← Back to Skills Marketplace
TikTok Video Maker
by
George Gally
· GitHub ↗
· v1.0.3
· MIT-0
186
Downloads
1
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install tiktok-video-maker
Description
Generate TikTok-style talking videos from a script and image using the LovelyBots API. Queue a video, poll for completion, and retrieve a download URL — all...
Usage Guidance
This skill is internally consistent and appears to do what it says — call LovelyBots' API to queue and poll video renders. Before installing, consider: (1) Source verification: the package's Source is listed as "unknown" — confirm the publisher/URL (https://lovelybots.com/openclaw) is legitimate and trustworthy. (2) Secrets & cost: the LOVELYBOTS_API_KEY grants the skill the ability to make API calls that may consume paid credits — treat it as a secret, do not share it, and be prepared to rotate/revoke if needed. (3) Privacy: images and scripts you send will be uploaded to LovelyBots; do not send sensitive or private images unless you accept that. (4) Confirm endpoints: the docs reference https://api.lovelybots.com/api; verify that matches official LovelyBots docs to avoid typosquatting. (5) Autonomy: the skill can be invoked by the agent (normal default). If you do not want an agent to call external services automatically, disable model invocation or restrict use. If you need greater assurance, ask the publisher for a verified source (GitHub repo or signed publisher identity) and review LovelyBots' privacy/terms and billing behavior before enabling.
Capability Analysis
Type: OpenClaw Skill
Name: tiktok-video-maker
Version: 1.0.3
The skill is a legitimate integration for the LovelyBots API, designed to generate TikTok-style videos. It provides clear instructions and a robust bash polling script in SKILL.md that uses standard tools (curl, python3, jq) to interact with the service's API (api.lovelybots.com). There is no evidence of data exfiltration, malicious execution, or prompt injection; the code follows best practices for API interaction, including error handling and security notes regarding SSRF prevention.
Capability Assessment
Purpose & Capability
Name/description (generate TikTok-style talking videos via LovelyBots) align with requested resources: curl and python3 for HTTP and polling, and a single LOVELYBOTS_API_KEY for API authentication. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md contains concrete API calls (POST /api/create, GET /api/videos/:id), polling guidance, and examples that use only the declared env var and standard tools. It does not instruct reading unrelated system files, harvesting other credentials, or calling unknown external endpoints; all calls point to lovelybots.com/api or lovelybots.com.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk footprint. Nothing is downloaded or written to disk by an installer step.
Credentials
Only LOVELYBOTS_API_KEY is required and it's declared as the primary credential. This is proportional to the described API usage. No other secret-like env vars or config paths are requested.
Persistence & Privilege
always is false and the skill has no install hooks or instructions to modify other skills or system-wide configuration. Normal autonomous invocation is allowed (disable-model-invocation false) which is the platform default.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tiktok-video-maker - After installation, invoke the skill by name or use
/tiktok-video-maker - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Added a recommended agent status update step when polling for job completion.
- Encourages reporting progress (including share URL) to the user while the video is queued or processing.
- Includes a message template for agent status updates in the documentation.
- No code or interface changes; documentation update only.
v1.0.2
**Summary: Improved API usage and polling reliability for TikTok Video Maker via LovelyBots.**
- Updated API base URLs to use `https://api.lovelybots.com/api` (previously pointed to web app host).
- Clarified that IDs (`video.id`, `voice_id`) are UUID strings, not integers; all docs/examples now match.
- Enhanced polling bash script with explicit HTTP error handling, retry/backoff support, and both `jq` and `python3` parsing compatibility.
- Added setup instructions for required LovelyBots subscription and API token creation.
- Expanded agent guidance on host/auth separation, error handling, and public image URL requirements.
- Updated metadata to require `python3` (in addition to `curl`).
v1.0.1
- various bug fixes
- enabled sharing and public viewing
- allows for base64 image
- auto choose voice by gender and age
v1.0.0
Initial release of TikTok Video Maker skill.
- Generate TikTok-style avatar videos from a script and image via the LovelyBots API.
- Submit a video job, poll status, and retrieve the download URL in a seamless workflow.
- Reports credits used per request; failed jobs are refunded.
- Supports any avatar image URL and ensures consistent avatar identity.
- Designed for marketing teams, e-commerce brands, and automation pipelines.
Metadata
Frequently Asked Questions
What is TikTok Video Maker?
Generate TikTok-style talking videos from a script and image using the LovelyBots API. Queue a video, poll for completion, and retrieve a download URL — all... It is an AI Agent Skill for Claude Code / OpenClaw, with 186 downloads so far.
How do I install TikTok Video Maker?
Run "/install tiktok-video-maker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TikTok Video Maker free?
Yes, TikTok Video Maker is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TikTok Video Maker support?
TikTok Video Maker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TikTok Video Maker?
It is built and maintained by George Gally (@georgegally); the current version is v1.0.3.
More Skills