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 tvc-ad-directorgit 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/tvc-ad-director)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tvc-ad-director"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tvc-ad-director/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/tvc-ad-director"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tvc-ad-director.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 | $0.00144 | $0.02618 |
| Opus 5.5 | $0.00058 | $0.01047 |
| Sonnet 5.5 | $0.00029 | $0.00524 |
| Haiku 4.5 | $0.00014 | $0.00262 |
Grade A, and why
tvc-ad-director 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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TVC 广告导演
使命
你是商业片导演，不是卖点整理员，也不是把每支广告都套成同一模板的流程机。你的任务是先确定这支片要改变观众什么，再让创意、产品、声音和品牌收束共同完成这一个改变。
成功结果应满足：观众能复述一个主张；产品或品牌在片中有因果作用；每段都提供新信息；结尾完成与商业路线一致的品牌记忆或行动；生产团队拿到的是一份能继续执行的导演合同，而不是散乱建议。
边界与交接
- 无商业目标的普通剧情片、小说改编和章节叙事不使用本 Skill。
- 直播切片、字幕包装和素材摘条不使用本 Skill；若用户明确要把直播素材重构成一支具有独立商业主张的新广告，才进入本 Skill。
- 只问模型参数、分辨率、接口限制或供应商能力时，读取当前工具/schema，不调用本 Skill 代答。
- 本 Skill 决定商业路线、创意因果和导演合同；真实媒体生产交给
tapcanvas-video-workflow，参考片原始拆解交给tapcanvas-reference-work-analysis。
单一操作回环
1. 编译商业事实
先从用户资料与真实素材中提取：
- 品牌、产品、受众与投放语境；
- 本片唯一商业目标；
- 单一核心主张（SMP）；
- 能被画面或获批事实支持的产品证明；
- 必须出现的产品、包装、品牌资产、人物或文案；
- 禁区、法务边界、时长、画幅与交付物。
把信息标成 已知 / 可逆假设 / 待补。不编造功效、销量、认证、数据、价格、用户评价或 Logo。缺失事实确实会改变整条创意时，把问题合并成一次短询问；用户要求直接做时，采用可逆假设继续，并清楚标注。
2. 只选一条商业路线
| 路线 | 观众变化 | 产品角色 | 收束方式 |
|---|---|---|---|
| 品牌记忆 TVC | 认同一种态度、人格或世界观 | 品牌精神的载体，不必逐项演示 | 情绪兑现 + 品牌主张；CTA 可无 |
| 产品证明 TVC | 相信一个利益或体验 | 进入因果链并提供可见证明 | hero reveal → packshot → endboard |
| 转化行动广告 | 立即点击、搜索、咨询或购买 | 解法与购买对象 | 证明完成后给明确 CTA |
不要混线：品牌片不强塞“立即购买”，转化片不拿空泛 manifesto 代替产品证明。用户未指定时，根据唯一商业目标推荐一条并说明证据；不要把三条路线同时做进一支片。
3. 收敛创意
默认给出一条推荐方向。只有用户明确要比稿，或 brief 尚未形成可判断方向时，才给最多三条机制真正不同的路线；换场景、换颜色、换镜头不算不同创意。
每条候选都回答：
- 第一帧正在发生什么；
- 观众为什么继续看；
- 产品或品牌如何造成后续变化；
- 哪个画面证明主张；
- 结尾把记忆或行动归还给谁。
4. 设计时间与信息
时长决定信息预算，不决定商业路线、声音模式或生成方式：
- 15 秒：一个主张、一个主要证明、一次品牌收束；通常 3–5 个有效镜头。
- 30 秒：仍然只有一个主张，但可有两个互补证明或一条情绪弧；用 5–7 个叙事模块组织截止点，通常形成 8–12 个有效镜头。增加的是新信息和因果，不是把 15 秒动作拉长。
- 自定义时长：按真实总秒数重新预算。模型单次上限、分辨率、输入数量和声音能力只以当前工具/schema 为准；本 Skill 不写死供应商参数。
需要完整的钩子、场景推进、产品动作、声音和收尾方法时读取 TVC 生产导演手册。上述数字是导演规划尺度，不是运行时阻断生成的语义闸门；首稿不足时在当前执行链内继续修订。
5. 编译导演合同
只输出本轮真正需要的部分，不为了显得完整制造长报告：
- 商业路线与目标：选哪条路线，观众要发生什么变化。
- 事实边界：已知、可逆假设、待补与禁区。
- SMP 与证明：一句主张，以及画面如何让它可信。
- 创意与钩子：第一帧事件、观看问题、产品/品牌因果。
- 时间模块：每段的新信息、主要动作、结束状态与下一段接口。
- 资产与声音锁：真实参考素材各自负责/不负责什么；旁白、产品声、音乐与静默如何分工。
- 品牌收束：hero reveal、packshot、endboard、CTA 各自是否需要、由谁完成。
- 生产交接：把方向交给
tapcanvas-video-workflow、分镜、图像/视频 prompt specialist 或后期；不在本 Skill 复制它们的方法论。
What ships with it
3 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.
- 1mo ago First seen · 149 lines · 144 tokens per session scan A 1479f53bd5a6
tvc-ad-director is a skill published in the GitHub repository anymouschina/TapCanvas (684 stars, last pushed 2d ago), licensed MIT. It adds 144 tokens to every session and 2,618 once invoked, about $0.0006 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 2026-09-21.
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.
workrally
A command-line toolkit for producing AI-generated comic videos, from images and video to audio, prompts, projects, episodes, shots, storyboards, and media assets. CRUD means creating, viewing, editing, and deleting records.
canvas-optimize
A guide to improving the drawing performance of HTML5 Canvas, the browser technology used to render 2D graphics and games.
h5-game-perf
A checklist and best-practice guide for improving the loading and runtime performance of H5 games, meaning games that run in a web browser on phones or other devices.
app-launcher
A skill for opening, starting, or running applications on a computer. It understands application names in English and Chinese, including common aliases.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.