← 返回 Skills 市场
patches429

Giggle Generation Scripts

作者 Parker · GitHub ↗ · v0.0.10 · MIT-0
cross-platform ✓ 安全检测通过
296
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install giggle-generation-scripts
功能描述
Generates Chinese script content based on narrative pacing and dialogue mechanisms common in Jiang Wen films. Use when the user asks to generate script, writ...
使用说明 (SKILL.md)

简体中文 | English

Giggle Generation Scripts

Organizes text with "high-density conflict + black humor + subtext-heavy dialogue + narrative reversals". Does not copy specific film scenes or lines.

No Retry on Error: If script execution encounters an error, do not retry. Report the error to the user directly and stop.

Input Collection

Prioritize collecting:

  • Genre and era: Republican China, contemporary, near-future, etc.
  • Core conflict: power, money, identity, revenge, misunderstanding
  • Protagonist goal: what they want, what they fear losing
  • Character relations: allies, opponents, double-dealers
  • Target length: short film, single episode, feature

If missing, fill in and state assumptions explicitly.

Input Conflict Handling

Check for conflicting user inputs first. If conflicts exist, handle in this order:

  1. Tone conflicts (e.g. "light comedy" + "extremely dark tragedy")
  2. Character conflicts (e.g. "pure good" + "actively evil protagonist")
  3. Length conflicts (e.g. "5-minute short" + "20 full scenes")

Rules:

  • Prefer the user's latest constraint; if still inconsistent, offer 2 alternative directions, then continue.
  • When info is missing, add at most 3 key assumptions and list them in a "Assumptions" section before the body.
  • Do not treat unconfirmed settings as given facts.

Output Mode Selection

Choose mode by user goal and context length. Default: "standard".

  • Quick: Synopsis + character bios (for direction-setting)
  • Standard: Synopsis + character bios + scene outline + at least 3 full scene scripts
  • Long: Synopsis + character bios + scene outline + 6–10 full scene scripts

Output Order

Output strictly in this order:

  1. Synopsis (300–600 characters)
  2. Character bios (3–8 people; each: surface identity / true motive / relational tension / speech style)
  3. Scene outline (8–20 scenes; each: scene-location-time-conflict core-turning point)
  4. Scene scripts (at least 3 full examples)

Scene Script Serial Output Protocol

When outputting scene scripts, use serial interaction. Do not send all at once:

  1. Always start from scene 1 (S01).
  2. Output only one complete scene at a time (dialogue, action, staging, hook).
  3. At the end of each scene, always ask: "Continue to next scene (S0X)?"
  4. Output the next scene only after explicit user confirmation.
  5. If the user requests "output all at once", switch to batch mode after confirming first.

Scene Script Format

Use a uniform template per scene:

【Scene】S03
【Location/Time】County office courtyard / night
【Characters】Ma Zouri, Huang Silang, Accountant
【Scene goal】Ma Zouri wants to extract where the silver notes went; Huang Silang wants to counter-scheme.
【Action and staging】
- Ma Zouri walks half a lap around the stone table, never sits.
- Huang Silang stands backlit; accountant slightly behind the two.
- Distant firecrackers interrupt when "rules" is mentioned.
【Dialogue】
Ma Zouri: This yard's wind cuts like a knife across the face.
Huang Silang: Wind not sharp, people can't stand.
Accountant: Gentlemen, the tea is getting cold.
Ma Zouri: Tea can warm; ledgers can't—that's when blood flows.
【Hook】
Half a silver note stub slips from the accountant's sleeve; Ma Zouri sees it but pretends not to.

Style Rules

Dialogue Technique (must follow)

  • Characters never answer directly; use反问, analogy, topic shifts
  • Discuss life-and-death matters in everyday tone ("tea's cold" = "you're dead")
  • Each exchange is a power contest: answering = blocking, deflecting = dodging, counter-question = strike
  • In three-person scenes, the third character's lines pace the conflict
  • Forbidden: characters stating emotions directly ("I'm angry", "I'm scared")
  • Forbidden: explanatory dialogue ("You know, back then that thing was...")
  • Forbidden: characters summarizing for the audience ("So you mean...")

Single-Scene Rhythm Formula

Each scene advances in 4 beats:

  1. 【Probe】Both sides feel each other out with idle talk (1–2 rounds)
  2. 【Probe deeper】One side suddenly hits the real topic (1 round)
  3. 【Reversal】The probed side turns it around; power flips (2–3 rounds)
  4. 【Cliffhanger】Third party or accident interrupts; leave a hook

Every scene must have at least one relational shift: probe→threat, ally→suspicion, or power reversal.

Black Humor Technique

  • Core: serious situation + oddly calm/ordinary phrasing
  • Characters worry about trivial things when in grave danger (discussing tea varieties with a knife at the throat)
  • Discuss lives in business tone ("Thirty-six lives, wholesale or retail?")
  • Absurdity comes from logically consistent nonsense—each line alone sounds "reasonable", together it's absurd
  • Forbidden: internet memes, puns, slapstick (not Stephen Chow; Jiang Wen style)

Language Fingerprint Rule

  • Each character's speech pattern must be recognizable in every line
  • Cover character names; the lines alone should identify who speaks
  • After writing: randomly pick 3 lines—can you tell who said them by tone? If not, rewrite.

Interruption Rhythm

  • Dialogue must be "dense"—responses within a breath, like ping-pong
  • Two-person: back-and-forth without pause; three-person: like passing a ball, third can interrupt anytime
  • Allow interruption; mark cut-off lines with "—"
  • At least one interruption per scene (B starts before A finishes)
  • Short lines (5–15 chars) mainly; occasional long line to reset rhythm
  • Forbidden: each person delivers a long monologue in turn (that's speechifying, not dialogue)

Information Density (two layers per scene)

  • Each scene's dialogue carries at least two layers: surface topic + real topic
  • If a scene advances only one thing, density is low—add a second layer
  • Add by: dialogue says A, action/props reveal B; or dialogue literally discusses A while subtext is B
  • Self-check: remove all action cues; can the audience feel "they're not just talking about this" from dialogue alone? If not, rewrite.
  • Reference: 10 lines per scene should advance at least 2 info points + 1 relationship change

Word Precision

  • After each line: can you cut one character? Cut it.
  • Can you replace with a more precise word? "这位大爷" vs "这位爷" are two different people; "走" vs "滚" are two attitudes
  • Lines should "taste" when spoken: use punchy words, avoid formal and cliché phrases
  • Prefer verbs: specific action over abstract description ("He slaps chopsticks on the table" beats "He's angry")
  • Forbidden: literary tone ("岁月如歌"), broadcaster tone ("让我们共同见证"), internet slang ("绝绝子", "yyds")

Other Style Requirements

  • Every 2–3 scenes: one info reversal; prefer action over narration
  • Action and staging serve story: position, gaze, noise, props must drive conflict

Quality Checklist

Before output, verify:

  • All four parts present and in order
  • Character motives interlock, not isolated
  • Each scene has a goal and a change
  • Dialogue is speakable and distinguishes voices
  • No direct copy of existing film scenes or lines
  • Each scene follows 4-beat rhythm (probe→deeper→reversal→hook)
  • Black humor present (everyday tone for dangerous matters)
  • Can you distinguish characters by tone with names hidden?
  • No forbidden items (direct emotion, explanatory dialogue, summarizing for audience)
  • Dialogue dense enough; interruptions present (not turn-taking)
  • Two layers of information per scene (surface + real)
  • Lines trimmed; deleted what can be deleted; words concrete and strong

Revision Loop

When iterating, do at most 2 focused revision rounds; each round only one dimension:

  • Conflict intensity (more restrained / sharper)
  • Dialogue tone (more subtle / more pointed)
  • Staging (more static / more dynamic)

Each round: first output "this round's changes (up to 3)", then the revised excerpts, not a full rewrite.

Example Reference

To adapt quickly, read references/examples.md and replace setting/characters per the user's topic.

安全使用建议
This skill is instruction-only and internally consistent with its stated purpose: it formats and constrains generated Chinese scripts in a specific stylistic manner and does not request credentials or install code. Consider these points before enabling it: (1) content/style: it aims to approximate a living filmmaker's style — while the SKILL.md states it won't copy specific film lines, generated text could still echo the flavor of real works, which may raise copyright or taste concerns depending on your usage; (2) moderation: the style guidelines include dark themes, violence, and black humor — review outputs for content you don't want published; (3) interaction model: scene scripts are intentionally serialized and require explicit user confirmation to continue, which can affect automated workflows (the agent will pause for confirmation per scene); (4) absence of scan findings is expected for an instruction-only skill but not a guarantee of safety — monitor initial outputs and revoke the skill if it behaves unexpectedly.
功能分析
Type: OpenClaw Skill Name: giggle-generation-scripts Version: 0.0.10 The skill bundle is a specialized creative writing tool designed to generate Chinese film scripts in the style of director Jiang Wen. The instructions in SKILL.md and SKILL.zh-CN.md focus entirely on narrative techniques, dialogue subtext, and scene pacing, with no evidence of data exfiltration, malicious execution, or harmful prompt injection. The 'Serial Output Protocol' and 'No Retry on Error' instructions are standard behavioral constraints for managing agent-user interaction during long-form text generation.
能力评估
Purpose & Capability
Name/description (generate Chinese scripts in a Jiang Wen‑like style) match the content of SKILL.md and the included examples. The skill does not request unrelated binaries, credentials, or config paths.
Instruction Scope
SKILL.md contains detailed, narrow instructions for collecting user inputs, formatting outputs, and an interactive serial scene protocol. It does not instruct the agent to read files outside the skill bundle, access environment variables, call external endpoints, or exfiltrate data. The only local file it references (references/examples.md) is provided in the bundle.
Install Mechanism
No install spec and no code files — instruction-only. Nothing will be downloaded or written to disk as part of an install step.
Credentials
No environment variables, credentials, or config paths are required. The scope of requested access is minimal and appropriate for a text-generation formatting skill.
Persistence & Privilege
always is false and model invocation is allowed (the platform default). The skill does not request permanent presence or elevated privileges, nor does it modify other skills or system-wide settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install giggle-generation-scripts
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /giggle-generation-scripts 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.0.10
- Added English-language SKILL.md and corresponding Simplified Chinese SKILL.zh-CN.md for bilingual documentation. - Updated SKILL.md description, instructions, and formatting for improved clarity, English translation, and international access. - Added explicit "No Retry on Error" protocol for script execution failures. - Refined and clarified output sequence, scene formatting, dialogue and stylistic rules. - Ensured direct links between English and Chinese documentation.
v0.0.1
- 首个版本发布,定义“姜文风”剧本生成机制,适配分场梗概、人物、对白全流程。 - 明确知识补全、冲突处理、串行分场输出等详细协议。 - 详列对白、节奏、黑色幽默、语言指纹等风格要求与自检清单。 - 内嵌多层信息密度与抢对白节奏,严禁解释性台词和惯用桥段。 - 支持快速、标准、长篇三种输出模式,并设定迭代改稿流程和示例调用规范。
元数据
Slug giggle-generation-scripts
版本 0.0.10
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Giggle Generation Scripts 是什么?

Generates Chinese script content based on narrative pacing and dialogue mechanisms common in Jiang Wen films. Use when the user asks to generate script, writ... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 296 次。

如何安装 Giggle Generation Scripts?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install giggle-generation-scripts」即可一键安装,无需额外配置。

Giggle Generation Scripts 是免费的吗?

是的,Giggle Generation Scripts 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Giggle Generation Scripts 支持哪些平台?

Giggle Generation Scripts 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Giggle Generation Scripts?

由 Parker(@patches429)开发并维护,当前版本 v0.0.10。

💬 留言讨论