comparative-review-skill

comparative-review-skill is a skill for Claude Code, Codex from Supreme-Ultimate/novel-to-script-team. It costs 45 tokens per session (3,287 once invoked), scanned A, original, MIT.

A comparison review that measures a generated script against successful reference scripts. It examines pacing, dialogue, emotion, conflict, and writing patterns, then returns a pass or fail decision with improvement suggestions.

In plain words
What is it for?
Use it to compare scripts, calculate writing and pacing measures, check them against stated limits, and produce a quality review.
Why use it?
It helps identify writing that feels unlike the chosen references or sounds mechanically generated. Measurements make differences in scene structure, dialogue length, emotional intensity, and conflict easier to spot.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare scripts, calculate writing and pacing measures, check them against stated limits, and produce a quality review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/supreme-ultimate/novel-to-script-team/comparative-review-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Supreme-Ultimate/novel-to-script-team --skill comparative-review-skill
Clone the repo
git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for comparative-review-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/comparative-review-skill/github.svg)](https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/comparative-review-skill)
Your own site
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/comparative-review-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/comparative-review-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for comparative-review-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/comparative-review-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/comparative-review-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.03287
Opus 5 $0.00023 $0.01643
Sonnet 5 $0.00009 $0.00657
Haiku 4.5 $0.00005 $0.00329

Measured 11d ago against content hash 226836943972, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

comparative-review-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/comparative-review-skill/SKILL.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

# 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

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

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

Read the full file on GitHub · 374 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 374 lines · 45 tokens per session scan A 226836943972

Subscribe to this mod's changes

comparative-review-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (165 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 3,287 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens