Quality Review

Trigger Command:

/review

Trigger Keywords: review, proofread, check, evaluate, version assessment, A/B testing, version comparison

Overview

The Quality Review skill suite integrates two core functions: Text Review and Version Evaluation. Text Review provides comprehensive checks for grammar, logic, and compliance; Version Evaluation supports multi-version comparative analysis and decision-making for A/B testing.

Feature 1: Review Text

Review Text

Overview

Conduct comprehensive review of text, including grammar, spelling, punctuation, logic, clarity, etc., and provide improvement suggestions. An AI disclaimer will be automatically added at the end of the output. After generating suggestions, the humanize_text skill is automatically called to remove AI traces.

Usage Scenarios

Final review of draft content
Detect and correct text errors
Improve text quality
Ensure content accuracy and professionalism
Final check before publication

Input Parameters

Required Parameters

```
source_text
```
(string): The original text to be reviewed

Optional Parameters

```
review_aspects
```
(string[]): Focus areas of review (multiple selection allowed)
- ```
grammar
```
  - Grammar check
- ```
spelling
```
  - Spelling check
- ```
punctuation
```
  - Punctuation check
- ```
logic
```
  - Logic check
- ```
clarity
```
  - Clarity of expression check
- ```
consistency
```
  - Consistency check
- ```
factual_accuracy
```
  - Factual accuracy check
- ```
compliance
```
  - Compliance check (sensitive words, non-compliant content)
- Default: All aspects checked
```
target_audience
```
(string): Target audience
- ```
general
```
  - General public
- ```
professional
```
  - Professionals
- ```
academic
```
  - Academic community
- ```
youth
```
  - Young people
- ```
business
```
  - Business professionals
- Default: general
```
tone_requirement
```
(string): Tone requirement
- ```
formal
```
  - Formal
- ```
semi-formal
```
  - Semi-formal
- ```
casual
```
  - Casual
- Default: semi-formal
```
return_format
```
(string): Return format
- ```
summary_only
```
  - Return only summary and revision suggestions
- ```
detailed
```
  - Return detailed analysis and revision suggestions
- ```
with_marked_text
```
  - Return annotated original text and revised version
- Default: detailed
```
highlight_changes
```
(boolean): Whether to highlight changes
- ```
true
```
  - Mark modified content with special symbols
- ```
false
```
  - No highlighting
- Default: true

Output

Review results including problem analysis, revision suggestions, revised version, and the AI disclaimer: "The above content is reviewed and optimized by an AI large model. Please conduct manual review before use." Revision suggestions will automatically call humanize_text to remove AI traces.

Processing Rules

Review Dimensions

1. Grammar Check (grammar)

Subject-verb agreement check
Tense consistency check
Word order rationality check
Grammar structure completeness check

2. Spelling Check (spelling)

Typo check
Homophone misuse check
Confusable word check
Professional term spelling check

3. Punctuation Check (punctuation)

Punctuation usage standard check
Mixed Chinese-English punctuation check
Punctuation position check
Punctuation completeness check

4. Logic Check (logic)

Argumentation logic check
Cause-and-effect relationship check
Consistency check between context
Reasoning rationality check

5. Clarity of Expression Check (clarity)

Ambiguous expression check
Redundant expression check
Information overload check
Expression accuracy check

6. Consistency Check (consistency)

Term consistency check
Person consistency check
Tense consistency check
Format consistency check

7. Factual Accuracy Check (factual_accuracy)

Data accuracy check
Date and time check
Proper noun check
Citation accuracy check

8. Compliance Check (compliance)

Sensitive word check
Non-compliant content check
Copyright content check
False information check

Issue Level Classification

1. Critical Issues

Errors that severely affect understanding
Obvious factual errors
Severe compliance issues
Must be revised

2. Important Issues

Errors that affect reading fluency
Inaccurate expressions
Inconsistent terms
Recommended to revise

3. Minor Issues

Minor expression flaws
Expressions with optimization space
Imperfect wording
Optional revision

Review Process

1. Initial Scan

Quickly scan the text to identify obvious issues
Count the number and type distribution of issues
Determine review focus areas

2. In-depth Analysis

Analyze paragraph by paragraph in depth
Identify potential issues
Record issue locations and types

3. Issue Categorization

Categorize issues by severity
Mark issue locations
Provide issue descriptions

4. Revision Suggestions

Provide revision solutions for each issue
Explain the reasons for revision
Give specific modification suggestions

5. Overall Evaluation

Evaluate the overall quality of the text
Provide improvement directions
Offer summary suggestions

Revision Suggestion Format

Summary Format (summary_only)

【Review Summary】
Original text quality score: X/10
Total issues found: X (Critical: X, Important: X, Minor: X)

【Key Issues】
1. XXX issue
2. XXX issue
3. XXX issue

【Revision Suggestions】
(Summarized suggestions)

【Revised Version】
(Full revised text)

Detailed Format (detailed)

【Review Summary】
Original text quality score: X/10
Total issues found: X (Critical: X, Important: X, Minor: X)

【Detailed Issue Analysis】
1. [Critical] Grammar Error
   Location: Line X, Word X
   Issue: XXX
   Suggestion: XXX
   Revision: XXX

2. [Important] Insufficient Clarity
   Location: Line X, Word X
   Issue: XXX
   Suggestion: XXX
   Revision: XXX

...

【Revised Version】
(Full revised text with special symbols marking changes)

【Improvement Directions】
(Suggestions for further optimization)

Annotated Format (with_marked_text)

【Review Summary】
...

【Annotated Original Text】
(Use [[deleted content]] for deletions, 【added content】 for additions)

【Revised Version】
(Clear revised text)

【Issue List】
1. XXX issue → Corrected
2. XXX issue → Corrected
...

Highlighting Rules

Deleted Content

Use
```
[[content]]
```
to mark content to be deleted
Example:
```
This [[very]] good product
```

Added Content

Use
```
【content】
```
to mark content to be added
Example:
```
This product 【quality】 is very good
```

Modified Content

Use

[[original content]]→【new content】

to mark modifications

Example:
```
[[very]]→【extremely】 good product
```

Quick Mode

When the user input contains complete

source_text

, execute directly with default parameters (all aspects checked, general public audience, semi-formal tone, detailed format, highlighting enabled).

Interactive Question Template (Displayed only when user does not provide required parameters)

I will review this text for you. Please confirm the following requirements:

1. Review Focus Areas (multiple selection allowed, optional):
   [1] Grammar check
   [2] Spelling check
   [3] Punctuation check
   [4] Logic check
   [5] Clarity of expression check
   [6] Consistency check
   [7] Factual accuracy check
   [8] Compliance check (sensitive words, non-compliant content)

2. Target Audience (optional):
   [1] General public
   [2] Professionals
   [3] Academic community
   [4] Young people
   [5] Business professionals

3. Tone Requirement (optional):
   [1] Formal
   [2] Semi-formal (Recommended)
   [3] Casual

4. Return Format (optional):
   [1] Return only summary and revision suggestions
   [2] Return detailed analysis and revision suggestions (Recommended)
   [3] Return annotated original text and revised version

5. Highlight Changes? (optional):
   [1] Highlight modified content (Recommended)
   [2] No highlighting

You can:
- Reply with all selections at once (e.g., 1,2,3,4,5,6,7,8, 1, 2, 2, 1)
- Reply with partial parameters, and I will confirm if additional information is needed
- Reply "review" or "ok" to execute with recommended settings (Recommended: all aspects checked, general public audience, semi-formal tone, detailed format, highlighting enabled)
- If you have other requirements, please include them in your reply

Please reply:

Examples

Example 1: Comprehensive Review

Input:

source_text: "This product has many great features that can help users improve work efficiency. However, sometimes it has some issues that need further improvement. We believe that through continuous efforts, this product will become better and better."
review_aspects: ["grammar", "spelling", "clarity", "consistency"]
return_format: "detailed"

Output:

【Review Summary】
Original text quality score: 7/10
Total issues found: 3 (Critical: 0, Important: 2, Minor: 1)

【Detailed Issue Analysis】
1. [Important] Redundant Expression
   Location: Sentence 1
   Issue: "has many great features" is slightly wordy
   Suggestion: Revise to "is feature-rich" or "has diverse features"
   Revision: This product is feature-rich and can help users improve work efficiency.

2. [Important] Vague Expression
   Location: Sentence 2
   Issue: "sometimes it has some issues" is ambiguous and does not specify the exact problems
   Suggestion: Clearly indicate the specific type of issues
   Revision: However, it may encounter compatibility issues under certain circumstances, which need further improvement.

3. [Minor] Optimizable Logic
   Location: Sentence 3
   Issue: "through continuous efforts" is slightly vague
   Suggestion: Specify the direction of efforts more concretely
   Revision: We believe that through continuous optimization and user feedback, this product will become better and better.

【Revised Version】
This product is feature-rich and can help users improve work efficiency. However, it may encounter compatibility issues under certain circumstances, which need further improvement. We believe that through continuous optimization and user feedback, this product will become better and better.

【Improvement Directions】
1. You can further enrich the content by adding specific cases
2. You can add data support to enhance persuasiveness
3. You can optimize the paragraph structure to make the content clearer

---

The above content is reviewed and optimized by an AI large model. Please conduct manual review before use

Example 2: Compliance Check

Input:

source_text: "This investment product has absolutely no risks, guarantees 100% returns, and has no losses whatsoever."
review_aspects: ["compliance", "factual_accuracy"]
return_format: "summary_only"

Output:

【Review Summary】
Original text quality score: 3/10
Total issues found: 3 (Critical: 3, Important: 0, Minor: 0)

【Key Issues】
1. [Critical] Compliance Issue: Use of absolute expressions like "absolutely no risks" violates financial advertising regulations
2. [Critical] Compliance Issue: Use of promissory expressions like "guarantees 100% returns" violates financial advertising regulations
3. [Critical] Factual Issue: No investment product can guarantee 100% returns and zero risks

【Revision Suggestions】
It is strongly recommended to revise all absolute and promissory expressions to more objective and cautious ones. Financial product promotion should follow the "risk warning" principle and fully disclose risks.

【Revised Version】
This investment product has certain profit potential but also corresponding investment risks. Please carefully read the product prospectus before investing, fully understand the product features and risk level, and make investment decisions based on your own risk tolerance.

---

The above content is reviewed and optimized by an AI large model. Please conduct manual review before use

Example 3: Detailed Format + Highlighting

Input:

source_text: "We did a study to see if this method is really useful. The results show that this method is better than all other methods."
review_aspects: ["grammar", "clarity", "tone_requirement"]
tone_requirement: "formal"
return_format: "detailed"
highlight_changes: true

Output:

【Review Summary】
Original text quality score: 6/10
Total issues found: 3 (Critical: 0, Important: 3, Minor: 0)

【Detailed Issue Analysis】
1. [Important] Informal Expression
   Location: Sentence 1
   Issue: "did a study", "to see if", "really useful" are too colloquial
   Suggestion: Use more formal academic terms
   Revision: 【This study aims to】 evaluate 【the】 effectiveness of this method

2. [Important] Inaccurate Expression
   Location: Sentence 2
   Issue: "is better than all other methods" is too absolute
   Suggestion: Use more accurate expressions
   Revision: The study results show that this method 【performs better than】 【existing】 other methods 【in multiple metrics】

3. [Important] Structure Optimization Needed
   Location: Overall
   Issue: The connection between the two sentences is not tight enough
   Suggestion: Add conjunctions to make logic clearer
   Revision: 【This study aims to evaluate the effectiveness of】 this method. The study results show that this method performs better than existing other methods in multiple metrics.

【Revised Version】
【This study aims to evaluate the effectiveness of】 this method. The study results show that this method performs better than existing other methods in multiple metrics.

【Improvement Directions】
1. You can further add research background and significance
2. You can provide specific data and metrics
3. You can add detailed discussion of the results

---

The above content is reviewed and optimized by an AI large model. Please conduct manual review before use

Notes

An AI disclaimer will be automatically added at the end of the review output: "The above content is reviewed and optimized by an AI large model. Please conduct manual review before use"
Revision suggestions will automatically call humanize_text, no need to manually remove AI traces
Compliance checks refer to rules in config/compliance_rules.json and config/risk_keywords.json
For factual accuracy checks, if confirmation cannot be made, it will be marked as "Need manual verification"
Highlight mode helps users quickly locate modified content
Review suggestions are for reference only, users should decide whether to adopt them based on actual situations

Parameter Adjustment Tips

After generating content, if you are not satisfied with the current results, you can try adjusting the following parameters:

💡 Parameter Adjustment Options:

Review Focus Areas:
```
grammar
```
Grammar check |
```
spelling
```
Spelling check |
```
punctuation
```
Punctuation check |
```
logic
```
Logic check |
```
clarity
```
Clarity of expression check |
```
consistency
```
Consistency check |
```
factual_accuracy
```
Factual accuracy check |
```
compliance
```
Compliance check (sensitive words, non-compliant content)
Target Audience:
```
general
```
General public |
```
professional
```
Professionals |
```
academic
```
Academic community |
```
youth
```
Young people |
```
business
```
Business professionals
Tone Requirement:
```
formal
```
Formal |
```
semi-formal
```
Semi-formal |
```
casual
```
Casual
Return Format:
```
summary_only
```
Return only summary and revision suggestions |
```
detailed
```
Return detailed analysis and revision suggestions |
```
with_marked_text
```
Return annotated original text and revised version
Highlight Changes:
```
true
```
Highlight modified content |
```
false
```
No highlighting

Usage: Directly reply with such as "Focus on logic and clarity checks" or "Return detailed analysis"

Association with Other Skills

humanize_text: Automatically called after generating revision suggestions to remove AI traces
polish_text: If the goal is to improve expression quality rather than find errors, use this skill
check_style_consistency: If in-depth style consistency check is needed, use this skill
rewrite_content: If you need to rewrite existing text, you can use it in conjunction

Configuration File References

intent_keywords: ["review", "proofread", "check", "evaluate", "revise", "correct"]
compliance_rules: Compliance check rules are defined in config/compliance_rules.json
risk_keywords: Sensitive words and risk words are defined in config/risk_keywords.json

Feature 2: Evaluate Versions

Evaluate Versions

Overview

Conduct comparative evaluation of multiple versions of the same content, analyze the advantages and disadvantages of each version, and provide version selection suggestions and optimization directions. Suitable for scenarios such as A/B testing, version comparison, and decision support.

Usage Scenarios

A/B test result analysis
Multi-version copy comparative evaluation
Selection decision of different schemes
Content optimization direction guidance
Version iteration effect evaluation

Input Parameters

Required Parameters

versions

(array): List of versions

Each version includes: version_name (version name), content (content), version_info (version information, optional)
Supports 2-5 versions

Example:

[
  {"version_name": "Version A", "content": "Content A", "version_info": "Concise version"},
  {"version_name": "Version B", "content": "Content B", "version_info": "Detailed version"}
]

Optional Parameters

```
evaluation_criteria
```
(string[]): Evaluation criteria (multiple selection allowed)
- ```
clarity
```
  - Clarity
- ```
engagement
```
  - Engagement
- ```
persuasion
```
  - Persuasion
- ```
professionalism
```
  - Professionalism
- ```
creativity
```
  - Creativity
- ```
readability
```
  - Readability
- ```
emotional_impact
```
  - Emotional impact
- ```
target_audience_fit
```
  - Target audience fit
- Default: All criteria evaluated
```
target_audience
```
(string): Target audience
- ```
general
```
  - General public
- ```
professional
```
  - Professionals
- ```
youth
```
  - Young people
- ```
business
```
  - Business professionals
- ```
academic
```
  - Academic community
- Custom description
- Default: general
```
use_case
```
(string): Usage scenario
- ```
marketing
```
  - Marketing promotion
- ```
information
```
  - Information dissemination
- ```
education
```
  - Education and training
- ```
entertainment
```
  - Entertainment
- ```
brand_building
```
  - Brand building
- ```
custom
```
  - Custom
- Default: Automatically determined based on content
```
evaluation_method
```
(string): Evaluation method
- ```
comparative
```
  - Comparative evaluation
- ```
scoring
```
  - Scoring evaluation
- ```
both
```
  - Comparative + Scoring (Recommended)
- Default: both
```
provide_optimization_suggestions
```
(boolean): Whether to provide optimization suggestions
- ```
true
```
  - Provide optimization suggestions for each version (Recommended)
- ```
false
```
  - Do not provide
- Default: true

Output

Version evaluation report including detailed analysis of each version, comparative evaluation, scoring ranking, selection suggestions, optimization directions, etc.

Processing Rules

Detailed Evaluation Criteria

1. Clarity

Evaluation Points:
- Whether information is expressed clearly and explicitly
- Whether logic is smooth
- Whether there are ambiguous expressions
- Whether information density is reasonable
Scoring Standard (0-10 points):
- 9-10 points: Very clear expression, no ambiguity
- 7-8 points: Relatively clear expression, occasional minor flaws
- 5-6 points: Basically clear expression, some unclear parts
- 0-4 points: Unclear expression, many ambiguities

2. Engagement

Evaluation Points:
- Whether the opening is eye-catching
- Whether the content is attractive
- Whether the rhythm is tight
- Whether it makes people willing to continue reading
Scoring Standard (0-10 points):
- 9-10 points: Very engaging, fascinating
- 7-8 points: Relatively engaging, with highlights
- 5-6 points: Moderately engaging, but not outstanding
- 0-4 points: Lack of engagement, hard to arouse interest

3. Persuasion

Evaluation Points:
- Whether arguments are sufficient
- Whether logic is rigorous
- Whether it can effectively influence readers
- Whether it has call-to-action
Scoring Standard (0-10 points):
- 9-10 points: Very persuasive, rigorous logic
- 7-8 points: Relatively persuasive, convincing
- 5-6 points: Moderately persuasive, but not sufficient
- 0-4 points: Lack of persuasion, hard to influence readers

4. Professionalism

Evaluation Points:
- Whether vocabulary is used professionally
- Whether expression is standardized
- Whether there are grammar errors
- Whether format is standardized
Scoring Standard (0-10 points):
- 9-10 points: Very professional, standardized and rigorous
- 7-8 points: Relatively professional, minor flaws
- 5-6 points: Basically professional, some non-standard parts
- 0-4 points: Lack of professionalism, many issues

5. Creativity

Evaluation Points:
- Whether expression is innovative
- Whether there is a unique perspective
- Whether there are creative elements
- Whether it is impressive
Scoring Standard (0-10 points):
- 9-10 points: Very creative, unique
- 7-8 points: Relatively creative, with highlights
- 5-6 points: Moderately creative, but not outstanding
- 0-4 points: Lack of creativity, plain

6. Readability

Evaluation Points:
- Whether sentence length is appropriate
- Whether paragraph structure is reasonable
- Whether words are easy to understand
- Whether reading experience is smooth
Scoring Standard (0-10 points):
- 9-10 points: Very readable, smooth reading experience
- 7-8 points: Relatively readable, minor issues
- 5-6 points: Moderately readable, some unsmooth parts
- 0-4 points: Poor readability, bad reading experience

7. Emotional Impact

Evaluation Points:
- Whether it can trigger emotional resonance
- Whether emotional expression is appropriate
- Whether it is infectious
- Whether it can leave a deep impression
Scoring Standard (0-10 points):
- 9-10 points: Strong emotional impact, deep resonance
- 7-8 points: Relatively strong emotional impact, resonance exists
- 5-6 points: Moderate emotional impact, not deep enough
- 0-4 points: Lack of emotional impact, hard to arouse resonance

8. Target Audience Fit

Evaluation Points:
- Whether language style fits audience habits
- Whether content meets audience needs
- Whether it is close to audience interests
- Whether it can trigger audience interaction
Scoring Standard (0-10 points):
- 9-10 points: Highly fits target audience
- 7-8 points: Relatively fits target audience
- 5-6 points: Basically fits, room for improvement
- 0-4 points: Does not fit target audience well

Evaluation Process

1. Version Analysis

Analyze content features of each version
Identify advantages and disadvantages of each version
Extract key information of each version

2. Dimension Scoring

Score each version according to selected
```
evaluation_criteria
```
0-10 points for each dimension, 1 point interval
Calculate average total score for each version

3. Comparative Analysis

Compare performance of different versions in each dimension
Identify strengths and weaknesses of each version
Analyze differences between versions

4. Comprehensive Evaluation

Synthesize performance in all dimensions
Combine
```
target_audience
```
and
```
use_case
```
Provide version selection suggestions

5. Optimization Suggestions

Provide optimization suggestions for each version
Point out improvement directions
Provide specific modification suggestions

Version Ranking Method

Comprehensive Scoring Ranking

Calculate average total score for each version
Rank from highest to lowest total score
Consider weights of each dimension (adjusted according to
```
use_case
```
)

Scenario-adapted Ranking

Adjust weights of each dimension according to
```
use_case
```
Calculate weighted total score
Rank from highest to lowest weighted total score

Example:

Marketing promotion scenario: Higher weights for engagement and persuasion
Information dissemination scenario: Higher weights for clarity and readability
Brand building scenario: Higher weights for professionalism and target_audience_fit

Evaluation Report Structure

1. Overview

Number of versions
Evaluation criteria
Target audience
Usage scenario

2. Detailed Analysis of Each Version

Analysis of Version A
- Version information
- Scores for each dimension
- Advantages and disadvantages
- Optimization suggestions
Analysis of Version B
- ...

3. Comparative Analysis

Score comparison table of each version
Performance comparison of each dimension
Version difference analysis

4. Version Ranking

Comprehensive scoring ranking
Scenario-adapted ranking
Recommended version

5. Selection Suggestions

Version selection suggestions based on different needs
Best applicable scenarios for each version
Combined optimization suggestions

Quick Mode

When the user input contains complete

versions

, execute directly with default parameters (all evaluation criteria, general public audience, automatically determined scenario based on content, comparative + scoring evaluation, provide optimization suggestions).

Interactive Question Template (Displayed only when user does not provide required parameters)

I will evaluate these versions for you. Please confirm the following requirements:

1. Version List (Required):
   Please provide the versions to be evaluated (2-5 versions)
   Format example:
   Version A: (content)
   Version B: (content)

2. Evaluation Criteria (multiple selection allowed, optional):
   [1] Clarity
   [2] Engagement
   [3] Persuasion
   [4] Professionalism
   [5] Creativity
   [6] Readability
   [7] Emotional impact
   [8] Target audience fit

3. Target Audience (optional):
   [1] General public
   [2] Professionals
   [3] Young people
   [4] Business professionals
   [5] Academic community
   [6] Custom (please describe)

4. Usage Scenario (optional):
   [1] Marketing promotion
   [2] Information dissemination
   [3] Education and training
   [4] Entertainment
   [5] Brand building
   [6] Custom

5. Evaluation Method (optional):
   [1] Comparative evaluation
   [2] Scoring evaluation
   [3] Comparative + Scoring (Recommended)

6. Provide Optimization Suggestions? (optional):
   [1] Provide optimization suggestions for each version (Recommended)
   [2] Do not provide

You can:
- Reply with all information at once
- Reply with partial parameters, and I will confirm if additional information is needed
- Reply "evaluate" or "ok" to execute with recommended settings (Recommended: all evaluation criteria, general public audience, automatically determined scenario, comparative + scoring, provide optimization suggestions)
- If you have other ideas, please include them in your reply

Please reply:

Examples

Example 1: Comparative Evaluation of Two Versions

Input:

versions: [
  {"version_name": "Version A", "content": "Our product is powerful, easy to operate, and user-friendly. Welcome to experience it!"},
  {"version_name": "Version B", "content": "This product is super useful, super powerful, super easy to get started, and super good-looking! Come and try it now!"}
]
evaluation_criteria: ["clarity", "engagement", "persuasion", "readability"]
evaluation_method: "both"

Output:

【Version Evaluation Report】

Overview:
- Number of versions: 2
- Evaluation criteria: Clarity, Engagement, Persuasion, Readability
- Target audience: General public
- Usage scenario: Marketing promotion

---

Detailed Analysis of Each Version:

【Version A】
Content: "Our product is powerful, easy to operate, and user-friendly. Welcome to experience it!"

Scores for each dimension:
- Clarity: 9/10 - Very clear expression, no ambiguity
- Engagement: 6/10 - Relatively plain, lack of engagement
- Persuasion: 7/10 - Persuasive, but not strong enough
- Readability: 10/10 - Very readable

Total Score: 8/10

Advantages:
- Clear and concise expression
- Standard and professional language
- High readability

Disadvantages:
- Lack of engagement, plain
- Persuasion is not strong enough

Optimization Suggestions:
1. Enhance engagement: Use more vivid expressions such as "super powerful", "super useful"
2. Enhance persuasion: Add specific data or cases such as "100,000 users have chosen us"

---

【Version B】
Content: "This product is super useful, super powerful, super easy to get started, and super good-looking! Come and try it now!"

Scores for each dimension:
- Clarity: 8/10 - Relatively clear, but repeated use of "super" is slightly redundant
- Engagement: 9/10 - Very engaging, lively and vivid
- Persuasion: 8/10 - Relatively strong persuasion, with call-to-action
- Readability: 7/10 - Relatively readable, but repeated "super" is slightly wordy

Total Score: 8/10

Advantages:
- Very engaging, lively and vivid
- Strong call-to-action
- Fits the preferences of young audiences

Disadvantages:
- Repeated use of "super" is slightly redundant
- Slightly less professional

Optimization Suggestions:
1. Reduce repeated use of "super" to avoid redundancy
2. Appropriately enhance professionalism, such as changing "super useful" to "very useful"

---

Comparative Analysis:

| Dimension | Version A | Version B | Winner |
|-----------|-----------|-----------|--------|
| Clarity   | 9/10      | 8/10      | Version A |
| Engagement| 6/10      | 9/10      | Version B |
| Persuasion| 7/10      | 8/10      | Version B |
| Readability| 10/10     | 7/10      | Version A |

Comprehensive Comparison:
- Version A performs best in clarity and readability
- Version B performs best in engagement and persuasion
- Both versions have their own advantages and are suitable for different scenarios

---

Version Ranking:

1. Comprehensive Scoring Ranking:
   1st Place: Version A (8/10) and Version B (8/10) tied

2. Scenario-adapted Ranking (Marketing promotion scenario, higher weights for engagement and persuasion):
   1st Place: Version B
   2nd Place: Version A

---

Selection Suggestions:

1. If the goal is to enhance brand image and professionalism:
   Recommend: Version A
   Reason: Version A is more professional and standardized, suitable for brand building

2. If the goal is to improve conversion rate and user clicks:
   Recommend: Version B
   Reason: Version B is more engaging and has a stronger call-to-action

3. If the target audience is young people:
   Recommend: Version B
   Reason: The language style of Version B fits the preferences of young audiences better

4. If the target audience is business professionals:
   Recommend: Version A
   Reason: Version A is more professional and formal

---

Combined Optimization Suggestions:

You can consider combining the advantages of both versions to create an optimized version:

Optimized Version:
"This product is powerful, very useful, easy to operate, and user-friendly. 100,000 users have chosen us, come and experience it now!"

Optimization Points:
- Retain engagement from Version B: "This", "very useful", "come and experience it now!"
- Retain professionalism from Version A: "powerful", "easy to operate", "user-friendly"
- Enhance persuasion: "100,000 users have chosen us"

Example 2: Multi-version Evaluation (Marketing Promotion Scenario)

Input:

versions: [
  {"version_name": "Version A", "content": "Limited time offer! Original price $299, now only $99!", "version_info": "Direct discount type"},
  {"version_name": "Version B", "content": "The $299 product can be taken home for $99 today! Only available today!", "version_info": "Limited time emphasis type"},
  {"version_name": "Version C", "content": "Get the $299 product for only $99, and get a VIP membership for free!", "version_info": "Gift offer type"}
]
evaluation_criteria: ["clarity", "engagement", "persuasion"]
target_audience: "general"
use_case: "marketing"
evaluation_method: "both"
provide_optimization_suggestions: true

Output:

【Version Evaluation Report】

Overview:
- Number of versions: 3
- Evaluation criteria: Clarity, Engagement, Persuasion
- Target audience: General public
- Usage scenario: Marketing promotion

---

Detailed Analysis of Each Version:

【Version A: Direct Discount Type】
Content: "Limited time offer! Original price $299, now only $99!"

Scores for each dimension:
- Clarity: 10/10 - Very clear, price information is straightforward
- Engagement: 7/10 - Engaging, but slightly plain
- Persuasion: 8/10 - Relatively strong persuasion, obvious price comparison

Total Score: 8.3/10

Advantages:
- Very clear price information
- Directly shows discount strength
- Concise and clear

Disadvantages:
- Lack of strong engagement, plain
- Lack of sense of urgency

Optimization Suggestions:
1. Enhance engagement: Add emotional elements such as "super value", "must grab"
2. Enhance urgency: Emphasize limited time, such as "Today's only offer", "Limited to today"

---

【Version B: Limited Time Emphasis Type】
Content: "The $299 product can be taken home for $99 today! Only available today!"

Scores for each dimension:
- Clarity: 9/10 - Clear and complete information
- Engagement: 9/10 - Very engaging, strong emotional impact
- Persuasion: 9/10 - Very strong persuasion, strong sense of urgency

Total Score: 9/10

Advantages:
- Very engaging, strong emotional impact
- Strong sense of urgency, stimulates purchase impulse
- Vivid expression, "taken home" is down-to-earth

Disadvantages:
- No obvious disadvantages

Optimization Suggestions:
- Already excellent, can be kept as is

---

【Version C: Gift Offer Type】
Content: "Get the $299 product for only $99, and get a VIP membership for free!"

Scores for each dimension:
- Clarity: 8/10 - Relatively clear, but slightly more information
- Engagement: 8/10 - Relatively engaging, gift is a highlight
- Persuasion: 9/10 - Very strong persuasion, gift adds attraction

Total Score: 8.3/10

Advantages:
- Gift adds engagement
- Strong sense of cost-effectiveness
- Very persuasive

Disadvantages:
- Slightly more information, clarity is slightly inferior to Version A and B
- Lack of sense of urgency

Optimization Suggestions:
1. Enhance urgency: Add "Today's only offer", "Limited time" etc.
2. Improve clarity: Simplify expression, such as "$99 = $299 product + VIP membership"

---

Comparative Analysis:

| Dimension | Version A | Version B | Version C | Winner |
|-----------|-----------|-----------|-----------|--------|
| Clarity   | 10/10     | 9/10      | 8/10      | Version A |
| Engagement| 7/10      | 9/10      | 8/10      | Version B |
| Persuasion| 8/10      | 9/10      | 9/10      | Version B & C |

Comprehensive Comparison:
- Version A performs best in clarity
- Version B performs best in engagement and persuasion
- Version C performs excellent in persuasion, gift is a highlight

---

Version Ranking:

1. Comprehensive Scoring Ranking:
   1st Place: Version B (9/10)
   2nd Place: Version A and Version C (8.3/10) tied

2. Scenario-adapted Ranking (Marketing promotion scenario, higher weights for engagement and persuasion):
   1st Place: Version B
   2nd Place: Version C
   3rd Place: Version A

---

Selection Suggestions:

1. If the goal is quick conversion and emphasizing urgency:
   Recommend: Version B
   Reason: Version B has the strongest sense of urgency and engagement, most likely to stimulate purchase impulse

2. If the goal is to convey super value and emphasize cost-effectiveness:
   Recommend: Version C
   Reason: Version C enhances the sense of super value through gifts, and has a strong sense of cost-effectiveness

3. If the goal is to convey information clearly and avoid information overload:
   Recommend: Version A
   Reason: Version A is the most concise and clear, and information is easiest to understand

---

Combined Optimization Suggestions:

You can consider combining the urgency of Version B and the gift of Version C to create an ultimate version:

Ultimate Optimized Version:
"The $299 product can be taken home for $99 today! Get a free VIP membership! Only available today!"

Optimization Points:
- Retain urgency from Version B: "today", "taken home", "Only available today!"
- Retain gift highlight from Version C: "Get a free VIP membership!"
- Clear price comparison: $299 vs $99

Example 3: Scoring Evaluation (No Optimization Suggestions)

Input:

versions: [
  {"version_name": "Version A", "content": "Artificial intelligence technology is changing our lives."},
  {"version_name": "Version B", "content": "AI technology is changing our lives at an unprecedented speed."},
  {"version_name": "Version C", "content": "The development of artificial intelligence technology is profoundly affecting all aspects of our lives."}
]
evaluation_criteria: ["clarity", "professionalism", "readability"]
evaluation_method: "scoring"
provide_optimization_suggestions: false

Output:

【Version Evaluation Report】

Overview:
- Number of versions: 3
- Evaluation criteria: Clarity, Professionalism, Readability
- Target audience: General public
- Usage scenario: Information dissemination

---

Detailed Analysis of Each Version:

【Version A】
Content: "Artificial intelligence technology is changing our lives."

Scores for each dimension:
- Clarity: 10/10 - Very clear expression, no ambiguity
- Professionalism: 8/10 - Uses standardized terms, relatively professional
- Readability: 10/10 - Concise sentence, very readable

Total Score: 9.3/10

Advantages:
- Concise and clear expression
- Standard term usage
- Easy to understand

Disadvantages:
- Relatively plain expression, lacks depth

---

【Version B】
Content: "AI technology is changing our lives at an unprecedented speed."

Scores for each dimension:
- Clarity: 8/10 - Relatively clear, but "unprecedented speed" is slightly exaggerated
- Professionalism: 7/10 - "AI" is an abbreviation, less standardized than "artificial intelligence"
- Readability: 9/10 - Slightly longer sentence, but relatively readable

Total Score: 8/10

Advantages:
- Relatively vivid expression
- Has certain appeal

Disadvantages:
- Uses abbreviation "AI", not standardized
- "unprecedented speed" is slightly exaggerated

---

【Version C】
Content: "The development of artificial intelligence technology is profoundly affecting all aspects of our lives."

Scores for each dimension:
- Clarity: 7/10 - Relatively lengthy expression, "all aspects" is slightly vague
- Professionalism: 9/10 - Uses standardized terms, professional expression
- Readability: 7/10 - Relatively long sentence, moderate readability

Total Score: 7.7/10

Advantages:
- Professional and standardized expression
- "profoundly affecting" has depth

Disadvantages:
- Relatively long sentence
- "all aspects" is slightly vague, affecting clarity

---

Version Ranking:

Comprehensive Scoring Ranking:
1st Place: Version A (9.3/10)
2nd Place: Version B (8/10)
3rd Place: Version C (7.7/10)

---

Selection Suggestions:

1. If the goal is to convey information concisely and clearly:
   Recommend: Version A
   Reason: Version A is the most concise and clear, easiest to understand

2. If the goal is to express vividly and have appeal:
   Recommend: Version B
   Reason: Version B is relatively vivid and has certain appeal

3. If the goal is professional expression with depth:
   Recommend: Version C
   Reason: Version C is the most professional and has depth

4. Comprehensive Recommendation:
   Version A has the best comprehensive performance, most recommended

Notes

Evaluation is based on AI analysis, for reference only, final decision should be made by humans
Weights of each evaluation criteria should be adjusted in different scenarios
Target audience and usage scenario have important impacts on evaluation results, please fill them in accurately
Optimization suggestions are based on current versions, for reference only
Evaluation results may differ from actual A/B test results, it is recommended to combine with actual data for comprehensive judgment

Parameter Adjustment Tips

After generating content, if you are not satisfied with the current results, you can try adjusting the following parameters:

💡 Parameter Adjustment Options:

Evaluation Criteria:
```
clarity
```
Clarity |
```
engagement
```
Engagement |
```
persuasion
```
Persuasion |
```
professionalism
```
Professionalism |
```
creativity
```
Creativity |
```
readability
```
Readability |
```
emotional_impact
```
Emotional impact |
```
target_audience_fit
```
Target audience fit
Target Audience:
```
general
```
General public |
```
professional
```
Professionals |
```
youth
```
Young people |
```
business
```
Business professionals |
```
academic
```
Academic community
Usage Scenario:
```
marketing
```
Marketing promotion |
```
information
```
Information dissemination |
```
education
```
Education and training |
```
entertainment
```
Entertainment |
```
brand_building
```
Brand building
Evaluation Method:
```
comparative
```
Comparative evaluation |
```
scoring
```
Scoring evaluation |
```
both
```
Comparative + Scoring
Provide Optimization Suggestions:
```
true
```
Provide optimization suggestions |
```
false
```
Do not provide

Usage: Directly reply with such as "Focus on engagement and persuasion evaluation" or "Change to marketing promotion scenario"

Association with Other Skills

review_text: If comprehensive review of a single version is needed, use this skill
rewrite_content: If you need to rewrite versions, you can use it in conjunction
check_style_consistency: If you need to check style consistency of multiple versions, use this skill
content_imitation: If you need Version A to imitate the style of Version B, use this skill

Configuration File References

intent_keywords: ["version evaluation", "version comparison", "A/B testing", "version selection", "multi-version evaluation"]
evaluation_criteria_weights: Weights of each evaluation criteria in different scenarios are defined in config/evaluation_weights.json

quality-review

NPX Install

Tags

SKILL.md Content (Chinese)

Quality Review

Overview

Feature 1: Review Text

Review Text

Overview

Usage Scenarios

Input Parameters

Required Parameters

Optional Parameters

Output

Processing Rules

Review Dimensions

1. Grammar Check (grammar)

2. Spelling Check (spelling)

3. Punctuation Check (punctuation)

4. Logic Check (logic)

5. Clarity of Expression Check (clarity)

6. Consistency Check (consistency)

7. Factual Accuracy Check (factual_accuracy)

8. Compliance Check (compliance)

Issue Level Classification

1. Critical Issues

2. Important Issues

3. Minor Issues

Review Process

1. Initial Scan

2. In-depth Analysis

3. Issue Categorization

4. Revision Suggestions

5. Overall Evaluation

Revision Suggestion Format

Summary Format (summary_only)

Detailed Format (detailed)

Annotated Format (with_marked_text)

Highlighting Rules

Deleted Content

Added Content

Modified Content

Quick Mode

Interactive Question Template (Displayed only when user does not provide required parameters)

Examples

Example 1: Comprehensive Review

Example 2: Compliance Check

Example 3: Detailed Format + Highlighting

Notes

Parameter Adjustment Tips

Association with Other Skills

Configuration File References

Feature 2: Evaluate Versions

Evaluate Versions

Overview

Usage Scenarios

Input Parameters

Required Parameters

Optional Parameters

Output

Processing Rules

Detailed Evaluation Criteria

1. Clarity

2. Engagement

3. Persuasion

4. Professionalism

5. Creativity

6. Readability

7. Emotional Impact

8. Target Audience Fit

Evaluation Process

1. Version Analysis

2. Dimension Scoring

3. Comparative Analysis

4. Comprehensive Evaluation

5. Optimization Suggestions

Version Ranking Method

Comprehensive Scoring Ranking

Scenario-adapted Ranking

Evaluation Report Structure