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 anymouschina/TapCanvas --skill tapcanvas-storyboard-expertgit clone --depth 1 https://github.com/anymouschina/TapCanvasWrote 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/anymouschina/tapcanvas/tapcanvas-storyboard-expert)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-storyboard-expert"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-storyboard-expert/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/anymouschina/tapcanvas/tapcanvas-storyboard-expert"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-storyboard-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.06130 |
| Opus 5 | $0.00044 | $0.03065 |
| Sonnet 5 | $0.00018 | $0.01226 |
| Haiku 4.5 | $0.00009 | $0.00613 |
Grade A, and why
tapcanvas-storyboard-expert 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 13d 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 — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TapCanvas Storyboard Expert
何时使用
当用户要你根据小说/剧本章节生成可执行提示词，并明确要求：
- 分多个镜头输出
- 每个镜头要素齐全
- 可直接用于图像/视频模型生成
核心目标
把“叙事文本”转换成“可执行的镜头生产 JSON”，并让输出可同时服务：
- 3D 建模师（形体/材质/姿态约束）
- 导演（调度/镜头/光线/节奏）
- 定格动画（帧步进/微抖动/手工痕迹）
- Seedance / 短剧视频生成（15 秒片段时间轴、镜头节奏、参考图图位、承接上一片段尾帧）
统一职责边界
本 skill 是当前仓库里唯一的章节分镜与 Seedance 派生产物主技能，统一负责：
- 章节正文 -> 章节剧本 / 分镜结构
- 角色 / 场景 / 道具资产规划
- Seedance 15 秒片段时间轴脚本
- 对白、OS、VO、闪回、字幕的脚本表达
- 上一片段尾帧 -> 下一片段首帧的连续性收口
若任务需要 Seedance 风格片段脚本，也必须在本 skill 内完成，不允许再切出平行分镜方法论。
附属参考资料
本 skill 附带以下权威参考资料：
references/seedance-manual.mdreferences/故事转视频脚本-转换工具.mdreferences/优化分镜.mdreferences/好剧本.md
当用户任务明确落在以下场景时，应主动读取对应 reference，而不是只依赖本文件摘要：
- 多模态 Seedance 输入限制、参考图/参考视频/参考音频用法、视频延长、视频编辑、音乐卡点
- 产品展示、角色动作、旅拍、空间漫游、口播、战争、长镜头追踪、伪纪录片等专门模板
- 从原始故事抽取核心梗、人物小传、三幕/四幕结构、15 秒集数弧线、尾帧衔接检查
- Seedance 提示词优化公式、动作/镜头/光影/画质/约束关键词
Seedance 多模态能力边界
当宿主明确要求输出可直接用于 Seedance 的提示词时，同时遵守以下多模态边界：
- 最多 12 个输入文件
- 图片参考
<= 9 - 视频参考
<= 3，总时长<= 15s - 音频参考
<= 3，总时长<= 15s - 支持的 Seedance 任务模式包括：
- 参考图像生成
- 参考视频复刻
- 视频延长 / 续拍
- 视频编辑 / 剧情改写
- 音频驱动口播
- 音乐卡点剪辑
- 不支持把“写实真人脸部素材”当成稳定可复刻输入；若用户强依赖此能力，必须显式提示限制
这些是 Seedance 侧操作约束，不得在派生 prompt 时遗漏。
Seedance 任务询问框架
当用户给的信息不足以直接写出稳定的 Seedance 提示词时，先补齐以下信息：
- 这条视频讲什么故事，核心冲突或卖点是什么
- 时长是多少，默认是否为 15 秒
- 现有参考素材有哪些：图片 / 视频 / 音频
- 画幅比例：
9:16 / 16:9 / 2.35:1 - 整体风格、色调和氛围
- 镜头语言：景别、运镜、转场
- 动作节奏：舒缓 / 急促 / 是否卡音乐拍点
- 声音设计：配乐、环境音、对白、旁白
若这些信息无法从上下文证据中恢复，必须显式指出缺口，而不是脑补。
输出模式（默认）
默认输出 JSON，除非用户明确要求其他格式。
- 仅输出一个 JSON 对象
- 禁止输出 markdown 包裹、解释性前后缀
- 默认必须满足
assets/storyboard-director-schema.v1.1.json的结构约束 - 缺关键输入时显式失败，不输出伪完整 JSON
输出模式（扩展）
除默认 JSON 外，当宿主明确要求“视频片段脚本 / Seedance 时间轴 / 剧本正文格式 / 素材清单”时，可在同一套章节理解基础上派生以下补充产物：
Seedance timeline prompt章节剧本正文资产清单Ending frame continuity note
但这些都属于默认 JSON 的派生产物，不得替代默认 JSON 成为唯一交付，除非宿主或用户明确要求只要这些格式。
强制输出协议
- 必须输出多个镜头，不得只给单段大提示词。
- 顶层必须包含：
schemaVersionchapterglobalStylecastrelationshipGraphmodelingSpecstopMotionSpecatmosphereSpecshots
- 每个镜头必须包含导演与生产关键字段：
shotIddurationSecnarrativeGoalsubjectAnchorscrowdRelationsscenerigAndPosecameralightingactionChaincompositiondramaticBeatperformancecontinuitycontinuityLocksreadabilityChecksfailureRisksnegativeConstraintsprompt
- 章节证据不足时必须显式失败并指出缺什么，不得脑补关键剧情。
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.
- 13d ago First seen · 514 lines · 89 tokens per session scan A 89de30d33de0
tapcanvas-storyboard-expert is a skill published in the GitHub repository anymouschina/TapCanvas (603 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 6,130 once invoked, about $0.0004 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
dramake
A production workflow for turning an idea, story, script, storyboard, or existing footage into a short AI drama or film. It covers planning, generation, voice, editing, and quality checks for formats such as vertical and horizontal video.
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
vchart-development-assistant
A coding assistant for VChart, a JavaScript chart library used to build visualizations such as bar, line, and pie charts.
short-drama-storyboard
A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.
md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…