 5

Distinctiveness Conflict Risk

Targets a fairly distinct niche (behavior-preserving refactors with unrelated-user-work preservation) that is unlikely to fire for unrelated skills, with only minor overlap risk against a generic "coding" skill.

4 / 5

Total

16

/

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
ageerle/ruoyi-ai
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.