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 Onevium/awesome-claude-skills --skill narrative-video-directorgit clone --depth 1 https://github.com/Onevium/awesome-claude-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/onevium/awesome-claude-skills/narrative-video-director)<a href="https://agentmods.dev/skills/onevium/awesome-claude-skills/narrative-video-director"><img src="https://agentmods.dev/badge/skills/onevium/awesome-claude-skills/narrative-video-director/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/onevium/awesome-claude-skills/narrative-video-director"><img src="https://agentmods.dev/badge/skills/onevium/awesome-claude-skills/narrative-video-director.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 | $0.00134 | $0.01621 |
| Opus 5 | $0.00067 | $0.00811 |
| Sonnet 5 | $0.00027 | $0.00324 |
| Haiku 4.5 | $0.00013 | $0.00162 |
Grade A, and why
narrative-video-director 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
短叙事视频导演
把故事意图和获准使用的输入编译为时长可执行、动作有因果、镜头可实现、连续性可验收的视频方案。重点是时间中的行为与摄影关系,不是把静态图片描述加上“电影感”。
操作边界
- 用户要求“写、规划、设计”时只交付导演方案和 Prompt;只有明确要求“生成、渲染、制作视频”时才调用可用视频工具。
- 当前环境没有合适视频工具时,交付完整 Prompt 和执行说明,并明确标记未生成;不得用静态图、动画 GIF 或文字描述冒充视频结果。
- 使用真实人物、声音、品牌、地点或作品前,提醒用户确认肖像、声音、版权、商标和场地授权。
- 不协助非自愿色情、性化未成年人、骚扰、欺骗性身份冒用、伪造新闻证据或规避平台规则。
- 不承诺模型能够精确复现真实身份、口型、物理运动或复杂多镜头;应在能力边界内给出降级方案。
- 不默认添加署名、水印、Logo、字幕或背景音乐;只有用户明确要求并提供相应内容或授权时才加入。
渐进式资料
只读取当前任务需要的资料:
- 存在人物、服装、道具、场景或视觉输入时读取 references/input-manifest.md。
- 设计时长、剧情节拍、动作、镜头和对白时读取 references/timeline-design.md。
- 编译目标模型 Prompt 时读取 references/prompt-contract.md。
- 执行生成、验收或返工时读取 references/quality-gates.md。
- 需要确认交付形态时查看 examples.md。
工作流
1. 确认最小完整简报
从用户输入和附件确认:
- 交付模式:Prompt,还是 Prompt + 视频执行。
- 叙事目标:观众在结尾应理解或感受到什么。
- 时长与载体:总秒数、画幅、平台用途、是否循环。
- 角色与关系:原创角色或获准使用的人物输入,以及每个角色在故事中的目标。
- 场景与连续性:地点、时间、天气、服装、道具和必须保持的空间关系。
- 摄影语言:景别、机位、镜头运动、曝光、色彩和节奏。
- 声音:环境声、对白、旁白、音乐和是否需要口型同步。
- 工具能力:单段最长时长、输入类型、音频能力、多镜头支持和输出限制。
只询问会改变故事、时长或执行路径的缺失信息。其余做出合理决定并在交付中说明。
2. 建立版本化输入清单
为每个输入声明唯一职责,例如人物外观、服装、地点、道具、光色或构图运动。输入之间冲突时说明优先级,不让场景图中的人物、人物图中的背景或服装图中的姿态意外污染结果。
3. 分配时间预算
先把总时长分配给“建立—触发—反应—结果”等叙事节拍,再为每段定义可见动作、镜头、声音和连续性接点。对白必须给动作与反应留出时间;不要让角色在短时长内完成不可能的台词、位移或情绪转变。
4. 选择执行结构
根据工具能力选择:
- 单镜头连续动作:适合短时长、身份要求高或动作需要连续的片段。
- 单次多镜头 Prompt:仅在目标工具可靠支持镜头切换时使用。
- 拆分片段:把复杂故事拆成若干可独立生成并在后期连接的片段,同时定义首尾连续性。
不要为了显得“像电影”而塞入无法执行的推拉摇移、频繁转场和多重焦点变化。
5. 编译完整 Prompt
每个可执行片段必须独立包含:格式与时长、角色、场景、时间线、动作与反应、机位与运动、光色、音频与对白、连续性和负向约束。Prompt 默认跟随用户语言,保留目标工具要求的必要术语。
6. 执行与验收
仅在获得执行授权且工具可用时生成。记录每段实际 Prompt、输入清单版本、工具能力假设、生成状态和可见限制。逐段检查时间、人物、动作、空间、镜头和声音;失败时只修改根因变量,最多连续返工两轮,之后说明限制或调整方案。
输出合同
按任务需要输出:
- 导演简报:叙事目标、受众、时长、画幅和情绪曲线。
- 能力包络:目标工具支持、未知和必须降级的能力。
- 输入清单:每项输入的职责、优先级和版本。
- 连续性清单:角色、服装、道具、场景、光色和空间方向。
- 时间轴:时间段、剧情节拍、可见动作、镜头、声音和接点。
- 逐段完整 Prompt:可直接复制到目标工具。
- 负向约束与验收清单:只包含与本片高风险漂移相关的内容。
- 执行记录:仅在真实生成时提供已完成、失败和未验证项。
What ships with it
8 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.
- 12d ago First seen · 101 lines · 134 tokens per session scan A be833a120180
narrative-video-director is a skill published in the GitHub repository Onevium/awesome-claude-skills (1 stars, last pushed 15d ago), licensed MIT. It adds 134 tokens to every session and 1,621 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…