Agent skill

Script Comparative Review Against Hits

by Supreme-Ultimate in Supreme-Ultimate/novel-to-script-team

Chinese-language skill that scores a generated short-drama script against a reference hit script on rhythm, dialogue style, emotional impact and structure, with PASS/FAIL thresholds.

MITAuto-check passedMedia & Creative

SKILL.md written in Chinese; this summary is our English description.

Install Script Comparative Review Against Hits

skills CLI
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill comparative-review-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Supreme-Ultimate/novel-to-script-team comparative-review-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/comparative-review-skill .claude/skills/comparative-review-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
comparative-review-skill
GitHub stars
175
Token cost
~1.8k tokens
SKILL.md length
128 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Chinese-language skill that scores a generated short-drama script against a reference hit script on rhythm, dialogue style, emotional impact and structure, with PASS/FAIL thresholds.

  • Works in 10 steps: 节奏对比 → 对话风格对比 → 情绪冲击力对比 → …
  • Checking whether a generated episode script matches the rhythm of a successful reference script
  • SKILL.md covers 必读, 功能, 对比维度 and 执行流程, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill compares a newly generated script to a reference hit script across several measurable dimensions and returns a PASS or FAIL verdict with improvement notes, aimed at keeping scripts from reading as AI-generated. It requires reading first-principles, script-writing-standard and review-gate reference documents shared across the pipeline.

Rhythm is compared by scene count, conflict density, scene duration and emotional intensity, each within a numeric tolerance of the reference. Dialogue style checks sentence length, dialogue ratio, visual-marker density and a count of web-fiction-flavored phrases against target ranges. Emotional impact looks at emotion-word density, polarity swings and climax or suspense points. Structure checks for an opening hook, mid-section conflict, a climax, a twist and a hook ending, passing with four of five present, and it hard-fails on any repeated scene or event across episodes, or an incomplete event within the current one.

When your agent uses it

  • Checking whether a generated episode script matches the rhythm of a successful reference script
  • Screening dialogue for web-fiction cliches before finalizing a script
  • Catching repeated scenes or plot points between consecutive episodes

Example prompts

  • “对比这一集生成的剧本和爆款参考剧本,给出PASS或FAIL。”
  • “Check this episode script for repeated scenes or dialogue from the previous episode.”
  • “这集的情绪冲击力够不够,和参考剧本比一下。”

Requirements

  • Python for the statistical comparison routines
  • A reference hit script to compare against

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. 节奏对比
  2. 对话风格对比
  3. 情绪冲击力对比
  4. 框架结构对比
  5. 跨集内容重复检查
  6. 事件完整性检查
  7. 加载剧本
  8. 统计指标
  9. 对比分析
  10. 生成审核报告

What it can do on your machine

Read from SKILL.md and the folder at commit 117dceb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Script Comparative Review Against Hits loads about 1.8k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Supreme-Ultimate/novel-to-script-team at commit 117dceb, republished under its MIT licence (© Supreme-Ultimate). 128 words, ~1,794 tokens.

Download SKILL.mdSave it as .claude/skills/comparative-review-skill/SKILL.md (or your agent's skills folder).
name
comparative-review-skill
description
对比审核技能。对比生成剧本与爆款剧本的节奏、对话、情绪、框架,给出PASS/FAIL判断和改进建议。

对比审核技能

必读

  1. ../../references/00-first-principles.md — 第一性原则(可拍性、留存性、一致性、可验证性)
  2. ../../references/03-script-writing-standard.md — 剧本写作标准(对话比、视觉标记、网文感、节奏控制)
  3. ../../references/04-review-gates.md — 审核门槛(PASS/FAIL标准、回改流程)

功能

对比生成剧本与参考的爆款剧本,从多个维度进行分析,防止AI味,确保剧本质量。

对比维度

1. 节奏对比

统计指标:

  • 场景数(scene_count)
  • 冲突密度(conflict_density)= 冲突次数 / 总字数
  • 平均场景时长(avg_scene_duration)
  • 时长方差(duration_variance)
  • 情绪强度(emotion_intensity)

对比方法:

python
# 统计生成剧本
generated = analyze_rhythm(generated_script)

# 统计参考剧本(5个的平均值)
reference = average([analyze_rhythm(ref) for ref in reference_scripts])

# 对比
rhythm_score = compare_metrics(generated, reference)

判断标准:

  • 场景数:±2个场景内为PASS
  • 冲突密度:±0.01内为PASS
  • 情绪强度:±0.01内为PASS
2. 对话风格对比

统计指标:

  • 平均句长(avg_sentence_length)
  • 对话比(dialogue_ratio)= 对话字数 / 总字数
  • 视觉标记密度(visual_markers_per_100)
  • 短句比例(short_sentence_ratio)< 10字符的句子占比
  • 网文感关键词密度(wanwen_keywords_per_100)

网文感关键词:

python
wanwen_keywords = [
    '冷笑', '嗤笑', '冷哼', '冷声', '冷冷',
    '眼神一冷', '眸光一沉', '嘴角勾起',
    '不屑', '轻蔑', '讥讽', '嘲讽',
    '霸气', '强势', '凌厉', '锐利'
]

判断标准:

  • 句长:12±3字符为PASS
  • 对话比:70%±10%为PASS
  • 视觉标记:3-5个/100字为PASS
3. 情绪冲击力对比

统计指标:

  • 情绪词汇密度(emotion_word_density)
  • 情感极性摆动(emotion_polarity_swing)
  • 高潮点数量(climax_count)
  • 悬念设置(suspense_count)

情绪词汇:

python
emotion_words = {
    '愤怒': ['愤怒', '暴怒', '怒火', '气愤', '恼怒'],
    '悲伤': ['悲伤', '难过', '伤心', '痛苦', '绝望'],
    '惊讶': ['惊讶', '震惊', '惊愕', '愕然', '惊呆'],
    '恐惧': ['恐惧', '害怕', '惊恐', '畏惧', '胆寒'],
    '喜悦': ['喜悦', '高兴', '欣喜', '愉悦', '兴奋']
}

判断标准:

  • 情绪词汇:1.5-2.5个/100字为PASS
  • 情感摆动:至少2次明显摆动为PASS
  • 高潮点:至少1个为PASS
4. 框架结构对比

结构要素:

  • 开局(hook):前10%是否有强钩子
  • 发展(development):中间60%是否有持续冲突
  • 高潮(climax):是否有明显高潮点
  • 反转(twist):是否有意外反转
  • 结局(ending):是否有强悬念/钩子

判断标准:

  • 5个要素至少满足4个为PASS
5. 跨集内容重复检查

检查对象:当前集与前一集的内容对比

检查项:

  • 场景重复:当前集与前一集是否有相同的场景
  • 剧情点重复:当前集与前一集是否有相同的剧情点
  • 对话重复:当前集与前一集是否有相似的对话
  • 事件重复:当前集与前一集是否是同一个事件

判断标准:

  • 发现任何重复内容,必须 FAIL
  • 必须指出具体的重复位置
  • 必须要求删除或重写重复内容

示例:

python
# 检查场景重复
ep01_scenes = extract_scenes(ep01_script)
ep02_scenes = extract_scenes(ep02_script)
duplicate_scenes = find_duplicates(ep01_scenes, ep02_scenes)

if duplicate_scenes:
    feedback.append({
        'dimension': '跨集内容重复',
        'issue': '发现重复场景',
        'location': f'第{N}集与第{N-1}集',
        'duplicates': duplicate_scenes,
        'suggestion': '删除重复场景,或改为新的场景'
    })
6. 事件完整性检查

检查对象:当前集的事件结构

检查项:

  • 事件完整性:当前集是否是一个完整的事件(有开始、发展、结束)
  • 剧情线完整性:当前集是否有未完成的剧情线
  • 逻辑连贯性:当前集与下一集的规划是否有逻辑断层

判断标准:

  • 事件不完整(如只有开始没有结束),必须 FAIL
  • 有未完成的剧情线,必须 FAIL
  • 与下一集的规划有逻辑断层,必须 FAIL

示例:

python
# 检查事件完整性
event_structure = analyze_event_structure(script)

if not event_structure['has_beginning']:
    feedback.append({
        'dimension': '事件完整性',
        'issue': '事件缺少开始',
        'suggestion': '添加事件的触发点'
    })

if not event_structure['has_ending']:
    feedback.append({
        'dimension': '事件完整性',
        'issue': '事件缺少结束',
        'suggestion': '添加事件的结果或转折'
    })

执行流程

Step 1: 加载剧本
python
# 加载生成剧本
with open(generated_script_path, 'r') as f:
    generated_script = f.read()

# 加载参考剧本(之前检索的Top 5)
reference_scripts = []
for ref_path in reference_paths:
    with open(ref_path, 'r') as f:
        reference_scripts.append(f.read())
Step 2: 统计指标
python
# 生成剧本指标
gen_rhythm = analyze_rhythm(generated_script)
gen_style = analyze_style(generated_script)
gen_emotion = analyze_emotion(generated_script)
gen_structure = analyze_structure(generated_script)

# 参考剧本平均指标
ref_rhythm = average([analyze_rhythm(ref) for ref in reference_scripts])
ref_style = average([analyze_style(ref) for ref in reference_scripts])
ref_emotion = average([analyze_emotion(ref) for ref in reference_scripts])
ref_structure = average([analyze_structure(ref) for ref in reference_scripts])
Step 3: 对比分析
python
feedback = []

# 节奏对比
if abs(gen_rhythm['scene_count'] - ref_rhythm['scene_count']) > 2:
    feedback.append({
        'dimension': '节奏',
        'issue': f"场景数偏{'少' if gen_rhythm['scene_count'] < ref_rhythm['scene_count'] else '多'}",
        'generated': gen_rhythm['scene_count'],
        'reference': ref_rhythm['scene_count'],
        'suggestion': f"建议调整为{ref_rhythm['scene_count']}个场景"
    })

# 对话风格对比
if gen_style['dialogue_ratio'] < 0.6:
    feedback.append({
        'dimension': '对话风格',
        'issue': '对话比偏低',
        'generated': f"{gen_style['dialogue_ratio']:.1%}",
        'reference': f"{ref_style['dialogue_ratio']:.1%}",
        'suggestion': '增加对话,减少叙述性文字'
    })

# 跨集内容重复检查
if previous_script:
    duplicate_scenes = find_duplicate_scenes(generated_script, previous_script)
    if duplicate_scenes:
        feedback.append({
            'dimension': '跨集内容重复',
            'issue': '发现重复场景',
            'location': f'第{N}集与第{N-1}集',
            'duplicates': duplicate_scenes,
            'suggestion': '删除重复场景,或改为新的场景',
            'severity': 'CRITICAL'  # 必须修复
        })

# 事件完整性检查
event_structure = analyze_event_structure(generated_script)
if not event_structure['is_complete']:
    feedback.append({
        'dimension': '事件完整性',
        'issue': event_structure['issue'],
        'suggestion': event_structure['suggestion'],
        'severity': 'CRITICAL'  # 必须修复
    })

# ... 其他维度对比
Step 4: 生成审核报告
python
report = {
    'verdict': 'PASS' if len(feedback) == 0 else 'FAIL',
    'overall_score': calculate_overall_score(gen, ref),
    'dimensions': {
        'rhythm': rhythm_score,
        'style': style_score,
        'emotion': emotion_score,
        'structure': structure_score
    },
    'feedback': feedback,
    'reference_examples': find_best_examples(feedback, reference_scripts)
}

输出格式

markdown
【综合审核报告】

判定:FAIL
综合得分:72/100

## 维度得分
- 节奏:65/100 ⚠️
- 对话风格:70/100 ⚠️
- 情绪冲击力:80/100 ✓
- 框架结构:85/100 ✓
- 跨集内容重复:FAIL ❌
- 事件完整性:FAIL ❌

## 详细反馈

### 跨集内容重复问题(CRITICAL)
1. 发现重复场景
   - 位置:第2集与第1集
   - 重复内容:搜身 + 签字 + 离开
   - 建议:删除第2集的重复内容,改为新的场景(如拍卖会、修炼等)

### 事件完整性问题(CRITICAL)
1. 事件不完整
   - 位置:第2集
   - 问题:第2集重复了第1集的事件,没有新的完整事件
   - 建议:第2集应该是一个新的完整事件,如"拍卖会展示实力"(入场 → 竞拍 → 展示 → 震惊)

### 节奏问题
1. 场景数偏少
   - 生成剧本:6个场景
   - 参考平均:8.5个场景
   - 建议:增加2个过渡场景,建议在第3场景后和第5场景后各增加一个

2. 冲突密度偏低
   - 生成剧本:0.015
   - 参考平均:0.035
   - 建议:在第3、5场景增加对抗情节

### 对话风格问题
1. 对话比偏低
   - 生成剧本:45%
   - 参考平均:72%
   - 建议:增加对话,减少叙述。将叙述性文字改为对话形式

2. 句长偏长
   - 生成剧本:18字符
   - 参考平均:12字符
   - 建议:拆分长句,增加短句比例

3. 视觉标记不足
   - 生成剧本:1个/100字
   - 参考平均:4个/100字
   - 建议:增加视觉标记(冷笑、嗤笑、冷哼等)

## 参考示例

请参考以下爆款剧本的处理方式:

1. 《封总的复仇娇妻》第15集
   - 对抗场景结构:先铺垫→冲突爆发→反转→钩子
   - 对话节奏:短句+高密度+情绪化

2. 《霸总的替身新娘》第8集
   - 打脸场景:层层递进,每次打脸都有新信息
   - 视觉标记:冷笑、嗤笑、眼神一冷等高频使用

## 修改建议

优先级1(必须修改 - CRITICAL):
- **删除第2集的重复内容,改为新的完整事件**
- **确保每集是一个独立的故事单元**

优先级2(必须修改):
- 增加2个过渡场景
- 提高对话比到70%以上

优先级3(建议修改):
- 拆分长句
- 增加视觉标记

优先级4(可选优化):
- 增强情绪词汇密度
- 优化悬念设置

成功标准

  • 综合得分 ≥ 80分为PASS
  • 4个维度得分均 ≥ 70分
  • 无优先级1的问题
  • 跨集内容重复检查:PASS(无重复内容)
  • 事件完整性检查:PASS(事件完整、无逻辑断层)

注意事项

  1. 对比基准:使用检索到的Top 5爆款剧本作为基准
  2. 动态调整:根据实际效果调整判断标准
  3. 具体建议:必须引用具体的参考剧本示例
  4. 可操作性:建议必须具体、可执行

© Supreme-Ultimate, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/comparative-review-skill of Supreme-Ultimate/novel-to-script-team.

Open the folder on GitHubat commit 117dceb

Compare with similar skills

Script Comparative Review Against Hits next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Script Comparative Review Against Hits compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Script Comparative Review Against Hits this skillSupreme-Ultimate/novel-to-script-team175—~1.8kAutomated safety check: PassMIT
Novel to Screenplay Rewriterchatfire-AI/huobao-drama16k—~209Automated safety check: PassCustom licence
VoxEasy Video Prompt Directorlouchi1984-coder/voxeasy117—~977Automated safety check: PassNone
Inputs V2 New Modulesaezlab/pypath164—~728Automated safety check: PassGPL-3.0
Novel WriterZJU-REAL/Easel3.3k—~1kAutomated safety check: PassApache-2.0
Python Manager Discoverymicrosoft/vscode-python-environments141—~2.7kAutomated safety check: PassMIT

Similar skills

  • Novel to Screenplay Rewriter

    chatfire-AI/huobao-drama

    Rewrites narrated novel chapters into a formatted screenplay with scene headers and dialogue, keeping the plot and cutting camera directions.

    16k GitHub stars~209 tokensUpdated 4 days ago
    Writing & ContentAuto-check passed
  • VoxEasy Video Prompt Director

    louchi1984-coder/voxeasy

    Turns a one-line topic, full script or SRT file into Vox-style paper-cut collage video prompts and JSON for Google Flow, planning subtitle shots first and confirming choices twice.

    117 GitHub stars~977 tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Inputs V2 New Module

    saezlab/pypath

    Create a new pypath inputsv2 module for an external database.

    164 GitHub stars~728 tokensUpdated today
    Writing & ContentAuto-check passed
  • Novel Writer

    ZJU-REAL/Easel

    长篇小说/网文连载创作:从世界观、人设和三级大纲写到逐章正文,并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.

    3.3k GitHub stars~1k tokensUpdated today
    Writing & ContentAuto-check passed
  • Python Manager Discovery

    microsoft/vscode-python-environments

    Official

    Environment manager-specific discovery patterns and known issues.

    141 GitHub stars~2.7k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Layered-Collage Documentary Shorts

    hassancs91/claude-faceless-shorts-creator

    Builds a vertical collage-style documentary short from script to render: scene dissection into image layers, layer production, TSX assembly on a collage kit, frame checks and voice.

    271 GitHub stars~1.5k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

More from Supreme-Ultimate/novel-to-script-team

All 17 skills in this repo
  • Production Art Prompt Designer

    Supreme-Ultimate/novel-to-script-team

    Turns the character and scene lists from a director analysis into detailed text-to-image prompts for character sheets, scenes and props, after confirming a visual style with you.

    175 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Art Direction Review

    Supreme-Ultimate/novel-to-script-team

    Reviews costume, makeup and prop design prompts for characters and scenes in a novel-to-film pipeline, scoring each one and returning PASS or FAIL with a problem list.

    175 GitHub stars~918 tokensUpdated 5 mo ago
    Auto-check passed
  • Director Script Breakdown for Seedance

    Supreme-Ultimate/novel-to-script-team

    Breaks a script or outline into plot points and writes a director's walkthrough, character list and scene list sized for Seedance video generation.

    175 GitHub stars~1.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Film Storyboard Prompt Builder

    Supreme-Ultimate/novel-to-script-team

    Turns a script, synopsis or scene outline into AI image prompts for storyboards, using a beat breakdown, a nine-panel Beat Board and four-panel Sequence Boards.

    175 GitHub stars~815 tokensUpdated 5 mo ago
    Auto-check passed
  • Hit Script Retrieval Skill

    Supreme-Ultimate/novel-to-script-team

    爆款剧本检索技能。使用混合搜索(语义+关键词)检索最相关的爆款剧本,为生成提供参考. An agent skill from Supreme-Ultimate/novel-to-script-team.

    175 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check passed
  • Image Generation Skill

    Supreme-Ultimate/novel-to-script-team

    调用 nano banana API(gemini-3.1-flash-image-preview)生成图片。支持纯文本生图和参考图生图。

    175 GitHub stars~640 tokensUpdated 5 mo ago
    Auto-check: notes

Works with

Questions about Script Comparative Review Against Hits

What does Script Comparative Review Against Hits do?

Chinese-language skill that scores a generated short-drama script against a reference hit script on rhythm, dialogue style, emotional impact and structure, with PASS/FAIL thresholds. This skill compares a newly generated script to a reference hit script across several measurable dimensions and returns a PASS or FAIL verdict with improvement notes, aimed at keeping scripts from reading as AI-generated. It requires reading first-principles, script-writing-standard and review-gate reference documents shared across the pipeline.

When should I use Script Comparative Review Against Hits?

Script Comparative Review Against Hits fits situations like: checking whether a generated episode script matches the rhythm of a successful reference script; screening dialogue for web-fiction cliches before finalizing a script; catching repeated scenes or plot points between consecutive episodes.

How do I install Script Comparative Review Against Hits in Claude Code?

Run `npx skills add Supreme-Ultimate/novel-to-script-team --skill comparative-review-skill -a claude-code`. Or copy the skill folder (skills/comparative-review-skill in Supreme-Ultimate/novel-to-script-team) into .claude/skills/comparative-review-skill in your project. Claude Code loads it when a task matches its description.

How do I install Script Comparative Review Against Hits in Codex?

Run `npx skills add Supreme-Ultimate/novel-to-script-team --skill comparative-review-skill -a codex`. Or copy the skill folder (skills/comparative-review-skill in Supreme-Ultimate/novel-to-script-team) into .agents/skills/comparative-review-skill in your project. Codex loads it when a task matches its description.

Can I use Script Comparative Review Against Hits in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Supreme-Ultimate/novel-to-script-team --skill comparative-review-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comparative-review-skill, .gemini/skills/comparative-review-skill, .github/skills/comparative-review-skill and .opencode/skills/comparative-review-skill in your project.

What does Script Comparative Review Against Hits need to run?

SKILL.md names no scripts, command-line tools or credentials: Script Comparative Review Against Hits is instructions for the agent only. Our summary lists: Python for the statistical comparison routines; A reference hit script to compare against.

Does Script Comparative Review Against Hits access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Script Comparative Review Against Hits safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Script Comparative Review Against Hits use?

Script Comparative Review Against Hits is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Script Comparative Review Against Hits use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Script Comparative Review Against Hits?

Skills that share tags, products or a category with Script Comparative Review Against Hits: Novel to Screenplay Rewriter (chatfire-AI/huobao-drama, 16k stars), VoxEasy Video Prompt Director (louchi1984-coder/voxeasy, 117 stars), Inputs V2 New Module (saezlab/pypath, 164 stars) and Novel Writer (ZJU-REAL/Easel, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Script Comparative Review Against Hits?

Supreme-Ultimate (a GitHub organization) maintains it in Supreme-Ultimate/novel-to-script-team, which has 175 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on May 2, 2026.

Source: Supreme-Ultimate/novel-to-script-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.