Agent skill

Short Drama Knowhow

by zenstory-ai in zenstory-ai/drama-skills

维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链,并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用;不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。

MITAuto-check passedEducation

Install Short Drama Knowhow

skills CLI
$ npx skills add zenstory-ai/drama-skills --skill short-drama-knowhow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zenstory-ai/drama-skills short-drama-knowhow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zenstory-ai/drama-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/maintainers/skills/short-drama-knowhow .claude/skills/short-drama-knowhow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
short-drama-knowhow
GitHub stars
2.7k
Token cost
~914 tokens
SKILL.md length
173 words
Files
7 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链,并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用;不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。

  • Works in 11 steps: 确立只读授权与隔离工作区 → 以覆盖缺口选样 → 定性通读完整项目链 → …
  • Tasks that involve Quizzes and assessments
  • SKILL.md covers 开始前锁定边界, 核心原则, 工作流 and 按需读取
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Short Drama Knowhow is an agent skill from zenstory-ai/drama-skills. 维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链,并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用;不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。

Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `agents/openai.yaml`, `references/blind-forward-eval.md` and `references/cards-and-coverage.md`).

It sits in Education, covering Quizzes and assessments. The repository describes itself as: 开源 AI 短剧/漫剧创作 skill 合集:剧本、角色资产、分镜 storyboard、图片/视频提示词、审查,适配 Claude Code 与 Codex | Open-source AI short drama / micro-drama skills for Claude Code & Codex: script, assets… The licence is MIT.

When your agent uses it

  • Tasks that involve Quizzes and assessments

Example prompts

  • “/short-drama-knowhow”

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. 确立只读授权与隔离工作区
  2. 以覆盖缺口选样
  3. 定性通读完整项目链
  4. 写私有 observation / decision cards
  5. 构建题材 × 机制 coverage matrix
  6. 用反例、冲突与适用边界压缩结论
  7. 去标识与 de-copy
  8. 形成公共 reference / rubric / synthetic fixture proposal
  9. 做 fresh-agent blind forward eval
  10. 交给 independent reviewer
  11. promotion / retire

What it can do on your machine

Read from SKILL.md and the folder at commit c2426e0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Short Drama Knowhow loads about 914 tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 173 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~914
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zenstory-ai/drama-skills at commit c2426e0, republished under its MIT licence (© zenstory-ai). 173 words, ~914 tokens.

Download SKILL.mdSave it as .claude/skills/short-drama-knowhow/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
short-drama-knowhow
description
维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链,并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用;不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。
license
MIT

短剧 Know-how 学习

把学习过程当作编剧、漫剧工作室与编导共同参与的定性研究,而不是词频挖掘。 先理解完整项目如何把戏剧意图传递到可执行的文本制作规格,再决定哪些知识可迁移。

开始前锁定边界

只在维护者主动调用本 skill,且当前会话已经提供授权的只读访问时读取非公开来源。 把连接细节、凭据、源名称和私有卡片留在维护者指定的隔离工作区;不得写入本 skill、 公开技能树、公共候选或评测夹具。没有授权或无法确认只读时停止来源读取,只能用合成材料演练流程。

本流程只研究文本及其版本关系。可读创意简报、故事结构、剧本、资产/连续性台账、图片提示词、 分镜/关键帧文字、视频提示词、审查与修订记录;不生成、渲染、下载或检查图像、音频或视频。 公开运行时永不连接非公开来源,也不承担任何媒体生成。

核心原则

  • 让 agent 判断题材语境、人物欲望、因果、信息差、情绪推进、表演动作、镜头意图与制作取舍。
  • 只把校验格式、比较文件、查重与隐私扫描等确定性步骤交给现有工具;不要为创作语义写规则匹配脚本。
  • 统计只用于描绘可选样本、发现覆盖缺口、寻找异常与安排下一次阅读;不得从频次、排名或相关性直接推出创作规则。
  • 一条候选知识必须同时携带证据、反例或失败情形、冲突解释、适用边界和置信度;“常见”不等于“有效”。
  • 每次只提出可审查的最小公共改动;未经盲测与独立审查不得直接进入公共 skill。

工作流

1. 确立只读授权与隔离工作区

记录本轮目的、允许读取的文本范围、禁止读取的内容、输出位置和销毁要求。测试一次只读行为, 但不回显连接信息。建立私有研究目录与单独的去标识候选目录;公共目录起初保持不变。

2. 以覆盖缺口选样

先查看维护者允许的最小索引或目录信息。按题材、受众承诺、核心机制、篇幅阶段、制作形态、 视觉语言、场景功能、提示词职责、完成度与修订状态寻找缺口、对照组和反常样本。统计只能帮助 “下一部读什么”,不能回答“应该怎么写”。 优先形成有差异的目的性样本,而不是只读最热门、最多见或最方便查询的项目。

3. 定性通读完整项目链

逐个项目从上游意图读到下游文本交付:创意/改编约束 → 故事引擎与分集设计 → 单集剧本 → 角色、场景、道具与连续性 → 图片提示词 → 分镜与关键帧文字 → 视频提示词 → 审查、修订和交付说明。 若某层不存在,明确记为缺失,不用别的项目或常识补齐。

沿同一承诺追踪:怎样建立期待、怎样制造阻碍和信息差、人物用什么可表演行动推进、转折怎样被铺垫, 以及镜头/提示词怎样保留而不是改写剧作意图。完整阅读后才写卡,不用批量关键词命中代替阅读。 卡片字段与合成例子见 cards-and-coverage.md。

4. 写私有 observation / decision cards

先写 observation card,严格区分直接观察、agent 解释与未知;再写 decision card,记录是否形成候选、 为什么缩小适用范围、有哪些替代解释。每张卡用不泄漏内容的稳定内部引用绑定同一项目链, 但私有卡片永不进入公共技能包。

5. 构建题材 × 机制 coverage matrix

用“题材/受众承诺”作为一轴,用“期待建立、冲突升级、信息释放、关系转向、反转兑现、集尾牵引、 表演动作、镜头承接、连续性”等机制作为另一轴;提示词研究再叠加制作形态/视觉语言、场景功能、 提示词职责与版本角色。每格记录支持卡、反例卡、边界、缺口和下一样本, 不填出现次数或成功率。矩阵格式见 cards-and-coverage.md。

6. 用反例、冲突与适用边界压缩结论

主动寻找同机制失败、同题材例外、同结果的替代解释,以及上游有效但下游不可制作的情形。 冲突未解释时保持候选,不做多数表决。把“总是如此”改写成“在这些观众承诺、人物状态和制作约束下, 这项机制可能解决这个问题;出现这些信号时应换法或不用”。详细判别见 synthesis-and-promotion.md。

7. 去标识与 de-copy

删除或抽象源名称、人物名、专有设定、原句、罕见组合、精确数值、路径、地址、标识符和连接信息。 把表层桥段拆成“观众状态 → 戏剧问题 → 可选机制 → 可观察效果 → 失败边界”,再用全新的题材、人物关系、 场景和措辞重建例子。若只有复述原内容才能表达,就不进入公共候选。

8. 形成公共 reference / rubric / synthetic fixture proposal

每个候选包同时提出:简洁 reference 改动、能定位证据与失败模式的 rubric、完全合成且与任何来源不近似的 fixture,以及预期受益任务和潜在副作用。proposal 先留在维护者 staging 区,不直接改 public suite。 公共候选不得要求运行时访问非公开来源,不得声称文本能证明真实媒体效果。

9. 做 fresh-agent blind forward eval

让没有读取私有卡片、原始项目和预期答案的 fresh agent,仅用公共基线或匿名候选之一完成同一组合成任务。 盲评其剧作判断、题材适配、制作可执行性、变体能力和是否机械套模板。执行 blind-forward-eval.md;不要把候选作者的结论泄漏进 prompt。

10. 交给 independent reviewer

由未参与本轮摘取、合成或候选写作的 reviewer 复查证据充分性、反例、适用边界、去标识、de-copy、 盲测设计与公共运行边界。候选作者不得自审放行;有未解决的泄漏、近似复刻、机械化或证据断层即退回。

11. promotion / retire

只有候选通过 fresh-agent blind forward eval 和 independent reviewer,且 reference、rubric、synthetic fixture 彼此一致,才能由维护者把最小改动 promotion 到公共资料。保留不含私密内容的决策记录与回滚说明。 后续反例证明候选过宽、盲测无增益或诱发模板化时,缩窄、替换或 retire;不要靠沉默删除掩盖知识变化。

按需读取

  • 写私有卡、合成例子或 coverage matrix 时读 cards-and-coverage.md。
  • 判断能否去标识、如何处理冲突或准备 promotion / retire 时读 synthesis-and-promotion.md。
  • 设计 fresh-agent blind forward eval、盲评和 reviewer handoff 时读 blind-forward-eval.md。
  • 准备 promotion / hold / retire,或需要让公共规则的评测与回滚证据可重放时读 promotion-ledger.md。
  • 学习不同题材、画风、场景与图片/视频提示词机制,或区分修订请求、输入参考观察和生成结果观察时读 prompt-production-learning.md。

不要预加载所有 reference;只读当前阶段需要的一份。

© zenstory-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in maintainers/skills/short-drama-knowhow of zenstory-ai/drama-skills.

  • SKILL.md
  • agents/openai.yaml
  • references/blind-forward-eval.md
  • references/cards-and-coverage.md
  • references/promotion-ledger.md
  • references/prompt-production-learning.md
  • references/synthesis-and-promotion.md

Open the folder on GitHubat commit c2426e0

Compare with similar skills

Short Drama Knowhow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Short Drama Knowhow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Short Drama Knowhow this skillzenstory-ai/drama-skills2.7k—~914Automated safety check: PassMIT
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch67k—~2kAutomated safety check: PassMIT
Codebase to Coursezarazhangrui/codebase-to-course5.7k—~4.4kAutomated safety check: PassNone
AI Engineering Phase Quizrohitg00/ai-engineering-from-scratch67k—~2.1kAutomated safety check: PassMIT
Scholar EvaluationK-Dense-AI/claude-scientific-writer2.4k2 repos~2.9kAutomated safety check: NotesMIT

Similar skills

  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated 3 days ago
    EducationAuto-check passed
  • AI Engineering Placement Quiz

    rohitg00/ai-engineering-from-scratch

    Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.

    67k GitHub stars~2k tokensUpdated today
    EducationAuto-check passed
  • Codebase to Course

    zarazhangrui/codebase-to-course

    Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.

    5.7k GitHub stars~4.4k tokensUpdated 6 mo ago
    EducationAuto-check passed
  • AI Engineering Phase Quiz

    rohitg00/ai-engineering-from-scratch

    Quizzes you on a completed phase of the AI Engineering from Scratch course, taking a phase number or name and mapping it to that phase's directory.

    67k GitHub stars~2.1k tokensUpdated today
    EducationAuto-check passed
  • Scholar Evaluation

    K-Dense-AI/claude-scientific-writer

    Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls.

    2.4k GitHub starsUsed in 2 repos~2.9k tokens
    EducationAuto-check: notes
  • Evaluation

    guanyang/open-agent-hub

    This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and…

    977 GitHub starsUsed in 2 repos~4.2k tokens
    EducationAuto-check passed

More from zenstory-ai/drama-skills

All 12 skills in this repo
  • Short Drama

    zenstory-ai/drama-skills

    基于文件系统初始化和继续短剧或漫剧项目,提供 creator-first 五文档路由、本地 Dashboard、制作形态与 Look Development 决策。用户提出“创建/继续短剧项目”“看进度/下一步”“做 Look Development”“打开 dashboard/短剧创作台”“导出制作资料”,或任务跨多个创作阶段时使用;明确的写作、资产、提示词、分镜、剪辑或审查请求由对应子…

    2.7k GitHub stars~1.6k tokensUpdated 8 days ago
    Auto-check passed
  • Short Drama Assets

    zenstory-ai/drama-skills

    从短剧剧本拆出人物/造型、地点/视图、道具/状态和跨场连续性,写成创作者可读的视觉设定。用户说“拆角色/场景/道具”“做资产设定”“判断复用还是新变体”“更新造型/道具状态”,或拿现成剧本直接做视觉资产准备时使用;不写图片提示词,不生成媒体。

    2.7k GitHub stars~592 tokensUpdated 8 days ago
    Auto-check passed
  • Short Drama Develop

    zenstory-ai/drama-skills

    将中文小说、短剧或漫剧想法、梗概、改编材料、已有系列笔记或多集完整剧本发展成可追溯的改编方案、戏剧方向、创作简报、导演阐述、故事引擎与分集地图,并按题材与制作形态(画风)选择写法。用户提出“导入小说做短剧”“从多集整稿生成/补分集地图”“开发短剧/漫剧”“做故事设定/系列大纲/分集规划”“写导演阐述”“这个题材怎么写”“定画风/制作形态”“把这个点子变成短剧”或需要梳理人物冲突与集间交接时使用;…

    2.7k GitHub stars~1.3k tokensUpdated 8 days ago
    Auto-check passed
  • Short Drama Edit

    zenstory-ai/drama-skills

    将已生成的短剧镜头剪成成片,记录入出点、镜序、声音、字幕与交付规格。用于套剪、加字幕、统一响度、调整节奏或导出精修素材;需要补素材或修改故事时转回对应创作阶段。

    2.7k GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed
  • Short Drama Image Prompts

    zenstory-ai/drama-skills

    为短剧人物、造型、地点、道具和状态编写或修改可直接复制的图片提示词 Markdown。用户提到角色设定图、三视图、参考图、场景板、道具图、风格帧、Look Development、状态变体或局部编辑提示词时使用;不生成图片,也不调用供应商。

    2.7k GitHub stars~535 tokensUpdated 8 days ago
    Auto-check passed
  • Short Drama Novel Analyze

    zenstory-ai/drama-skills

    把长篇小说、连载网文或多集散稿拆成可追溯的原著分析:章节索引、改编价值快评、逐章功能提取、剧情单元与节奏聚合、人物与设定归并,最后给出改编价值判定与分集候选,交给 $short-drama-develop 立契约。用户说“导入这本小说”“拆这本书”“分析原著”“这本书能不能改短剧”“先看看值不值得拆”“把长篇拆成分集候选”,或直接给出小说文件路径时使用。只做只读的结构化分析,不写剧本、不建资产、…

    2.7k GitHub stars~1.9k tokensUpdated 8 days ago
    Auto-check passed

Categories

Questions about Short Drama Knowhow

What does Short Drama Knowhow do?

维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链,并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用;不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。. Short Drama Knowhow is an agent skill from zenstory-ai/drama-skills.

When should I use Short Drama Knowhow?

Short Drama Knowhow fits situations like: tasks that involve Quizzes and assessments.

How do I install Short Drama Knowhow in Claude Code?

Run `npx skills add zenstory-ai/drama-skills --skill short-drama-knowhow -a claude-code`. Or copy the skill folder (maintainers/skills/short-drama-knowhow in zenstory-ai/drama-skills) into .claude/skills/short-drama-knowhow in your project. Claude Code loads it when a task matches its description.

How do I install Short Drama Knowhow in Codex?

Run `npx skills add zenstory-ai/drama-skills --skill short-drama-knowhow -a codex`. Or copy the skill folder (maintainers/skills/short-drama-knowhow in zenstory-ai/drama-skills) into .agents/skills/short-drama-knowhow in your project. Codex loads it when a task matches its description.

Can I use Short Drama Knowhow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zenstory-ai/drama-skills --skill short-drama-knowhow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/short-drama-knowhow, .gemini/skills/short-drama-knowhow, .github/skills/short-drama-knowhow and .opencode/skills/short-drama-knowhow in your project.

What does Short Drama Knowhow need to run?

SKILL.md names no scripts, command-line tools or credentials: Short Drama Knowhow is instructions for the agent only.

Does Short Drama Knowhow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Short Drama Knowhow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Short Drama Knowhow use?

Short Drama Knowhow is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Short Drama Knowhow use?

About 914 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.2k tokens, read only when the agent opens those files.

What are the alternatives to Short Drama Knowhow?

Skills that share tags, products or a category with Short Drama Knowhow: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 67k stars), Codebase to Course (zarazhangrui/codebase-to-course, 5.7k stars) and AI Engineering Phase Quiz (rohitg00/ai-engineering-from-scratch, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Short Drama Knowhow?

zenstory-ai (a GitHub organization) maintains it in zenstory-ai/drama-skills, which has 2,683 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 3, 2026.

Source: zenstory-ai/drama-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.