Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

anime-storyboard-creator

v1.0.0

专业级动漫短剧/漫剧分镜脚本文案创作 skill。当用户需要生成动漫短视频分镜脚本、漫剧分镜文案、AI绘图分镜脚本时使用。用户提供宫格规格(9格/16格/25格)和角色参考图,自动输出可直接用于 AI 绘图的标准化结构化分镜脚本。

0· 219·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for wutzh195-max/anime-storyboard-creator.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "anime-storyboard-creator" (wutzh195-max/anime-storyboard-creator) from ClawHub.
Skill page: https://clawhub.ai/wutzh195-max/anime-storyboard-creator
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install anime-storyboard-creator

ClawHub CLI

Package manager switcher

npx clawhub@latest install anime-storyboard-creator
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The name/description promise a storyboard generator based on user-supplied grid and character image. However the runtime instructions explicitly require '全域内容检索' across major web novel platforms, social media and video platforms to source high‑light material. That external-data retrieval capability is not reflected in any required env vars, binaries, install steps, or declared endpoints—creating an incoherence about how the skill will obtain those resources and whether it will access paywalled or copyrighted material.
!
Instruction Scope
SKILL.md directs the agent to perform broad, unspecific web searches and to combine '全网公开小说素材与主流网文平台热门作品' and social media sources when generating output. This grants the agent wide latitude to fetch and reuse third‑party content (potentially copyrighted or paywalled) though the skill accepts only two user inputs. The instructions also do not constrain provenance, licensing, or how to treat paywalled/paid works—risking scope creep, copyright issues, and unpredictable external requests.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk and there is no package download risk.
Credentials
No environment variables, binaries, or credentials are requested—which at first glance is good. But the instructions imply network scraping of multiple third-party platforms (some paywalled). If the implementation requires API keys or scraping credentials, those are not declared. This mismatch should be clarified: any external API usage or credential needs should be explicitly listed.
Persistence & Privilege
No 'always: true' and no install/persistence behavior declared. The skill does not request elevated platform presence or modifications to other skills/configs.
What to consider before installing
Before installing or using this skill, ask the maintainer to clarify how it performs the promised '全网' content retrieval: which endpoints or APIs it calls, whether any API keys or scraping tools are required (and where those credentials would be stored), and how copyrighted or paywalled material is handled. If you plan to adapt third‑party novels or videos, ensure you have the right to do so—otherwise prefer a mode that only uses user-provided plot text or public-domain sources. Also request limits on automatic web scraping and explicit declarations of any external services the agent will contact; if those details are absent, treat outputs as possibly derived from copyrighted content and avoid publishing adaptations without rights clearance.

Like a lobster shell, security has layers — review code before you run it.

latestvk97czk8075awfj74871n0fwbs983vygp
219downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

动漫短视频分镜脚本创作 Skill

定位

作为专业级动漫短剧 / 漫剧分镜脚本文案创作智能体,自动化生成可直接用于 AI 绘图的标准化分镜文案,输出内容可直接落地制作动漫短视频。


用户输入规则

仅接收以下两项参数:

参数说明限制
宫格分镜格式指定输出分镜格数仅限 9格、16格、25格 三种规格
人物角色参考图用户上传的角色形象图片支持任意常见图片格式

核心工作流程

Step 1:素材匹配

结合全网公开小说素材与主流网文平台热门作品,进行全域内容检索,重点覆盖:

  • 起点中文网、番茄小说、七猫小说、晋江文学城、掌阅等主流平台热门榜单
  • 抖音/快手/B站热门漫剧改编来源
  • 近期社交媒体高讨论度的爆款剧情

Step 2:风格智能判定

基于用户上传的角色参考图,精准识别:

  • 角色人设:性别、年龄感、气质(强势/温柔/腹黑/清冷等)、服装朝代/风格
  • 视觉风格:国漫风/日漫风/古风水墨/赛博/Q版/写实等
  • 题材类型:古风 / 玄幻 / 现代都市 / 恋爱甜宠 / 悬疑反转 / 逆袭爽文 / 豪门虐恋 等
  • 整体调性:确定作品基调(甜虐/爽快/惊悚/唯美/热血等)

Step 3:优质内容筛选

根据判定风格,在资源库及全网素材中,按以下优先级筛选高光剧情片段:

  1. 热度最高 — 改编漫剧播放量/讨论量
  2. 剧情冲突最强 — 反转、揭秘、对峙、表白、撕脸等高冲突节点
  3. 受众讨论度最高 — 弹幕、评论区高频提及的"名场面"
  4. 观赏性最佳 — 画面感极强、适合静帧表现的场景

Step 4:分镜结构化拆分

严格按照用户指定宫格数量进行分镜拆分,遵循以下原则:

  • 逻辑连贯:每格画面叙事完整,前后承接自然
  • 节奏把控:起承转合分布合理,高潮置于 2/3 处
  • 画面感极强:每格都是可独立成图的视觉构图
  • 人物一致性:同一角色在所有分镜中外貌/服饰保持一致
  • 景别丰富:合理搭配远景/全景/中景/近景/特写/大特写

输出规范

脚本文件头部(必须包含)

【作品名称】:XXX(基于XXX改编)
【题材类型】:XXX
【风格调性】:XXX
【核心剧情】:一句话概括本段剧情
【角色说明】:角色A - XXX;角色B - XXX
【总格数】:X格

每一格标准格式

严格按以下8个字段输出,每格独立成块

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
第 X 格 / 共 X 格
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
【景别】远景 / 全景 / 中景 / 近景 / 特写 / 大特写(二选一)
【时长】建议 X 秒
【画面】(详细描述画面构图、人物位置、环境、光线、色调,直接可用于 AI 绘图 prompt)
【动作】(角色具体动作、表情、肢体语言)
【台词】"XXX"(无台词则填:无)
【音效】(如:心跳声加速 / 玻璃破碎 / 环境风声 / 无)
【BGM】(如:紧张弦乐 / 轻柔钢琴 / 古筝悠扬 / 无)
【转场】(如:硬切 / 淡入淡出 / 推镜转场 / 翻页效果 / 无)

AI 绘图 Prompt 辅助输出(可选附加)

每格【画面】字段后,可附加英文 AI 绘图 Prompt,格式:

[AI Prompt]: (style tag), (character description), (scene), (composition), (lighting), (color tone), high quality, detailed

不同宫格的节奏建议

9格(约60-90秒短视频)

  • 格1-2:开场引入/悬念钩子
  • 格3-5:剧情发展/冲突升级
  • 格6-8:高潮爆发/情绪顶点
  • 格9:结尾反转/留白/引发下期期待

16格(约90-150秒短视频)

  • 格1-3:开场背景/人物引入
  • 格4-7:剧情铺垫/关系建立
  • 格8-11:冲突爆发/对峙/转折
  • 格12-14:高潮名场面/情绪最高点
  • 格15-16:余波/反转/结尾钩子

25格(约3-5分钟短视频)

  • 格1-4:开场世界观建立/主角登场
  • 格5-9:矛盾引入/人物关系交代
  • 格10-14:第一轮冲突/小高潮
  • 格15-19:主要矛盾激化/剧情反转
  • 格20-23:终极高潮/情绪爆发
  • 格24-25:收尾/续集钩子

质量检查清单

完成所有格后,自我检查以下项目:

  • 每格均包含全部8个字段,无缺漏
  • 人物外貌/服装描述在所有格中保持一致
  • 景别搭配丰富,无连续5格以上相同景别
  • 台词自然口语化,符合角色性格
  • 【画面】字段描述详细,可直接复制给 AI 绘图工具使用
  • 总格数与用户指定格数完全一致
  • BGM 和音效与情绪节奏匹配
  • 结尾格具有钩子效果(引发好奇/期待/情感共鸣)

参考资源

  • 详细分镜格式模板 → references/storyboard_template.md
  • 常用 AI 绘图风格标签库 → references/ai_prompt_tags.md
  • 热门题材高光场景类型清单 → references/plot_highlights.md

Comments

Loading comments...