CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

refactoring-code

Plan and execute behavior-preserving structural changes to existing code: simplify, decompose, modernize, and reduce technical debt with tests and safe steps. Use when implementation change is requested. Do not use for a review-only finding report, new features, or bug fixes that change behavior.

1.00x
Quality

83%

Does it follow best practices?

Impact

100%

1.00x

1 of 3 eval scenarios. Add 2 more for a full score.

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.

A well-engineered instruction skill: a clearly sequenced workflow with explicit validation and revert feedback loops, concrete risk-tier protocols, and clean progressive disclosure into a complete, well-signposted references/ bundle. Minor deductions for boilerplate-heavy Base Framework/Workflow Integration sections and links to shared/ files that don't exist in the bundle.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — it never explains basic refactoring concepts, defines refactoring in one line, and puts catalogs in references with 'don't front-load them all'. Anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed') fits because the Base Framework section and Optional Workflow Integration section are boilerplate-heavy and could be tightened; it is well above anchor 3's 'several unnecessary explanations'.

4 / 5

Actionability

Concrete, executable guidance throughout: the risk-tier table with per-tier protocols, the smell→pattern map with named catalog transformations, and precise instructions like 'tests green → apply → tests green → checkpoint/commit'. It does not reach anchor 5 because transformation mechanics and examples are deferred to references/patterns.md rather than covered inline (e.g., no worked characterization-test example), leaving minor gaps.

4 / 5

Workflow Clarity

The workflow is clearly sequenced (Phases A–D, steps 1–11 in order) with explicit validation checkpoints ('If tests go red, revert — don't debug a broken refactoring forward', 'confirm every change is structural'), feedback loops for error recovery, and pointers to per-phase checklists in references/workflow.md — a direct match for anchor 5.

5 / 5

Progressive Disclosure

Excellent one-level-deep structure: every reference mentioned in the body exists in references/ (all 7 files), each step names which file to read when needed, and the Reference Map table gives a 'Read / When' navigation index. It falls just short of anchor 5 because the body links to shared/base/*.md policy files and shared/workflow-contract.md that are not present in the bundle — a minor navigation gap against the actual file listing.

4 / 5

Total

17

/

20

Passed

Description

78%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 strong, well-scoped description that states concrete capabilities, explicit use and do-not-use triggers, and excellent distinctiveness from neighboring skills. Its only weakness is that the 'when' clause ('implementation change is requested') is more abstract than natural user trigger phrases, and the most obvious keyword ('refactor') is absent from the description itself.

DimensionReasoningScore

Specificity

The description lists several specific actions ('Plan and execute behavior-preserving structural changes', 'simplify, decompose, modernize, and reduce technical debt with tests and safe steps'), matching anchor 4's 'several specific actions; minor gaps in coverage'. It falls short of anchor 5 because the actions are stated as verbs without fuller concrete coverage (e.g., extract, reorganize, remove duplication appear only in the body), and sits above anchor 3 because it clearly names more than 1-2 concrete actions.

4 / 5

Completeness

Both 'what' (behavior-preserving structural changes: simplify, decompose, modernize, reduce technical debt) and 'when' ('Use when implementation change is requested') are explicit, plus negative triggers. It does not reach anchor 5 because the 'when' clause is abstract ('implementation change is requested') rather than concrete trigger phrases users would naturally say, matching anchor 4's "'when' could be more explicit or specific".

4 / 5

Trigger Term Quality

Good natural keyword coverage — 'simplify', 'modernize', 'reduce technical debt', 'structural changes' are phrases users would say — but a few natural terms are missing, most notably 'refactor'/'refactoring' itself and 'clean up'. This matches anchor 4 ('Good keyword coverage; a few natural terms missing') rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche (behavior-preserving structural change) with explicit negative triggers ('Do not use for a review-only finding report, new features, or bug fixes that change behavior') that sharply separate it from code-review, debugging, and feature skills — minimal conflict risk, matching anchor 5.

5 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 10 missing, 9 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

Noorkhalel/saas-ai-skills

Path

skills/refactoring-code/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.