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.
npx skills add Supreme-Ultimate/novel-to-script-team --skill comparative-review-skillgit clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamWrote 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.
[](https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/comparative-review-skill)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
../../references/00-first-principles.md— 第一性原则(可拍性、留存性、一致性、可验证性)../../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)../../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
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.
- 11d ago First seen · 374 lines · 45 tokens per session scan A 226836943972
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…