← 返回 Skills 市场
patches429

Giggle Generation Drama

作者 Parker · GitHub ↗ · v0.0.10 · MIT-0
cross-platform ✓ 安全检测通过
260
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install giggle-generation-drama
功能描述
Use when the user wants to generate video, shoot short films, or view available video styles. Triggers: short film, make video, shoot short, AI video, genera...
使用说明 (SKILL.md)

简体中文 | English

⚠️ Review Before Installing

Please review before installing. This skill will:

  1. Network – Calls Giggle.pro API for video generation

Requirements: python3, GIGGLE_API_KEY (system environment variable), pip packages: requests

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


Required Setup Before First Use

Before performing any operation, confirm the user has configured the API Key to avoid workflow failure due to auth errors.

  • API Key: Log in to Giggle.pro and obtain the API Key from account settings.
  • Configuration: Set system environment variable GIGGLE_API_KEY
    • export GIGGLE_API_KEY=your_api_key

Verification steps:

  1. Confirm the user has configured GIGGLE_API_KEY in system environment.
  2. If not configured, guide the user:

    Hello! Before using the video generation feature, you need to configure the API Key. Please go to Giggle.pro to get your API Key, then run export GIGGLE_API_KEY=your_api_key in the terminal.

  3. Wait for the user to configure before continuing the workflow.

Generation Modes

Supports three modes. Ask the user to select a mode before starting the workflow. If not specified, default to Episodes mode (director).

Mode project_type Description
Episodes director AI-directed short drama with storyboards and shot language
Narration narration Narration-focused video
Short Film short-film Story and visuals balanced; cinematic short film

Main Workflow: execute_workflow

Use execute_workflow to run the full workflow: submit + poll + auto-pay (if needed) + wait for completion. Call once and wait for return.

  1. Submit task
  2. Poll progress every 3 seconds
  3. Detect pending payment and auto-pay (if needed)
  4. Wait for completion (max 1 hour)
  5. Return video download link or error

Function Signature

execute_workflow(
    diy_story: str,                           # Story/script content (required)
    aspect: str,                              # Aspect ratio: 16:9 or 9:16 (required)
    project_name: str,                        # Project name (required)
    video_duration: str = "auto",             # Duration, default "auto" (optional)
    style_id: Optional[int] = None,          # Style ID (optional)
    project_type: str = "director",           # Mode, default "director" (optional)
    character_info: Optional[List[Dict]] = None  # Character images (optional)
)

Parameter Description

Parameter Required Description
diy_story yes Story or script content
aspect yes Aspect ratio: 16:9 or 9:16
project_name yes Project name
video_duration no auto, 30, 60, 120, 180, 240, 300; default "auto"
style_id no Style ID; omit if not specified
project_type no director / narration / short-film; default "director"
character_info no Character image list: [{"name": "Character name", "url": "Image URL"}, ...]

Usage Flow

  1. Introduce and select generation mode (required): Before generating, must introduce the three modes and let the user choose. Display:

    We support three video generation modes. Please choose:

    Episodes (director): AI director handles storyboards and shot language. Good for short drama with dialogue and plot.

    Narration (narration): Narration-focused with visuals. Good for knowledge sharing, news commentary, product introductions.

    Short Film (short-film): Story and visuals balanced; cinematic shots and pacing. Good for emotional shorts, creative stories, artistic expression.

    Wait for explicit user choice before continuing. If not specified, default to Episodes.

  2. If the user wants to pick a style: Call get_styles() for the style list; show ID, name, category, description; wait for choice before continuing.

  3. If the user provides character image URLs: Build character_info array with name and url per character.

  4. Run workflow:

    • Call execute_workflow() with story, aspect ratio, project name.
    • Set project_type per chosen mode; pass video_duration if specified (else "auto"); pass style_id if chosen; pass character_info if provided.
    • Call once and wait — the function handles create, submit, poll, pay, and completion; returns download link or error.

Examples

View style list:

api = TrusteeModeAPI()
styles_result = api.get_styles()
# Display style list to user

Basic workflow (no duration, no style):

api = TrusteeModeAPI()
result = api.execute_workflow(
    diy_story="An adventure story...",
    aspect="16:9",
    project_name="My Video Project"
)
# result contains download URL or error

Specify duration, no style:

result = api.execute_workflow(
    diy_story="An adventure story...",
    aspect="16:9",
    project_name="My Video Project",
    video_duration="60"
)

Specify duration and style:

result = api.execute_workflow(
    diy_story="An adventure story...",
    aspect="16:9",
    project_name="My Video Project",
    video_duration="60",
    style_id=142
)

Narration mode:

result = api.execute_workflow(
    diy_story="Today we'll talk about AI development...",
    aspect="16:9",
    project_name="Narration Video",
    project_type="narration"
)

Short film mode:

result = api.execute_workflow(
    diy_story="Sunset. An old fisherman rows home alone. The sea glows red...",
    aspect="16:9",
    project_name="Short Film",
    project_type="short-film"
)

With character images (when user provides character image URLs):

result = api.execute_workflow(
    diy_story="Xiao Ming and Xiao Hong meet in the park, they smile at each other...",
    aspect="16:9",
    project_name="Custom Character Video",
    character_info=[
        {"name": "Xiao Ming", "url": "https://xxx/xiaoming.jpg"},
        {"name": "Xiao Hong", "url": "https://xxx/xiaohong.jpg"}
    ]
)

Return Value

The function blocks until the task completes (success or failure) or times out (1 hour). Wait for it to return.

Success (includes download link):

{
    "code": 200,
    "msg": "success",
    "uuid": "...",
    "data": {
        "project_id": "...",
        "video_asset": {...},
        "status": "completed"
    }
}

Return the full signed URL to the user (data.video_asset.download_url), e.g.:

https://assets.giggle.pro/private/ai_director/348e4956c7bd4f763b/qzjc7gwkpf.mp4?Policy=...&Key-Pair-Id=...&Signature=...&response-content-disposition=attachment

Do not return unsigned URLs without query params, e.g.:

https://assets.giggle.pro/private/ai_director/348e4956c7bd4f763b/qzjc7gwkpf.mp4

Failure:

{
    "code": -1,
    "msg": "Error message",
    "data": null
}
安全使用建议
This skill appears to be a legitimate client for Giggle.pro, but before installing: 1) Ensure you trust Giggle.pro and understand your API key's permissions (billing) because the workflow can auto-pay on your account. 2) Be aware that any story text and character image URLs you provide will be sent to the remote service (privacy/PII risk). 3) If you want to be cautious, create a limited/billing-controlled API key or test with a throwaway account and small jobs first. 4) Review the included scripts/trustee_api.py (readable) if you want to confirm there are no extra endpoints or unexpected behavior. 5) Confirm you are comfortable with the agent waiting up to 1 hour for job completion and that you want automatic payment behavior.
功能分析
Type: OpenClaw Skill Name: giggle-generation-drama Version: 0.0.10 The skill is a legitimate integration for the Giggle.pro video generation service. The core logic in `scripts/trustee_api.py` uses a user-provided API key to interact with the service's REST API for creating projects and generating videos. While the script includes an 'auto-pay' feature that spends service credits, this behavior is clearly documented in `SKILL.md` as part of the 'Trustee Mode' workflow and is accompanied by safety instructions for the AI agent to stop execution and avoid retries upon encountering errors, preventing accidental overspending.
能力评估
Purpose & Capability
The name/description (video/short-film generation) matches the code and runtime requirements: python3, requests, and a GIGGLE_API_KEY. The API endpoints are all under giggle.pro and the primary credential is GIGGLE_API_KEY — this is proportionate to the stated purpose.
Instruction Scope
SKILL.md instructs the agent to create/submit projects, poll progress, and perform auto-pay if needed; it requires the agent to wait up to 1 hour for completion. The only environment access the instructions require is GIGGLE_API_KEY (declared). Note: the workflow will send user-provided story text and any character image URLs to the remote Giggle API and may trigger on-account payments automatically.
Install Mechanism
No install spec is provided (instruction-only plus a small Python script). This is low risk: nothing is downloaded from arbitrary URLs and the only pip dependency is requests (declared in requirements.txt).
Credentials
Only GIGGLE_API_KEY is required and is the primary credential; that matches the service. There are no unrelated secrets or config paths requested. However, the API key likely carries billing privileges, so it can be used to incur charges via the provider's API (the skill's workflow includes auto-pay).
Persistence & Privilege
The skill is not force-included (always:false) and does not request system-wide persistence. It can be invoked autonomously (platform default) — combined with auto-pay behavior this is something to be aware of, but autonomy alone is expected.
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-drama
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /giggle-generation-drama 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
**0.0.10 Summary: Adds English docs, pip dependencies, and updated setup instructions.** - Added English documentation (`SKILL.md`) with complete usage instructions alongside the new Chinese doc (`SKILL.zh-CN.md`). - Explicitly documents required Python `requests` package and pip dependency in metadata. - Updated setup guide to use environment variables instead of `.env` file. - Clarifies networking/API requirements and error handling (do not retry on error). - Refines usage flow and parameter descriptions for better clarity in English.
v0.0.1
Initial release of giggle-generation-drama. - Supports one-stop AI video generation based on user story/script, with three modes: director, narration, and short-film. - Provides clear setup instructions for configuring the required GIGGLE_API_KEY. - Guides users to select video mode and style, with examples and parameter explanations. - Supports optional character images, customizable video duration, and style choice. - Returns downloadable signed video link upon completion or provides error details if failed.
元数据
Slug giggle-generation-drama
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 Drama 是什么?

Use when the user wants to generate video, shoot short films, or view available video styles. Triggers: short film, make video, shoot short, AI video, genera... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 260 次。

如何安装 Giggle Generation Drama?

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

Giggle Generation Drama 是免费的吗?

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

Giggle Generation Drama 支持哪些平台?

Giggle Generation Drama 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 Drama?

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

💬 留言讨论