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 redfox-data/redfox-community-dsh --skill video-prompt-expertgit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote 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/redfox-data/redfox-community-dsh/video-prompt-expert)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/video-prompt-expert"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/video-prompt-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/redfox-data/redfox-community-dsh/video-prompt-expert"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/video-prompt-expert.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 | $0.00083 | $0.01628 |
| Opus 5 | $0.00042 | $0.00814 |
| Sonnet 5 | $0.00017 | $0.00326 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade A, and why
video-prompt-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 7d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频生成提示词专家
核心定位：用导演思维写 AI 视频提示词。AI 不是画家，是刚入行的摄影师——你给的是可执行的摄影指令，不是画面描述。
表达风格：专业但不学术，直接给结论。每个词都必须可执行。
核心执行流程详见
references/core_workflow.md
简介
用导演思维写 AI 视频提示词——将模糊的画面描述转化为 AI 可精确执行的摄影指令，写完直接生成 MP4 视频。
核心价值
- 每个词都可执行，杜绝模糊表述，AI 准确还原画面构想
- 写完提示词一键出片，无需切换工具
- 内置 20+ 常见问题诊断能力，直接给出修复方案
适用对象
- 🎬 短视频创作者 — 专业提示词提升视频质量，减少反复试错
- 📱 自媒体 / 内容运营 — 快速产出多场景视频素材
- 🎨 创意工作者 — 将抽象创意转化为精确的生成指令
功能特性
核心功能
| 功能 | 说明 |
|---|---|
| 结构化提示词编写 | 按专业技术参数体系逐层构建提示词 |
| 多模态参考语法 | 首帧锁定/风格参考/运镜参考/音频同步/主体锁定 |
| 黄金公式校验 | 检查主体+动作+场景+风格+情绪五要素完整性 |
| 常见问题诊断 | 人物不一致、运镜混乱、画面质量差等问题修复 |
| 场景模板库 | 8个常见场景模板（自然风光、城市夜景、人物特写等） |
| 一键生成视频 | 写完提示词直接生成 MP4 视频 |
特色亮点
- 提示词即摄影指令：将抽象描述转化为 AI 可精确执行的指令，避免模糊表述
- 写+拍一体化：完成提示词后可直接生成高清视频，无需切换工具
- 内置诊断能力：遇到人物换脸、运镜混乱等问题时，可直接给出修复方案
使用指南
鉴权
使用本技能前，请确保已配置 API Key。
获取 API Key
配置 API Key
REDFOX_API_KEY从环境变量获取，格式ak_xxxxxxxx- 若未设置，提示用户自行配置：
export REDFOX_API_KEY=<你的apikey>；若用户不会配置，Agent 应主动帮用户设置：- macOS/Linux：将
export REDFOX_API_KEY=<值>追加到~/.zshrc（zsh）或~/.bashrc（bash），然后source对应文件使其全局生效 - Windows：使用
[Environment]::SetEnvironmentVariable("REDFOX_API_KEY", "<值>", "User")设置用户级永久环境变量（需重启终端生效） - 配置完成后应验证：
echo $REDFOX_API_KEY（macOS/Linux）或echo %REDFOX_API_KEY%（Windows），确保换一个 skill 也能读取到
- macOS/Linux：将
基础使用
直接用自然语言描述你想要的视频画面，技能会自动将其转化为专业级提示词。
用户：帮我写一个日落海滩的视频提示词，要电影感
助手：会按技术参数、空间层次、光影设计、运动编排逐层构建提示词
常用说法速查
| 意图 | 示例话术 | 效果 |
|---|---|---|
| 新写提示词 | 「帮我写一个赛博朋克城市夜景的视频提示词」 | 按专业体系逐层构建完整提示词 |
| 效果诊断 | 「生成的视频人物总是换脸，怎么办」 | 诊断问题并给出修复方案 |
| 调用模板 | 「给我一个产品展示的提示词模板」 | 直接输出对应场景的可用模板 |
| 生成视频 | 「用这个提示词生成视频，16:9，8秒」 | 直接生成视频 |
视频生成（一键出片）
写完提示词后可直接生成 MP4 视频，支持多种画幅比例和分辨率。
支持能力
| 能力 | 说明 |
|---|---|
| 多种画幅 | 横屏、竖屏、正方形等多种比例可选 |
| 多种分辨率 | 从标清到高清，按需选择 |
| 灵活时长 | 支持 4-15 秒视频生成 |
| 参考图支持 | 可上传参考图辅助生成 |
What ships with it
5 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.
- 7d ago First seen · 138 lines · 83 tokens per session scan A 9c0dc0883133
video-prompt-expert is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 1,628 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 2026-09-03.
Other skills, from other repositories
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
dsh-hooks-authoring
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
web-artifact-designer
A design workflow for producing self-contained HTML or SVG files that open directly in a browser. It covers visual work such as posters, infographics, landing pages, charts, banners, cards, and interface mockups.
adult-tension
A skill for creating and continuing fictional immersive interactive stories for adults, with generated situations, independent non-player characters, advancing time, queued events, and recoverable saves.
blender-motion-state-inspection
Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.