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 sutchan/Agent-Skills-Hub --skill short-drama-writegit clone --depth 1 https://github.com/sutchan/Agent-Skills-HubWrote 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/sutchan/agent-skills-hub/short-drama-write)<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/short-drama-write"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/short-drama-write/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/sutchan/agent-skills-hub/short-drama-write"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/short-drama-write.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 | $0.00108 | $0.02384 |
| Opus 5 | $0.00054 | $0.01192 |
| Sonnet 5 | $0.00022 | $0.00477 |
| Haiku 4.5 | $0.00011 | $0.00238 |
Grade A, and why
short-drama-write 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 2d 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.
This is a copy
95% identical to short-drama-write — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
短剧写作
把单集意图写成可表演、可拍摄、会改变故事状态的 剧集/<EP>/剧本.md。
Quick Start
只维护一份剧本 Markdown,不另建 episode card、beats、block index、录音表、QA 或接受记录。
一级标题使用 # EP001 集名,场景标题使用 ## EP001-SC001 内 · 地点 · 时间/天气。
对白写 角色(可选表演提示):台词;生产标签使用 [VO]、[OS]、[SFX]、[画面文字]、
[连续性]、[转场]。不要把含冒号的动作叙述误写成对白。
入口
- 有分集规划:读取本集进入状态、目标、转折、回报和交接事实。
- 只有想法/大纲:在上下文形成最小单集契约和因果节拍,再直接写剧本。
- 已有剧本:保留作者语言,只做用户点名的定点修订。
- 非规范文本要进入制作:保留原文,只做必要的场景、动作、对白和生产标签规范化。
开发大纲和长篇分析都是可选上游;当前材料足够时直接写。
工作流
- 锁定本集承诺的观看体验、谁现在要什么、阻力、当集兑现和退出状态。
- 只识别本集实际存在的发动机:若主打艰难选择,检查两边价值;若判断转折依赖争议证据,检查证明边界;若前景化精确死线,检查动作容量;若题面限定次数、轮次、呼吸或节拍,检查每个单位是否在边界内完成所需状态。没有时不强行补齐;输入已经以它为主发动机时,要让它真正改变行动、关系或结果,不只在台词中点名。
- 在上下文排“因为—行动—结果—下一股压力”,不落盘节拍表;让物件、对白、沉默、空间或声音按本集题材承担必要工作,不预设某一种载体。
- 逐场确定不可替代的功能、可见变化与场尾状态;由争取或冲突组织的场景再明确焦点议程与阻力。承担主要戏剧功能的配角要有自己的策略,事务性或环境性角色保持简洁即可。
- 把动作、对白、画外音、声音事实和画面文字写入同一份剧本。
- 用户要求整集就写完整集,场景批次自动续跑。
- 交稿前静默反查:只看剧本能否接收到本集承诺、人物行动是否有因果、题材语气是否一致;再对本集确实使用的选择、证据、有限单位或精确死线做专项检查。若自检让剧本长出输入没有要求的机关,撤掉机关而不是替它找理由。
- 局部修订保留无关段落;明确问题直接修正,只把真实剧情分叉交给用户。
写作要求
- 先服从输入已经给出的事实、
必须/禁止、题材观看契约和退出状态;本技能的审查项与手艺默认只帮助实现这些要求,不能反过来补造题面没有的精确数字、记录、资源、程序、关系或机关。 - 每场改变信息、权力、关系、情绪、物理状态或风险;无变化的场删掉或合并。核心阻力的转向要有可追溯的事实、筹码、权限、代价或人物行动,不能只靠对手停止反应。
- 对白必须在争取、回避、试探、逼迫或重新定义关系;用可见、可听、可触的行为表现状态,不用解释替代行动,也不把已经演清的机制再说一遍。
- 观众理解当前行动所必需的赌注要进入剧本,但载体服从题材;选择、证据、有限单位、精确死线等专项规则只在输入真正以它为发动机时启用,并按需读取剧作手艺,普通决定、普通物件和模糊时间压力不升级成同一套机关。
- 压缩过程时只保留会改变策略、关系、风险或结果的节点。资源与外部反应必须来自输入或前文建立,且不能替人物完成最难的戏剧行动。
- 承担主要冲突的角色要保持相称的目标、判断或策略;事务性、环境性角色保持简洁,不为检查表硬加秘密、反转或人物弧。
- 已建立的代价、不可逆后果、关键持物、空间和知识状态要进入可追溯的退出状态;结尾可推进、留白、反讽、安静收束或形成余韵,不强制追加外部事件。
[连续性]只交接由前文动作已经建立、又容易在下游丢失的状态;不能用作者标签证明镜头外从未发生某事,也不复述正文已清楚呈现的结果。- 交稿前静默做一次经济性检查:是否增加了输入没有要求的精确数字或记录链;是否用标签/对白重复动作;是否在回报后堆了多个同方向后果。没有新作用的内容删掉,knowhow 本身不删。
- 输入给出目标时长时按真实表演、动作和停顿通读压稿,先删重复验证、解释和同义收尾;不用统一字数、镜头数或节拍数填模板。
- 用户原文优先;“去 AI 味”是定点修订,不抹平作者个性。
按需知识
默认只读本 SKILL 和直接输入。出现下列明确信号时,在写正文前读取对应知识;同一输入有多个不同问题 可以分别读取,但不遍历无关引用:
What ships with it
18 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 270 B
- assets/beats.jsonl 1.4 KB
- assets/episode-card-standalone.json 3.2 KB
- assets/episode-card.json 1.3 KB
- assets/screenplay.md 1.6 KB
- assets/voice-record-sheet.jsonl.md 5.4 KB
- references/dialogue-craft.md 21 KB
- references/production-format-dialect.md 18 KB
- references/scene-handoff-capsule.md 1.5 KB
- references/scene-sound-dramaturgy.md 2.4 KB
- references/screenplay-format.md 9.7 KB
- references/script-craft.md 43 KB
- references/stage-contract.md 6.6 KB
- references/substitutable-realization.md 6.1 KB
- scripts/duration_estimate.py 12 KB runs code
- scripts/screenplay_index.py 43 KB runs code
- scripts/selftest.py 8.7 KB runs code
- scripts/voice_sheet_check.py 15 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.
- 2d ago Changed · -2 lines 859d01337ed3
- 8d ago First seen · 93 lines · 108 tokens per session scan A cf217a77bd3d
short-drama-write is a skill published in the GitHub repository sutchan/Agent-Skills-Hub (2 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 2,384 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to short-drama-write, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
skill-creator
Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.
iflytek-hyper-tts
A text-to-speech tool that turns written text into an MP3 recording. It can use an authorized voice and adjust speaking speed, volume, and pitch.