final

Web fiction manuscript completion verification

Trigger keywords

I've finished writing the novel, help me check it, export a format suitable for Qidian/Fanqie, check for typos, detect sensitive words, organize into a release version, help me export a novel publishing format, check the novel for typos, sensitive word detection, novel manuscript completion check, export adapted to Qidian format, Fanqie novel format export, novel layout organization, multi-platform format export, novel manuscript completion export

Core features

1. Typo, punctuation, and grammar error checking
2. Sensitive content and violating content screening
3. Unified format standards: chapter titles, paragraph formatting, punctuation standards
4. Full-text word count statistics, completion report generation
5. Export adapted to publishing formats of different platforms
6. Batch replacement function
7. Automatic paragraphing function

Output content

• Error list: typos, punctuation errors, grammar issues
• Sensitive content alerts: violating content that needs adjustment
• Verified clean full text
• Completion report: total word count, number of chapters, core content summary
• Multi-platform publishing format versions (Qidian, Fanqie, Jinjiang, etc.)

Export format rules for each platform

Qidian Chinese Network (qidian)

• Chapter title format:第X章 标题内容, center-aligned
• First line of each paragraph indented by 2 characters
• Leave one blank line between paragraphs
• Use full-width Chinese punctuation
• Recommended chapter length: 3000-5000 characters
• Special symbols are prohibited as chapter titles
• Dialogue should be in its own paragraph

Fanqie Novel (fanqie)

• Chapter title format:第X章 标题内容
• First line of paragraphs not indented, leave one blank line between paragraphs
• Keep each sentence as short as possible, suitable for mobile reading
• Recommended chapter length: 2000-3000 characters
• Key content may use bold markers
• Dialogue should be wrapped in quotation marks, with the speaker in a separate paragraph or noted at the end of the sentence

Jinjiang Literature City (jjwxc)

• Chapter title format:第X章 标题内容
• Supports HTML format tags
• First line of each paragraph indented by 2 characters
• Recommended chapter length: 2500-4000 characters
• Author's notes area set separately
• Supports chapter summaries

Zongheng Chinese Network (zongheng)

• Chapter title format:第X章 标题内容
• First line of each paragraph indented by 2 characters
• Recommended chapter length: 3000-6000 characters
• Supports volume settings
• Use full-width Chinese punctuation

17K Novel Network (17k)

• Chapter title format:第X章 标题内容
• First line of each paragraph indented by 2 characters
• Recommended chapter length: 2000-4000 characters
• Supports chapter preview
• Next chapter preview can be set at the end of each chapter

Sensitive word detection standards

Level 1 sensitive (must be modified)

• Content that violates national laws and regulations
• Involves politically sensitive figures or events
• Pornographic or obscene descriptions
• Violent or terrorist content
• Speech that splits the country or undermines ethnic unity
• Religiously extremist content

Level 2 sensitivity (revision recommended)

• Excessively graphic violent details
• Vulgar language or profanity
• Medical descriptions that may cause discomfort
• Inappropriate content involving minors
• Descriptions related to gambling or drugs
• Content that infringes on others' privacy

Level 3 sensitivity (optimization suggestions)

• Too much internet slang affecting readability
• Ambiguous expressions
• Potentially controversial topics
• Overuse of internet memes
• Repetitive and redundant expressions

Incorrect level prompt

Serious error (red mark)

• Typos that completely change the meaning
• Level 1 sensitive word violation content
• Chapter title format completely non-compliant with standards
• Severely chaotic paragraph structure
• Widespread punctuation errors

Moderate error (yellow mark)

• General typos
• Non-standard punctuation usage
• Level 2 sensitive word content
• Inconsistent paragraph formatting
• Grammatical errors affecting comprehension

Minor error (blue mark)

• Wording recommended for optimization
• Punctuation usage could be more standard
• Level 3 sensitive word content
• Paragraph layout can be further beautified
• Suggestions for repetitive expressions

Batch replacement feature description

Feature characteristics

• Supports global batch replacement of specified words
• Supports regular expression replacement
• Supports preview confirmation before replacement
• Supports simultaneous execution of multiple replacement rule sets
• Supports querying replacement history

Use cases

1. Unified modification of character names
2. Batch adjustment of place names and setting names
3. Batch replacement of sensitive words
4. Unified standardization of punctuation
5. Batch conversion of internet slang

Operation methods

• Preset rules: Select commonly used replacement rule templates
• Custom rules: Manually enter search content and replacement content
• Regex mode: Use regular expressions for complex matching
• Confirm replacement: Review the replacement preview and then confirm execution

Automatic paragraph splitting feature description

Feature characteristics

• Intelligently identifies dialogue and narrative content
• Automatically splits paragraphs based on sentence length
• Supports custom word count threshold for paragraph splitting
• Maintains logical integrity of paragraphs
• Dialogue automatically becomes its own paragraph

Paragraph splitting rules

1. Dialogue priority: Dialogue content automatically becomes its own paragraph
2. Word count control: 100-300 words per paragraph recommended
3. Logical integrity: Avoid splitting in the middle of a sentence
4. Scene switching: Automatically splits paragraphs when scenes change
5. Psychological activity: Appropriately splits long psychological descriptions into paragraphs

Configurable parameters

• Maximum paragraph word count (default 300 words)
• Minimum paragraph word count (default 50 words)
• Whether to force dialogue into separate paragraphs
• Whether to add a separator line when scenes change
• Whether to retain the original paragraph structure

Data persistence

Finalized data is automatically saved to the .sumeru/finalize/ directory:

• clean/full-text.md: The complete clean version after validation
• clean/chapters/: Clean version files split by chapter
• platforms/: Export versions for each platform, stored by platform name
• error-report.json: Error list, including all issues such as typos, punctuation, and sensitive words
• sensitive-words.json: List and locations of detected sensitive words
• stats.json: Finalization statistics report, total word count, number of chapters, average chapter length, etc.
• export-config.json: Export configuration parameters for each platform

Data reuse

• Other platform formats can be re-exported at any time without re-validation
• The error report can serve as a reference for avoiding issues in subsequent writing
• Supports incremental export; after modifying some chapters, only the platform versions of the corresponding chapters are regenerated
• The finalization report can be used directly to fill in materials for publishing the work