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 kangarooking/director-skills --skill miora-video-studiogit clone --depth 1 https://github.com/kangarooking/director-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/kangarooking/director-skills/miora-video-studio)<a href="https://agentmods.dev/skills/kangarooking/director-skills/miora-video-studio"><img src="https://agentmods.dev/badge/skills/kangarooking/director-skills/miora-video-studio/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/kangarooking/director-skills/miora-video-studio"><img src="https://agentmods.dev/badge/skills/kangarooking/director-skills/miora-video-studio.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 | $0.00176 | $0.11541 |
| Opus 5.5 | $0.00070 | $0.04616 |
| Sonnet 5.5 | $0.00035 | $0.02308 |
| Haiku 4.5 | $0.00018 | $0.01154 |
Grade A, and why
miora-video-studio scanned grade A with 1 finding 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 28d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **本机可能没有 `curl`、没有 `ffmpeg`**。要下载返回值里的 `signedUrl` 做指纹对账时,用 Python `urllib.request`;要读视频头规格时,直接 `importlib` 加载本脚本复用它的 `probe()`,不必另装工具。 How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
miora 视频生成工作台
使用前提:当前环境已经配置 WorkBuddy / Miora 视频工具。若工具不可用,本 Skill 只能用于诊断与解释,不能替代实际的视频生成通道。
若环境同时提供下列 Skill,可以协同加载:
miora-creative-core—— 底座:确认与费用边界、生成前参数怎么定、画布交付。miora-video-generation—— 决策:镜头语言、时长画幅、主体一致性、失败处置。
它们不是本 Skill 的安装前提;本 Skill 自身负责:完成信号怎么判、参数实测到哪、提示词怎么改。
1. 唯一的核心问题:完成信号
miora 生成进程与对话进程是分离的。由此推出五条,任一条都不能违背:
- 完成信号来自落盘事实,不来自接口返回。 返回值可能整体丢失——实测发生过:15 秒视频生成成功、成片已落盘,调用方什么也没收到。把"没返回"当成"失败"是错的。反向情形同样存在:调用会阻塞到任务完成再返回
status: completed+resultFiles[].localPath(实测等约 6.4 分钟),此时仍要走一次--wait核验——用文件头读规格,不采信自报值。- 返回值里带了
localPath时,那个绑定优先于文件扫描:立刻--wait --claim <localPath> --job <作业名>落账(见第 4 节;--claim不是独立动作,必须和--submit/--wait/--poll/--poll-all之一同时给,否则 argparse 直接报错退出)。别让启发式扫描有机会把并发作业的成片算到你头上。
- 返回值里带了
- 提交之前先登记作业,再发起生成。顺序颠倒就失去跨轮追溯能力。
- 生成后立刻轮询,不靠用户再发一句话。视频要 6 ~ 21 分钟,单轮等得完。
- 规格以文件头为准,时长 / 分辨率 / 音轨自己读出来,不采信自报值。
- 不重复提交。 状态不明不等于失败;重复提交会重复计费,且已提交的任务无法取消。
配套脚本 scripts/miora_watch.py 实现上述判定。
调用前需 connect_cloud_service 取会话凭据,把 clientTempToken 作为 tempKey 传给视频工具。凭据有效期不稳定——实测出现过同一 token 在同一分钟内第二次使用就被拒(AUTH_INVALID_TEMP_KEY)。所以:报 AUTH_*_TEMP_KEY 就重新取一次再重试;连续重试时干脆每次重取,比猜有效期省事。凭据内容不得展示给用户。
1.1 第 0 步:先查工具在不在
每次开工都查,不要凭上次的经验跳过——同一台机器上不同会话的可用性可能不同(实测过:同一台机器,一个会话里 mcp__miora__* 正常可用并成功出片,另一个新会话里完全没有注册)。
开工第一步确认当前会话的工具清单里有没有 mcp__miora__*。
判定分三步,顺序不能颠倒——两种"缺失"形态容易混判。
第一步:先看主工具清单。 如果 mcp__miora__miora_reference_to_video / mcp__miora__miora_text_to_video / mcp__miora__miora_write_canvas 这些直接出现在当前会话的可调用工具清单里,那就是可用,直接开工。 无需再做任何探查——它们不在 deferred 索引里,ToolSearch 天生搜不到它们。
第二步(仅当主清单里看不到 mcp__miora__* 时): ToolSearch 用 queries: ["miora"] 搜。这里的结果只用于识别"server 条目在、子工具一个都没注册"的空壳状态:available_deferred_tools 里列着 mcp__miora,但对比 mcp__agent-mail / mcp__sheetagent 能看到人家的子工具名都展开了,miora 没有。
第三步(二次确认): 用 DeferExecuteTool 探 mcp__miora__miora_reference_to_video——报 Tool "..." not found in the deferred tools index 才是决定性证据。
第四步(只在确诊缺失后做,用于分清"没配"还是"没启用"): 三处落盘证据一起看,给用户的结论才具体。
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.
- 28d ago First seen · 395 lines · 176 tokens per session scan A 3b4441ecce74
miora-video-studio is a skill published in the GitHub repository kangarooking/director-skills (202 stars, last pushed 10d ago), licensed MIT. It adds 176 tokens to every session and 11,541 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
lanshu-create-ai-presenter-video
Turn a topic or finished script into a complete, publish-ready explainer video — led by an AI presenter from an authorized adult presenter image, or performed with no presenter in one of twelve explainer styles (nine visual styles and three narrative ones). Not for promos, ads, or footage montages. Use for new…
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…
prop-asset
A preset for designing reference images of props, meaning objects used in a scene or production. It records an object’s appearance, materials, dimensions, condition, views, ownership, orientation, and consistency rules.