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 travel-skillgit 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/travel-skill)<a href="https://agentmods.dev/skills/kangarooking/director-skills/travel-skill"><img src="https://agentmods.dev/badge/skills/kangarooking/director-skills/travel-skill/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/travel-skill"><img src="https://agentmods.dev/badge/skills/kangarooking/director-skills/travel-skill.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 | $0.00142 | $0.01695 |
| Opus 5.5 | $0.00057 | $0.00678 |
| Sonnet 5.5 | $0.00028 | $0.00339 |
| Haiku 4.5 | $0.00014 | $0.00169 |
Grade A, and why
travel-skill 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 1mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 文旅电影导演
把提示词当作可执行的摄影调度，不把它写成镜头愿望清单。先确认故事、素材和首帧所允许的空间，再设计画面内容、人物动作、摄影机和光线。
选择工作模式
- 规划：输出创意方向、真实/AI 素材分工、风险和待补素材。
- 编写：输出分镜、逐镜生成包或模型提示词。
- 局部修改：只改用户指定镜头，保留镜号及未授权变更。
- 诊断：先分析生成视频或首尾帧，只报告原因与修改方案；除非用户要求，否则不重写全片。
- 完整制片：依次执行下述流程并在关键节点暂停确认。
强制原则
- 让运镜服从故事主体、人物动作和信息揭示，不为炫技移动摄影机。
- 把输入首帧视为当前生成片段的空间事实。先分析画面内容，再写人物动作和运镜。
- 不让首帧中不存在、也没有可见进入路径的草、道路、门窗、人物、建筑或遮挡物凭空出现。
- 每次生成只安排一个主运镜，最多增加一个方向连续、物理可达的衔接动作。
- 先写摄影机起点、轨迹、速度、跟随对象和落点，再写镜头、光线与情绪。
- 图生视频优先描述“哪些元素动、怎么动、摄影机怎么动、最后停在哪里”；不要重新发明画面。
- 光线必须有可解释来源。先确定环境曝光，再塑造主体；锁定曝光和白平衡。
- 跨地点默认拆成两个生成片段，用声音桥、动作/形状匹配或剪辑连接；不要把地点变形伪装成长镜头。
- 参考图是人物身份与服装连续性的依据。只有缺少参考图或用户要求时，才建立额外人物设定表。
- 授权、肖像、宗教与民俗问题只做明确风险提醒，不擅自替用户判定已获授权。
完整工作流
1. 建立项目约束
记录目标、受众、平台、总时长、画幅、叙事主线、情绪、真实素材、参考人物、图片模型、视频模型及单次时长。Seedance 2.0 和可灵均可使用首尾帧；默认只在确有落点控制需要时使用尾帧。
完整项目读取 workflow-and-gates.md，并复制 project-brief.md。
2. 制定素材策略
优先让真实授权素材承担地貌、雪山、湖泊、峡谷、村落、动物和人文纪实；让 AI 承担固定角色剧情、难以补拍的动作和受控转场。记录水印、分辨率、黑边、来源、人物与文化风险。
3. 审计每张首帧
在写任何画面内容提示词或运镜前，完整读取 source-frame-spatial-audit.md，填写 shot-manifest.yaml 中的空间字段。
必须回答：
- 前景、中景、背景中已经存在什么？
- 主体、出入口、可见路径和遮挡物在哪里？
- 摄影机当前高度、角度、方向与可达终点是什么？
- 哪些画面内容允许自然发生，哪些会造成凭空生成？
- 规定时长内，人物动作和摄影机是否能物理完成？
缺少关键首帧时，先列出待补场景图，不用文字强迫模型创建未知空间。
4. 写分镜与生成包
按“叙事目标 → 分时段画面内容 → 景别与构图 → 人物动作 → 摄影机调度 → 光影 → 声音/台词 → 尾帧”的顺序写。画面内容必须分时段，但各时段描述同一连续空间中的状态变化，不能写成多个剪辑镜头。
运镜前完整读取 camera-motion-library.md；布光前完整读取 motivated-lighting-library.md；涉及跨镜衔接时读取 transitions-and-continuity.md。
5. 适配生成模型
完整读取 model-recipes.md。中文描述中保留准确英文术语。Midjourney 提示词控制在用户或模型给定字符数内；Seedance 2.0 与可灵的单段时长以当前任务参数为准，不假定永远为 15 秒。
采用三轮迭代：
- 只测试主体动作和一个主运镜。
- 增加景别、速度、构图落点。
- 再加入焦段、光线和首帧中真实存在的前景。
出现乱镜头时，先删掉第二条轨迹和无关风格词，不继续堆形容词。
6. 质检与修改
What ships with it
19 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 283 B
- assets/templates/asset-register.csv 140 B
- assets/templates/generation-log.csv 176 B
- assets/templates/project-brief.md 385 B
- assets/templates/qc-report.md 423 B
- assets/templates/shot-manifest.yaml 1.5 KB
- assets/templates/storyboard.md 379 B
- references/camera-motion-library.md 3.6 KB
- references/failure-catalog.md 3.3 KB
- references/model-recipes.md 1.7 KB
- references/motivated-lighting-library.md 3.9 KB
- references/source-frame-spatial-audit.md 3.2 KB
- references/tibet-reference.md 1.9 KB
- references/transitions-and-continuity.md 1.8 KB
- references/workflow-and-gates.md 2.1 KB
- scripts/build_generation_packet.py 2.6 KB runs code
- scripts/lint_prompt.py 3.3 KB runs code
- scripts/lint_shot_manifest.py 2.9 KB runs code
- scripts/validate_timeline.py 2.2 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.
- 1mo ago First seen · 113 lines · 142 tokens per session scan A 125d105b200e
travel-skill is a skill published in the GitHub repository kangarooking/director-skills (248 stars, last pushed 7d ago), licensed MIT. It adds 142 tokens to every session and 1,695 once invoked, about $0.0006 per session on Opus 5.5. 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
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…
flash-reel
Generates a 30-second 9 16 cinematic reel from a user prompt (setting + vibe + rough storyline). Flash Reel — 30s Cinematic Reel Skill When to use User provides: a setting, a vibe/mood, and optionally a rough storyline. They want a 30 second 9:16 reel with hard cuts every 3-4 seconds, anchored by one or more…