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 pynooblin/ai-script-reviewer --skill ai-script-reviewergit clone --depth 1 https://github.com/pynooblin/ai-script-reviewerWrote 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/pynooblin/ai-script-reviewer/ai-script-reviewer)<a href="https://agentmods.dev/skills/pynooblin/ai-script-reviewer/ai-script-reviewer"><img src="https://agentmods.dev/badge/skills/pynooblin/ai-script-reviewer/ai-script-reviewer/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/pynooblin/ai-script-reviewer/ai-script-reviewer"><img src="https://agentmods.dev/badge/skills/pynooblin/ai-script-reviewer/ai-script-reviewer.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 | $0.00177 | $0.01209 |
| Opus 5.5 | $0.00071 | $0.00484 |
| Sonnet 5.5 | $0.00035 | $0.00242 |
| Haiku 4.5 | $0.00018 | $0.00121 |
Grade A, and why
ai-script-reviewer 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 2mo 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.
What it actually says
AI漫剧剧本合规审查
审查工作流
收到用户提供的剧本/大纲/概念稿后，按以下5步依次审查：
步骤1：题材分类判断
判断剧本是否涉及特殊题材（无论投资额多少，均按重点微短剧由广电总局直接审核）：
- 政治、军事、外交、国家安全、统战、民族、宗教、司法、公安
同时判断投资额对应的分类层级（2026年1月新标准）：
- 重点微短剧：投资>=300万 或 特殊题材 → 总局审核
- 普通微短剧：100万<=投资<300万 且一般题材 → 省级审核
- 其他微短剧：投资<100万 且一般题材 → 平台自审
如涉及特殊题材，明确告知用户审核层级和周期影响。
步骤2：逐项红线扫描
读取 content-redlines.md，对照红线清单逐项检查剧本内容。
步骤3：经典IP风险评估
如剧本涉及经典文学作品、历史人物、英雄模范等，读取 classic-ip-rules.md 评估"AI魔改"风险。
步骤4：版权合规检查
检查剧本是否存在真人肖像/声音使用、照搬爆款剧情等问题。读取 copyright-compliance.md。
步骤5：价值观综合评估
评估整剧立意导向是否"积极向上"。读取 value-assessment.md。
风险等级定义
| 等级 | 标记 | 含义 | 处理方式 |
|---|---|---|---|
| 致命 | CRITICAL | 违反法律法规，上线即违规 | 必须彻底重写相关内容 |
| 高危 | HIGH | 触碰监管红线，大概率被下架/拒审 | 必须修改后方可提交 |
| 中危 | MEDIUM | 存在擦边风险，审核可能要求整改 | 建议修改，可附修改方案 |
| 低危 | LOW | 轻微风险，审核通过但可能被关注 | 建议优化但不阻塞上线 |
| 建议 | INFO | 提升质量的建议 | 自行决定是否采纳 |
输出格式
每次审查输出以下结构：
## 审查报告
### 基本信息
- 剧本名称：（如提供）
- 题材分类：重点/普通/其他
- 审核层级：总局/省级/平台
- 审查日期：YYYY-MM-DD
### 风险汇总
| # | 风险等级 | 问题类别 | 涉及位置 | 简述 |
|---|---------|---------|---------|------|
| 1 | CRITICAL | 内容红线 | 第X集/第X段 | ... |
### 详细审查
#### 问题1：[风险等级标记] [问题标题]
- **位置**：剧本中具体位置（章/集/段/台词）
- **问题描述**：具体违规内容描述
- **违规依据**：引用具体规则条文或监管文件
- **参考案例**：相似的违规案例（读取 [violation-cases.md](references/violation-cases.md)）
- **修改建议**：具体的修改方案
（对每个问题重复此结构）
### 总体评估
- 整剧立意导向：[积极/中性/消极]
- 上线风险判断：[可上线/需修改后上线/不建议上线]
- 备案建议：[需备案层级和注意事项]
### 优化建议
（非合规类的内容质量建议）
定期更新提醒
审查报告末尾附加提醒：
法规更新提醒：本审查基于截至2026年4月27日的监管规定。建议每月至少进行一次法规更新检索，重点关注：1)广电总局官网新发布的通知；2)各平台（红果/抖音）最新审核标准；3)典型违规案例通报。可使用 websearch-deep skill 搜索"微短剧 审核新规 最新"获取最新动态。
版权声明
MIT License
原作者微信：jujua214
此skill最佳适配ClawWork，官网：https://xiemoai.com/
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 103 lines · 177 tokens per session scan A 15239953e612
ai-script-reviewer is a skill published in the GitHub repository pynooblin/ai-script-reviewer (7 stars, last pushed 6mo ago), licensed MIT. It adds 177 tokens to every session and 1,209 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-31.
ai-script-reviewer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-script-reviewerpynooblin/ai-script-reviewer | Skill | 7 | 6mo ago | MIT | A | 177 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |