ai-drama-review
AI短剧内容基因检测。零依赖可用:AI直接分析版权疑似、年龄分级违规、小说魔改程度,输出结构化风险图谱。可选配 Python 环境启用三重相似度算法(n-gram / 编辑距离 / TF-IDF)提升精度。结果仅供内容审核参考,不构成法律意见。
Best use case
ai-drama-review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
AI短剧内容基因检测。零依赖可用:AI直接分析版权疑似、年龄分级违规、小说魔改程度,输出结构化风险图谱。可选配 Python 环境启用三重相似度算法(n-gram / 编辑距离 / TF-IDF)提升精度。结果仅供内容审核参考,不构成法律意见。
Teams using ai-drama-review should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ai-drama-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ai-drama-review Compares
| Feature / Agent | ai-drama-review | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
AI短剧内容基因检测。零依赖可用:AI直接分析版权疑似、年龄分级违规、小说魔改程度,输出结构化风险图谱。可选配 Python 环境启用三重相似度算法(n-gram / 编辑距离 / TF-IDF)提升精度。结果仅供内容审核参考,不构成法律意见。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
用户提供剧本文本、台词或字幕文件,输出结构化风险图谱。
**⚠️ BETA** — 检测结果仅供内容审核参考,不构成法律意见,高风险内容请结合专业法律咨询。
---
## 运行模式
| 模式 | 依赖 | 适用场景 |
|------|------|---------|
| **纯推理模式**(默认) | 无 | Agent / API 调用、快速扫描 |
| **增强模式** | Python 3.8+ | 精确算法检测,适合批量处理 |
| **深度模式** | Python + API Key | 算法 + AI 语义双重确认,最高精度 |
> 纯推理模式:AI 直接对文本进行分析,无需任何安装。
> 增强/深度模式:可选,通过 `python3 scripts/text_similarity.py` 等脚本提升算法精度。
---
## 调用示例
```
# 完整审查
审查这个剧本:[粘贴文本]
# 单项检测
检测这段台词是否存在版权问题:[文本]
判断这个剧本的年龄分级:[文本]
# 改编对比
对比原著和改编版本的偏离程度:
原著:[文本]
改编:[文本]
```
---
## 核心方法论:内容基因检测三角
```
版权基因 年龄分级基因 改编偏离基因
│ │ │
文本相似度 语义风险密度 结构对齐偏差
│ │ │
└──────────── 综合风险指数 ────────────┘
```
所有检测遵循:**先快速定位嫌疑区,再上下文确认消除误报**。
---
## Phase 1: 版权相似度检测
对输入文本按段落执行相似度分析,标记疑似侵权段落。
**三重互补算法(增强/深度模式):**
```
综合得分 = 0.3 × Jaccard(n-gram) + 0.3 × (1 - 归一化编辑距离) + 0.4 × TF-IDF余弦
阈值:综合得分 > 0.7 → 标记疑似侵权
```
| 算法 | 检测侧重 |
|------|---------|
| n-gram Jaccard | 局部词汇重复、直接抄录 |
| 归一化编辑距离 | 轻微改写、同义替换 |
| TF-IDF余弦 | 主题语义相似、结构性借用 |
**纯推理模式**:AI 直接分析段落,识别明显的情节/台词重复、标志性表达借用,给出风险评估和可疑片段标注。
**数据流向**:文本内容仅在本次会话中处理。深度模式下,疑似段落发送至配置的 AI API(OpenAI/Anthropic)进行语义确认。不向任何第三方传输原始文本。
---
## Phase 2: 年龄分级基因扫描
对文本按内容类别扫描风险信号,给出分级建议。
**类别与严重度:**
| 类别 | 严重度级别 |
|------|-----------|
| 暴力/血腥 | mild / moderate / severe |
| 性暗示/色情 | mild / moderate / severe |
| 恐怖/惊悚 | mild / moderate / severe |
| 脏话/侮辱 | mild / moderate / severe |
| 毒品/违禁品 | mild / moderate / severe |
上下文确认原则:命中词不等于违规,需排除否定语境("不允许暴力")、文学修辞、历史引用等误报。
| 分级 | 判定说明 |
|------|---------|
| 全年龄 | 无违规内容 |
| 12+ | 轻度冲突,需家长指导 |
| 18+ | 较强暴力/成人主题 |
| 不合规 | 超出可接受范围,建议修改 |
---
## Phase 3: 改编偏离度评分
对比原著与改编版本,量化"魔改程度"。输入:原著文本 + 改编版本文本。
**偏离度公式:**
```
偏离度 = 结构对齐偏差 × 40% + 角色设定偏差 × 35% + 核心情节偏差 × 25%
```
| 偏离度 | 分类 | 操作建议 |
|--------|------|---------|
| 0–30 | 忠实改编 | 低风险,正常推进 |
| 30–60 | 合理改编 | 建议与版权方沟通确认 |
| 60–100 | 严重魔改 | 高风险,建议法律审查后再发布 |
---
## 输出格式
```json
{
"overall_risk": "中",
"copyright": {
"risk_level": "高",
"suspicious_paragraphs": [
{"index": 3, "score": 0.83, "reason": "与《XX》第7章高度相似"}
]
},
"age_rating": {
"suggested_rating": "12+",
"hits": [
{"category": "暴力", "severity": "mild", "count": 4, "locations": [22, 45]}
]
},
"adaptation": {
"deviation_score": 61,
"classification": "严重魔改",
"key_changes": ["主角性格完全反转", "结局改动超出原著核心"]
},
"recommendations": [
"第3、7段建议改写或获取书面授权",
"第22段暴力描写建议降级处理"
]
}
```
---
## 边界与合规
**本技能做什么:** 内容风险识别、分级建议、改编偏离量化、整改方向指引。
**本技能不做什么:**
- 不提供法律意见,不替代版权律师的专业判断
- 不保证零漏报(算法和 AI 均存在误判可能)
- 不联网检索版权数据库(使用本地参考库)
**凭证(均为可选):**
- `OPENAI_API_KEY` 或 `ANTHROPIC_API_KEY` — 启用深度语义确认
- 所有凭证仅通过环境变量读取,不持久化、不记录、不传输Related Skills
Post-Mortem & Incident Review Framework
Run structured post-mortems that actually prevent repeat failures. Blameless analysis, root cause identification, and action tracking.
Pitch Deck Reviewer
Reviews pitch decks and provides investor-ready feedback with scoring
Performance Review Engine
> Your AI-powered performance management system. Write reviews that develop people, not just evaluate them. From self-assessments to 360° feedback to calibration — complete frameworks for every review cycle.
Deal Desk — Structured Deal Review & Approval
Run every non-standard deal through a repeatable review process. Catch margin leaks, enforce discount guardrails, and close faster with pre-approved terms.
Contract Review Assistant
Analyze business contracts for risks, unfavorable terms, and missing clauses. Get a plain-English summary of what you're signing.
afrexai-code-reviewer
Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any language, any repo, no dependencies required.
performance-review-cn
绩效面谈报告、OKR对齐度检测、校准辅助
clawdtm-review
Review and rate OpenClaw skills on ClawdTM. See what humans and AI agents recommend.
cyber-owasp-review
Map application security findings to OWASP Top 10 categories and generate remediation checklists. Use for normalized AppSec review outputs and category-level prioritization.
Contract Reviewer - AI Legal Document Risk Scanner
Upload any contract or legal document and get a structured risk analysis with flagged clauses, plain-language explanations, and negotiation suggestions.
serde-code-review
Reviews serde serialization code for derive patterns, enum representations, custom implementations, and common serialization bugs. Use when reviewing Rust code that uses serde, serde_json, toml, or any serde-based serialization format. Covers attribute macros, field renaming, and format-specific pitfalls.
rust-testing-code-review
Reviews Rust test code for unit test patterns, integration test structure, async testing, mocking approaches, and property-based testing. Use when reviewing _test.rs files,