CtrlK
BlogDocsLog inGet started
Tessl Logo

review-and-refactor

Review and refactor code in your project according to defined instructions

67

0.98x
Quality

50%

Does it follow best practices?

Impact

96%

0.98x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/review-and-refactor/SKILL.md

The canonical home for this skill is review-and-refactor in github/awesome-copilot

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 content is concise and reasonably well-structured for a simple instruction skill, but its guidance is abstract rather than concrete and its validation checkpoint is weak for a project-wide refactoring task. Adding specific refactor patterns and stronger verification steps would meaningfully improve it.

Suggestions

Add concrete, actionable guidance such as example refactor patterns, specific commands (e.g., how to run the test suite), and criteria for deciding when a refactor is needed, moving actionability from vague hints to executable steps.

Strengthen the validation loop: require running the test suite (or an equivalent check) and only proceeding when it passes, with an explicit fix-and-retry cycle rather than a conditional 'if the project includes tests'.

Split the single flat task list into distinct Review and Refactor phases so the workflow sequence and checkpoints are clearer.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence with no padding about what refactoring or coding standards are; only minor unnecessary flourishes like "Take a deep breath" keep it from a 5.

4 / 5

Actionability

Guidance is high-level ("review all the code carefully and make code refactorings if needed") with no concrete commands, examples, or specific refactor patterns; the only concrete detail is the instruction file paths, leaving it minimal and abstract.

2 / 5

Workflow Clarity

A numbered 1-4 sequence exists with one weak validation checkpoint ("ensure tests are still passing"), but for a batch refactoring operation the validation is incomplete and conditional, capping it at 3 per the destructive/batch guidance.

3 / 5

Progressive Disclosure

As a simple under-50-line skill with no needed external references, it is organized into clear Role and Task sections; minor gaps in separating review from refactor phases keep it just below 5.

4 / 5

Total

13

/

20

Passed

Description

46%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 states a clear goal (review and refactor code) but lacks trigger guidance, synonym coverage, and specificity, making it generic and high-overlap with other coding skills. It needs an explicit "Use when..." clause and more concrete, distinguishing triggers.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations (e.g., 'Use when the user asks to clean up code, apply coding standards, or refactor a project').

Replace generic verbs with specific actions (e.g., 'apply coding guidelines from .github/instructions, refactor non-compliant code, and run tests') to raise specificity and distinctiveness.

Include natural synonyms and trigger terms users would say (e.g., 'code review', 'clean up', 'coding standards', 'linting', 'Copilot instructions') to improve trigger term quality.

DimensionReasoningScore

Specificity

Names the domain (code) and two concrete actions ("Review" and "refactor") but offers no specifics on refactor types, languages, or scope, matching the anchor for 1-2 concrete actions.

3 / 5

Completeness

A clear "what" is stated (review and refactor code per instructions) but there is no "Use when..." clause or equivalent trigger guidance; per the rubric this caps completeness at 3.

3 / 5

Trigger Term Quality

"review", "refactor", and "code" are reasonably natural terms but no synonyms, file extensions, or richer variations are present, matching the anchor for some relevant keywords with missing variations.

3 / 5

Distinctiveness Conflict Risk

"Review and refactor code" is very broad and overlaps heavily with linting, formatting, and general development skills; the "defined instructions" qualifier narrows it only slightly, fitting the high-overlap-risk anchor.

2 / 5

Total

11

/

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
trackdubllc/Babel-Player-Alpha
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.