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 isjiamu/jiamu-skills --skill tvc-ad-filmgit clone --depth 1 https://github.com/isjiamu/jiamu-skillsWrote 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/isjiamu/jiamu-skills/tvc-ad-film)<a href="https://agentmods.dev/skills/isjiamu/jiamu-skills/tvc-ad-film"><img src="https://agentmods.dev/badge/skills/isjiamu/jiamu-skills/tvc-ad-film/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/isjiamu/jiamu-skills/tvc-ad-film"><img src="https://agentmods.dev/badge/skills/isjiamu/jiamu-skills/tvc-ad-film.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 | $0.00219 | $0.02758 |
| Opus 5 | $0.00110 | $0.01379 |
| Sonnet 5 | $0.00044 | $0.00552 |
| Haiku 4.5 | $0.00022 | $0.00276 |
Grade A, and why
tvc-ad-film 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 12d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TVC 产品广告片
定位
- 只负责:把「一个产品 + 一句诉求」变成一条 15-25 秒的 TVC 品牌广告短片,走完「产品理解 → 创意方案 → 分镜脚本 → 逐镜头提示词 → 成片」。
- 不负责:达人口播 / UGC 种草、多集剧情、静态物料;不负责画幅 / 分辨率 / 模型等规格——用户没指定就走默认,不硬填。
输入
- 必须有:产品是什么(名称 / 图片 / 简单描述,任一即可起步)。
- 缺失会显著改变成片的,先问:核心卖点(1-3 个)、目标受众、投放场景、期望调性、slogan 或必须出现的元素。
- 严守项:品牌名、产品名、slogan、包装上的事实信息——逐字准确,不改写、不臆造功效。
- 参考项:用户给的风格偏好是方向不是枷锁,方案里可以给出你认为更优的选择供其确认。
内部流程与 Knowhow
Step 1 · 产品理解
从产品图和描述提炼三件事:
- 品类与真实使用场景(谁、在什么时刻、解决什么问题)。
- 包装的视觉资产:主色、IP 形象、瓶型 / 袋型、可入镜的图形元素——这些是全片的品牌底色和记忆锚点。
- 卖点的「可拍化」翻译:每个卖点必须翻译成镜头拍得到的画面("天然无添加"→ 真实花田与原料超微距;"孩子爱喝"→ 孩子抢着喝的表情);包装上的每个视觉资产也顺手映射成候选镜头语言(IP 形象 → 角色镜头,主色 → 色彩体系底色,原料图案 → 微观世界入口)。
产出一段简短的《产品视觉档案》给用户过目:我看到了什么、我准备用什么。
Step 2 · 创意方案(6 选 1)
加载 创意风格库.md,一次给出 6 个创意方向,每个包含:方案名、一句话故事概念、风格基调、叙事策略、情绪曲线、预计记忆点。
合格判准:
- 叙事策略互不重复,且在风格库给出的三个维度(世界观尺度 / 情绪曲线 / 真实度光谱)上呈明显分布——不是同一个创意换六层皮。
- 至少 2 个方案是该品类广告的非常规拍法,但能自圆其说为什么适合这个产品。
- 每个方案都能回答:观众看完 20 秒,记住了什么?答不出来的方案不合格。
用 ask_human 让用户选一个(允许"方案 2 的世界观 + 方案 5 的结尾"式杂交,杂交后按新方案重新过一遍判准)。
Step 3 · 分镜脚本
按选定方向写 5-6 镜脚本,节奏走「起承转合」:首镜立世界观 / 悬念,中段引入角色与产品、渐快,倒数第二镜是情绪高点或视觉奇观,末镜回归产品与品牌收束。单镜 2-4 秒,总时长默认 15 秒以内——以能被视频模型一次生成覆盖为准(如 Seedance 2.0 一次生成 15 秒整片),这是成片一致性的最优区间。用户明确要更长时,按"每段一次生成上限"设计成多段,段与段之间设计一个桥接镜头(元素或动作跨段延续)。
脚本分条列出每镜的画面、情绪、产品是否露出,给用户确认后再进提示词。
Step 4 · 逐镜头提示词
加载 分镜提示词规范.md,严格按其生成:总控头(六要素)定全片风格,逐镜头(七要素)写视听细节,整段连续文本输出。规范里的关键约束逐条对照,不凭印象。
Step 5 · 锚点与关键帧
- 产品锚点图:包装事实还原、全片复用;用户上传的产品图优先直接注册为锚点,不重绘。
- 角色锚点:方案里有 IP 形象或关键角色的,生成横向四视图(脸部特写、正面、侧面、背面,纯白背景)作为锚点——四视图比单张立绘更能锁住多角度镜头下的一致性。用户自己有角色图就直接用,标记为最高优先级参考。
- 场景锚点:需要场景参考图时,把主角 / 产品放进场景图里一起出——一张图同时交代场景氛围和角色与环境的相对大小,防止视频里比例失调。
- 关键帧确认:视频生成前,先出 1-2 张关键帧图(通常是首镜画面 + 末镜产品收尾画面),风格按总控头执行,给用户过目。这是最后一道便宜的闸门——文字脚本锁不住视觉风格,关键帧能;用户在图上说"不对",成本是一张图,在视频上说"不对",成本是一整条片。
- 喂给视频模型的参考图必须是干净的画面帧(锚点图、关键帧)——带标注、表格、运动曲线、箭头的故事板信息图绝不入模,模型会把标注当画面内容,错漏百出。
Step 6 · 生成与合成
- 整片一次生成是首选:总时长在单次生成上限内时,把完整的逐镜头提示词连同锚点、关键帧一次交给支持该时长的模型(如 Seedance 2.0 一次生成 15 秒)整片生成——让模型一次看到全部镜头的衔接逻辑,是消灭跨段接缝、音乐打架、角色走形的根本手段。
- 抽卡是常规操作不是失败补救:同一份提示词生成 2-3 次,一次 15 秒 = 5-6 个连贯镜头,三次就是十几个可选素材——逐镜挑最佳,个别镜头不满意时用最佳素材混剪替换,不必整条重来。
- 分辨率判准:抽卡阶段用模型提示词响应最好的中低档分辨率(更快、更便宜、跟随提示词更准),定稿后再对成片做超分放大;不要在抽卡阶段追高清——高分辨率档位往往响应更差还容易改变主体形象。
- 更长的片子按段串联:每段都是一次完整生成(段内含多镜头),段与段在桥接镜头处相接;生成后段时,把前一段成片作为衔接参考一并输入,桥接处用元素衔接或首尾帧卡点,让观众看不出段落边界。
- BGM 按脚本的声音叙事线单独生成,在合成阶段与视频(含音效)统一叠加。
- 生成后逐镜比对提示词:风格是否统一、衔接是否成立、产品与包装是否走形、有没有凭空多出来的字幕或文字。
What ships with it
2 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.
- 12d ago First seen · 86 lines · 219 tokens per session scan A 15e207cacd8d
tvc-ad-film is a skill published in the GitHub repository isjiamu/jiamu-skills (134 stars, last pushed 2mo ago), licensed MIT. It adds 219 tokens to every session and 2,758 once invoked, about $0.0011 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…