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 wanghui2323/ai-video-maker --skill make-ai-videogit clone --depth 1 https://github.com/wanghui2323/ai-video-makerWrote 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/wanghui2323/ai-video-maker/make-ai-video)<a href="https://agentmods.dev/skills/wanghui2323/ai-video-maker/make-ai-video"><img src="https://agentmods.dev/badge/skills/wanghui2323/ai-video-maker/make-ai-video/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/wanghui2323/ai-video-maker/make-ai-video"><img src="https://agentmods.dev/badge/skills/wanghui2323/ai-video-maker/make-ai-video.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 | $0.00127 | $0.02067 |
| Opus 5 | $0.00063 | $0.01033 |
| Sonnet 5 | $0.00025 | $0.00413 |
| Haiku 4.5 | $0.00013 | $0.00207 |
Grade A, and why
make-ai-video 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 10d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 视频制作助手
从用户已有的想法或素材开始,先判断输入和当前阶段,再协助完成内容、声音、画面与审核。不要把文章当作默认入口,也不要把首次声音建档、本次正式配音和整片发布合并成一次生成。
启动即执行
触发 Skill 后,立即进入工作流并执行当前可安全完成的步骤,不要只复述流程、列菜单或让用户自己拼命令。
- 先运行
node scripts/doctor.mjs --json检查基础能力。定位或创建本次生产包,检查已有文件、设备、运行时和当前状态;没有生产包时运行node scripts/create-package.mjs --dir <目录> --input-mode <类型> --summary <摘要>,不要临时拼接一套不可复用目录。 - 把用户现有输入写入
video-brief.json,明确缺失项,并继续执行到下一个真实人工门禁。 - 可逆的本地检查、建目录、生成合同对象和校验应主动执行。安装依赖、下载大模型或需要额外系统权限时,说明体积、目录和用途后发起所需批准;获准后继续,不要退回成教程。
- 只有授权/权利不明、核心事实待核验、口播确认、声音所有者选声、整片审核和发布授权等人工门禁才暂停。
- 每次暂停或交付都报告:
当前阶段 / 已完成动作 / 产物路径 / 校验结果 / 需要用户做的一个决定 / 批准后下一步。
用户说“帮我做成视频”代表持续推进到下一个人工门禁;用户明确要求本人克隆声音且没有可用 Profile 时,按下文时钟 A 先执行本地声音建档,然后自动回到时钟 B。不要把“给一句开始话术”当作完成。
读取所需合同
- 先读
references/input-routing.md,把用户输入整理为VideoBrief。 - 设计内容时读
references/content-contract.md。 - 选择画幅和分镜时读
references/visual-routing.md。 - 使用声音、渲染或报告状态前读
references/production-gates.md。 - 只有用户要求克隆或复用克隆声音时,才读
references/voice-cloning.md。 - 进入画面与渲染阶段时读
references/rendering-adapter.md。如果当前项目没有渲染适配器,继续交付内容、声音、字幕和video-unit.json,但不得声称已经可以生成正式 MP4。 assets/example-package/只用于理解完整对象和测试,不作为新项目直接改写;需要首次本地声纹建档时,再复制assets/voice-clone-starter/。
使用两条时钟
时钟 A:低频声音能力建立
仅在用户明确选择克隆声音且没有可用 VoiceProfile 时执行:
授权与私有范围
→ 参考录音和准确逐字稿
→ 三个校准候选
→ 机器 QA
→ 声音所有者选择
→ production-pilot VoiceProfile
这条链通常只在首次建档、参考或模型漂移、授权范围变化时重跑。它先于完整视频生产,但不生成本次正式口播。
时钟 B:每条视频自己的生产
每个视频项目都执行:
VideoBrief
→ ContentDecision
→ VideoContentPlan
→ 口播人工确认
→ 本次 VoiceRun 或其他配音
→ 正式时序
→ 视觉预检
→ 渲染与技术检查
→ 整片人工审核
→ 发布候选
如果已有可用声音档案,在项目开始时做一次 preflight,口播确认后再生成本次三个候选。不要在口播未冻结时提前生成正式音频。
执行工作流
1. 建立 video-brief.json
识别 idea、article、outline、script、source-pack 或 audio 输入。记录受众、期望变化、来源、权利、证据成熟度、时长/画幅偏好和声音意图。
用户只有想法时,协助展开方向,但把假设与待核验事实写入 verificationNeeds;不要编造个人经历、数据或案例。
2. 检查声音依赖
none、human或普通synthetic:按相应合同继续。cloned且已有 Profile:立即 preflight;漂移则阻断。cloned且没有 Profile:读取references/voice-cloning.md,先做设备与本地模型预检;缺少模型时按该参考执行下载与锁定,随后走时钟 A,再自动进入完整生产。
What ships with it
29 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.
- agents/openai.yaml 285 B
- assets/example-package/captions.json 648 B
- assets/example-package/content-decision.json 2.1 KB
- assets/example-package/narration-and-rhythm.md 334 B
- assets/example-package/source-notes.md 885 B
- assets/example-package/video-brief.json 779 B
- assets/example-package/video-content-plan.json 5.7 KB
- assets/example-package/video-unit.json 2.6 KB
- assets/example-package/workflow-state.json 1.0 KB
- assets/voice-clone-starter/gitignore.snippet 78 B
- assets/voice-clone-starter/narration.txt 118 B
- assets/voice-clone-starter/reference-transcript.txt 75 B
- assets/voice-clone-starter/voice-consent.json 513 B
- assets/voice-clone-starter/voice-provider.json 1.9 KB
- references/content-contract.md 2.1 KB
- references/input-routing.md 2.0 KB
- references/production-gates.md 2.3 KB
- references/rendering-adapter.md 1.2 KB
- references/visual-routing.md 1.2 KB
- references/voice-cloning.md 5.7 KB
- requirements-voice-mlx.txt 203 B
- scripts/create-package.mjs 4.1 KB runs code
- scripts/doctor.mjs 3.6 KB runs code
- scripts/providers/qwen3-tts-mlx.py 12 KB runs code
- scripts/qa-voice-run.py 10 KB runs code
- scripts/validate-package.mjs 22 KB runs code
- scripts/voice-common.mjs 7.6 KB runs code
- scripts/voice-profile.mjs 10 KB runs code
- scripts/voice-run.mjs 10 KB runs code
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.
- 10d ago First seen · 143 lines · 127 tokens per session scan A c1aa7edba9e6
make-ai-video is a skill published in the GitHub repository wanghui2323/ai-video-maker (103 stars, last pushed 25d ago), licensed MIT. It adds 127 tokens to every session and 2,067 once invoked, about $0.0006 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.