← Back to Skills Marketplace
coolhackboy

Kling 3.0 video generation

by coolhackboy · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
468
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install kling-3
Description
Kling 3.0 video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `kling-3.0/standard`, `kling-3.0/pro`, single-shot, multi...
README (SKILL.md)

PoYo Kling 3.0 Multi-Shot Video Generation

Use this skill for Kling 3.0 jobs on PoYo. It covers single-shot and multi-shot video generation, element-referenced prompting, and sound-enabled output.

Use When

  • The user explicitly asks for Kling 3.0, kling-3.0/standard, or kling-3.0/pro.
  • The task needs multi-shot storytelling or structured multi-prompt input.
  • The workflow depends on kling_elements, reference frames, or sound control.

Model Selection

  • kling-3.0/standard: standard-quality entry point.
  • kling-3.0/pro: higher-quality variant for users who explicitly want pro output.

Key Inputs

  • sound, multi_shots, and duration drive the main workflow.
  • prompt is for single-shot; multi_prompt is for multi-shot.
  • image_urls is for start/end frames and is also required when kling_elements is used.
  • aspect_ratio supports 1:1, 16:9, 9:16.

Execution

  • Read references/api.md for endpoint details, model ids, key fields, example payloads, and polling notes.
  • Use scripts/submit_kling_3_0.sh to submit a raw JSON payload from the shell.
  • If the user only needs a curl example, adapt the example from references/api.md instead of rewriting from scratch.
  • After submission, report the task_id clearly so follow-up polling is easy.

Output expectations

When helping with this model family, include:

  • chosen model id
  • final payload or a concise parameter summary
  • whether reference images are involved
  • returned task_id if a request was actually submitted
  • next step: poll status or wait for webhook
Usage Guidance
This skill appears to do exactly what it claims: submit Kling 3.0 payloads to PoYo. Before installing, verify you trust the poyo.ai service and the homepage docs listed in the skill. Protect your POYO_API_KEY (provide only to agents you trust). Be cautious when including a callback_url in payloads—webhooks send results to the provided URL and could expose generated content or metadata to that endpoint. If you need stricter controls, run submissions manually or review payloads before sending. If you see unexpected network calls or additional env-var requests at runtime, stop and investigate.
Capability Analysis
Type: OpenClaw Skill Name: kling-3 Version: 1.0.0 The skill bundle provides a standard integration for the PoYo Kling 3.0 video generation API. It includes a shell script (scripts/submit_kling_3_0.sh) that wraps a curl command to the legitimate service endpoint (api.poyo.ai) and documentation (SKILL.md, references/api.md) that accurately describes the API's parameters and usage without any signs of malicious intent, data exfiltration, or prompt injection.
Capability Assessment
Purpose & Capability
Name/description, declared dependency (curl), required env var (POYO_API_KEY), referenced API endpoint (api.poyo.ai), and the included shell submission script all align with a video-generation integration for PoYo. Nothing requested appears unrelated to the stated purpose.
Instruction Scope
SKILL.md confines behavior to building/submitting JSON payloads to the documented PoYo endpoint and advising polling or webhook usage. It does not instruct reading other system files, scanning environment variables beyond POYO_API_KEY, or contacting unexpected endpoints.
Install Mechanism
Instruction-only skill with a small shell script; no install spec or remote downloads. This minimizes disk writes and avoids arbitrary code installation.
Credentials
Only one credential is required (POYO_API_KEY) and it is the obvious and documented API key for the service. No additional unrelated secrets, keys, or config paths are requested.
Persistence & Privilege
Skill is not always-enabled and uses default autonomous-invocation behavior. It does not request system-wide persistence or modify other skills' configurations.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install kling-3
  3. After installation, invoke the skill by name or use /kling-3
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Kling 3.0 video generation on PoYo. - Supports single-shot, multi-shot, and structured multi-prompt video creation. - Covers both standard and pro models (`kling-3.0/standard`, `kling-3.0/pro`). - Enables use of element-based prompts, reference frames (`image_urls`), and sound-enabled output. - Provides payload building guidance and clear reporting of submitted `task_id` for follow-up. - Directs users to official API documentation and example scripts for advanced scenarios.
Metadata
Slug kling-3
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Kling 3.0 video generation?

Kling 3.0 video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `kling-3.0/standard`, `kling-3.0/pro`, single-shot, multi... It is an AI Agent Skill for Claude Code / OpenClaw, with 468 downloads so far.

How do I install Kling 3.0 video generation?

Run "/install kling-3" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Kling 3.0 video generation free?

Yes, Kling 3.0 video generation is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Kling 3.0 video generation support?

Kling 3.0 video generation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Kling 3.0 video generation?

It is built and maintained by coolhackboy (@coolhackboy); the current version is v1.0.0.

💬 Comments