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 hanzhcn/laohan-skills --skill laohan-fenjingtishicigit clone --depth 1 https://github.com/hanzhcn/laohan-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/hanzhcn/laohan-skills/laohan-fenjingtishici)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-fenjingtishici"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-fenjingtishici/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/hanzhcn/laohan-skills/laohan-fenjingtishici"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-fenjingtishici.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 | $0.00099 | $0.01398 |
| Opus 5 | $0.00049 | $0.00699 |
| Sonnet 5 | $0.00020 | $0.00280 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
laohan-fenjingtishici 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
分镜提示词生成与校验
为产品带货/短视频生成分镜图片提示词,并校验输出质量。
不适用场景
- 生成视频本身 → 这是分镜图片提示词,不是视频生成
- 生成封面图 → 用 laohan-fengmianqiuzhi
- 生成口播稿 → 用 laohan-chuangzuo
- 没有产品描述 → 模式1必须提供产品视觉描述才能生成
使用
# 模式1:生成 Gemini 提示词模板
/laohan-fenjingtishici <视频秒数> <产品视觉描述>
# 模式2:校验并拆分 Gemini 返回的分镜
/laohan-fenjingtishici <用户粘贴的 Gemini 输出>
模式1:生成提示词模板
输入视频秒数和产品描述,输出可直接粘贴到 Gemini 的提示词(内嵌所有规则)。
提示词模板内容见 references/prompt_template.md。
模板中需要替换的变量:
{VIDEO_LENGTH}→ 实际视频秒数{FRAME_COUNT}→ 向上取整(视频秒数 ÷ 5){PRODUCT_DESCRIPTION}→ 产品的视觉特征(颜色、材质、形状)
模式2:校验并拆分
用户把 Gemini 返回的分镜结果粘贴过来,按检查清单逐项验证,通过后拆分为独立文件。
检查清单
校验以下 8 项,每项通过/失败+具体问题:
| # | 检查项 | 通过标准 |
|---|---|---|
| 1 | 帧数正确 | 帧数 = 向上取整(视频秒数 ÷ 5) |
| 2 | 产品占位符一致 | 所有帧中产品位置都使用 [PRODUCT] 占位符(除非物理状态变化) |
| 3 | 动势预设 | 每帧都有 mid-action / 动态姿势描述 |
| 4 | 正负分离 | Positive Prompt 和 Negative Prompt 已分离 |
| 5 | 无填充词 | 没有 "Generate an image..."、"HIGH RESOLUTION" 等对话式指令 |
| 6 | 无 meta-tags | 没有 "(Product reference: ...)" 标签,产品用 [PRODUCT] 占位 |
| 7 | 摄影术语 | 包含景别、角度、f值、焦距、光源方向、色温K值、照明技法 |
| 8 | 场景一致性 | 所有帧的 [SCENE] 描述完全相同(背景/环境/氛围不可跳变),只允许机位和光位变化 |
校验失败处理
- 项 1(帧数错误):自动修正帧数,提示用户重新生成
- 项 2(占位符不一致):标出差异帧,建议统一替换为 [PRODUCT]
- 项 3-8:标出具体问题帧和修改建议,不自动修改(保持 Gemini 原始输出)
拆分规则
校验通过后,每帧拆为一个文件:
{输出目录}/frame_1_prompt.txt
{输出目录}/frame_2_prompt.txt
...
{输出目录}/frame_N_prompt.txt
输出目录默认为当前项目目录,可由用户指定。
文件格式
每个文件包含帧标题 + Positive Prompt + Negative Prompt,和 Gemini 输出格式一致:
Frame N [timestamp - storytelling purpose]:
Positive Prompt:
[完整提示词]
Negative Prompt:
[negative 内容]
提示词工程规则
这些规则同时嵌入模板和用于校验:
- 5秒分段:每帧对应一个 5 秒视频片段(Wan 2.2 的 81 帧 ÷ 16fps)
- 余数向上取整:32 秒视频 → 7 帧(35 秒),最后一帧按完整 5 秒节奏描述,后期裁剪
- 单一节拍:每帧只描述一个动作/时刻
- 纯视觉描述:适配扩散模型,不含对话式指令,分辨率由工具控制
- [PRODUCT] 占位符:产品外观用 [PRODUCT] 占位,生图时由上传的产品参考图决定外观,不写具体产品描述
- 动作适配(CRITICAL):彻底根除参考视频中绑定原产品的专属交互(套硅胶壳、穿挂绳、塞入耳塞),替换为通用高级商业交互("adjusting outer textures"、"arranging items gracefully"、"presenting side-by-side")
- 环境强制隔离:剥离参考视频的特定背景/风格,强制用 "real commercial photography style"
- 场景一致性锁定:所有帧的 [SCENE] 必须完全相同(同一背景/环境/氛围),只允许机位和光位变化
- 动势预设:每帧描述 mid-action 姿态,为 I2V 提供运动张力
- 正面/负面分离:可直接复制到 ComfyUI 的两个 CLIPTextEncode 节点
- 负面提示词语义:
floating objects压制的是无因漂浮噪声,不与 positive 中的手部受因悬停矛盾 - 负面基线:每帧 Negative Prompt 默认包含 "CG, glowing effects, over-saturation"
What ships with it
1 file 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 · 111 lines · 99 tokens per session scan A b72eee6906dd
laohan-fenjingtishici is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 1,398 once invoked, about $0.0005 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
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
douyin-upload
A workflow for using the sau command-line tool to log in to Douyin, the Chinese short-video platform, check account cookies, and publish videos or image-and-text posts.
kuaishou-upload
A workflow for using the sau command-line tool to log in to Kuaishou, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
xiaohongshu-upload
A workflow for using the sau command-line tool to log in to Xiaohongshu, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.