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 e06084/claude-screenwriting --skill screenwriting-reimaginegit clone --depth 1 https://github.com/e06084/claude-screenwritingWrote 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/e06084/claude-screenwriting/screenwriting-reimagine)<a href="https://agentmods.dev/skills/e06084/claude-screenwriting/screenwriting-reimagine"><img src="https://agentmods.dev/badge/skills/e06084/claude-screenwriting/screenwriting-reimagine/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/e06084/claude-screenwriting/screenwriting-reimagine"><img src="https://agentmods.dev/badge/skills/e06084/claude-screenwriting/screenwriting-reimagine.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 | $0.00109 | $0.02883 |
| Opus 5 | $0.00055 | $0.01442 |
| Sonnet 5 | $0.00022 | $0.00577 |
| Haiku 4.5 | $0.00011 | $0.00288 |
Grade A, and why
screenwriting-reimagine 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 11d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenwriting Reimagine
基于已有故事素材,按 3 阶段流水线 创造性地重新构想故事核心。每阶段的输出是下一阶段的输入约束,确保结构一致性。
与其他 Skill 的区别
| Skill | 功能 | 模式 |
|---|---|---|
/screenwriting-ingest |
从素材中提取 | 3 阶段提取(confidence 标注) |
/screenwriting-refactor |
在约束下微调 | Diff 修改(Hard Rules 严格约束) |
/screenwriting-reimagine |
创造性重构 | 3 阶段生成(理论约束 + 创作自由) |
3 阶段流水线
Stage 1: Meta 定位 (genre + logline + theme)
↓ 用户确认
Stage 2: 人物设计 (角色卡 + 人物关系 canvas)
↓ 用户确认(支持增删改循环)
Stage 3: 故事线节拍表 (15 beats + 故事线 canvas)
↓ 用户确认
写入版本目录
可加 --full 参数跳过中间确认,一次性全生成。
Step 0: 读取现有版本
- 读取
wiki/meta/logline.md+wiki/meta/genre.md+wiki/meta/theme.md - 读取
wiki/characters/— 获取所有角色设定 - 读取
wiki/beats/— 获取当前 15-beat 结构 - 读取
wiki/故事线.canvas+wiki/人物关系.canvas
汇总为"原版概要",向用户展示后接收创作方向。
Stage 1: Meta 定位
输入: 原版概要 + 用户创作方向 输出: genre + logline + theme + tone + comparable_works
流程
-
确定 genre(Save the Cat 10 大类型,必选其一)
- 屋里有怪物 / 金羊毛 / 如愿以偿 / 麻烦家伙 / 成长仪式
- 伙伴情 / 推理侦探 / 傻瓜成功 / 被制度化 / 超级英雄
- 这决定了整个故事的"引擎",后续角色和 beats 必须兑现类型承诺
-
撰写 logline(一句话,最多 50 字)
- 公式: 一个[有缺陷的主角],在[催化事件]后,必须[行动目标],否则[赌注]
- 必须包含讽刺性(irony)
-
确定 theme(题材类型标签,1-3 个)
- 从标准标签中选: 剧情/喜剧/动作/爱情/惊悚/犯罪/悬疑/科幻 等
- 第一个为主标签,用于视频平台归类
-
补充: tone(基调)、comparable_works(2-3 部对标作品)
展示与确认
Stage 1 完成 — Meta 定位:
Genre: {STC 10选1}
Logline: {一句话故事}
Theme: {题材标签 1-3个}
基调: {tone}
对标: {作品名}
确认?(y/进入 Stage 2 | r/调整 | n/取消)
理论约束
- genre 必须从 Save the Cat 10 种中选 1(见
references/genre-constraints.md) - logline 必须体现 irony,一句话最多 50 字
- theme 从标准题材标签中选 1-3 个
- genre(结构引擎)和 theme(题材标签)应匹配(如"推理侦探"对应"悬疑/犯罪")
Stage 2: 人物设计
输入: Stage 1 的 meta 定位 + 用户方向 输出: N 个角色卡 + 人物关系.canvas
流程
- 查询类型约束:读取
references/genre-constraints.md中对应 genre 的角色约束 - 设计角色网络:基于类型约束 + 创作方向确定角色列表
- 生成角色卡(每个角色 3 层结构):
- Tab 1 人物塑像: 性别、年龄、外表/行为/社会身份标签
- Tab 2 人物真相: wants、needs、shard_of_glass、contradiction、arc_type
- Tab 3 人物维度: big_five、virtues、six_flaws、backstory、relationships
- 生成人物关系 canvas
- 校验:类型约束的"必须"角色是否都存在?主角 wants ≠ needs?
What ships with it
2 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.
- 11d ago First seen · 291 lines · 109 tokens per session scan A b6e0c6cf4492
screenwriting-reimagine is a skill published in the GitHub repository e06084/claude-screenwriting (7 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 2,883 once invoked, about $0.0005 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
novel-to-screen-adaptation
A process for turning a novel into a screenplay by breaking it down into its main idea, story engine, objects, scenes, episodes, and script in that order. It is an adaptation workflow, not a general script-writing tool.
novel-original-writing
A Chinese-language workflow for turning an original story idea directly into a filmable script, without adapting a novel or other existing source. It develops the idea through seven stages, from concept and world-building to characters, structure, performance, and aftermath.
video-prompt-adapter
A Chinese-language system for creating performance-focused prompts for video generation, combining acting direction, platform details, and production handoffs.
plannotator-visual-explainer
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
short-drama-storyboard
A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.