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 hirogoing/gradio-mini-agent --skill interactive-story-writergit clone --depth 1 https://github.com/hirogoing/gradio-mini-agentWrote 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/hirogoing/gradio-mini-agent/interactive-story-writer)<a href="https://agentmods.dev/skills/hirogoing/gradio-mini-agent/interactive-story-writer"><img src="https://agentmods.dev/badge/skills/hirogoing/gradio-mini-agent/interactive-story-writer/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/hirogoing/gradio-mini-agent/interactive-story-writer"><img src="https://agentmods.dev/badge/skills/hirogoing/gradio-mini-agent/interactive-story-writer.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 | $0.00083 | $0.01294 |
| Opus 5.5 | $0.00033 | $0.00518 |
| Sonnet 5.5 | $0.00017 | $0.00259 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
interactive-story-writer 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 2mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
互动游戏写作助手
概述
本技能专注于为自媒体创作者提供互动游戏的完整写作解决方案。支持以下类型：
- 文字冒险：多分支剧情，玩家选择决定走向
- 恋爱养成：角色互动+情感选择机制
- 悬疑推理：解谜+选项推进剧情
- 心理测试：选择题形式，结果导向不同解读
- 剧情模拟：情景对话+多结局
工作流程
Step 1: 需求确认
创作前明确以下信息：
| 信息项 | 说明 |
|---|---|
| 游戏类型 | 文字冒险/恋爱/悬疑/心理测试/剧情模拟 |
| 主题/世界观 | 故事背景、年代、风格 |
| 目标受众 | 年龄段、阅读偏好 |
| 篇幅 | 短篇（3-5分支）/中篇（8-12分支）/长篇（15+分支） |
| 平台 | 公众号/知乎/小红书/独立发布 |
| 结局数量 | 单结局/双结局/多结局 |
Step 2: 结构规划
根据游戏类型选择对应模板：
- 线性分支型：适合悬疑、推理、测试类
- 网状分支型：适合恋爱、角色扮演类
- 树状分支型：适合多结局故事
参考 references/game_templates.md 获取详细模板。
Step 3: 内容创作
按照结构化格式输出，确保：
- 每个分支点清晰标记
- 选项具有引导性和区分度
- 伏笔与回收逻辑自洽
- 结局与选择存在合理关联
Step 4: 逻辑校验
创作完成后进行自检：
- 所有分支都有对应的后续剧情
- 选项与结果之间存在逻辑关联
- 关键伏笔在后文有回收
- 多结局的解锁条件明确
输出格式
标准结构化文档
# 互动故事标题
## 世界观/背景
[简短设定说明]
## 角色卡片（可选）
- 角色名：xxx
- 性格：xxx
- 关键特征：xxx
## 剧情分支
### 节点A：「场景/情节标题」
【场景描述】
...
【选项】
A. [选项1描述] → 跳转【节点B】
B. [选项2描述] → 跳转【节点C】
C. [选项3描述] → 跳转【结局X】
### 节点B：「...」
...
### 结局X：「…」
【结局内容】
【结局类型】：XX / BE / NE / HE
各类型输出规范
参考具体模板文件：
| 类型 | 模板文件 |
|---|---|
| 文字冒险 | references/text_adventure.md |
| 恋爱养成 | references/romance_game.md |
| 悬疑推理 | references/mystery_game.md |
| 心理测试 | references/quiz_game.md |
| 剧情模拟 | references/sim_game.md |
分支逻辑指南
常用分支结构
- 二叉分支：每个节点2个选项
- 多选分支：每个节点3-4个选项
- flag触发：累积选择触发隐藏剧情
- 属性系统：选择影响角色属性，属性决定结局
避免死循环
- 每个非结局节点至少有一个选项通往下一节点
- 避免「无路可走」的死胡同（除非设计成BAD ENDING）
伏笔设计技巧
- 在早期节点埋设「钩子」
- 选择时暗示后续影响
- 多结局中让早期选择产生影响
参考资源
references/
game_templates.md- 各类型模板汇总text_adventure.md- 文字冒险模板romance_game.md- 恋爱养成模板mystery_game.md- 悬疑推理模板quiz_game.md- 心理测试模板sim_game.md- 剧情模拟模板
脚本工具（可选）
scripts/validate_branches.py- 分支逻辑校验脚本
注意事项
- 字数控制：每节点控制在100-300字，保持阅读节奏
- 选项质量：选项要有区分度，避免「都一样」的感觉
- 情感节奏：张弛结合，避免连续高能或平淡
- 平台适配：根据平台特性调整输出格式
What ships with it
7 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.
- 2mo ago First seen · 148 lines · 83 tokens per session scan A f87ca68d7683
interactive-story-writer is a skill published in the GitHub repository hirogoing/gradio-mini-agent (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,294 once invoked, about $0.0003 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 2026-08-31.
interactive-story-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| interactive-story-writerhirogoing/gradio-mini-agent | Skill | 2 | 7mo ago | Apache-2.0 | A | 83 | Claude Code, Codex |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 7.4k | 10d ago | Apache-2.0 | A | 95 | Claude Code |
| texture-workflowarjun988/blender-skills | Skill | 2.0k | yesterday | MIT | A | 41 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.5k | today | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 9d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | today | MIT | A | 25 | Claude Code, Codex |