TKSeller is an interactive automation skill designed to integrate custom TikTok seller SaaS platforms directly with messaging clients.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawshop-pro
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install clawshop-pro using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is TKSeller?
TKSeller is a specialized developer integration designed to work with Openclaw Skills. The tool functions as a bridge between an AI agent and a TikTok seller SaaS platform, mapping complex API workflows (/api/v1/*) to simple slash commands and graphical button events. It offers digital commerce teams a robust mechanism to manage video-centric e-commerce tasks without manually jumping between dashboards.
The skill structures and automates the creative asset pipeline. By processing background generation runs, product catalog linkages, multi-tier storyboard reviews, and video approvals within active chat channels, TKSeller lowers the friction of maintaining high-frequency content campaigns. It runs under a strict zero-preamble execution rule, ensuring fast API communication and reliable runtime feedback.
TKSeller Use Cases
- Automating the collection and linking of video assets to target TikTok Shop merchandise.
- Performing multi-step creative approvals for storyboards, product pairings, and video generation directly in team chats.
- Polling asynchronous remote events and updates from SaaS backends in real time.
- Managing discrete local states and security tokens securely across distinct team channels.
- Minimizing conversational latency during agent tool execution in live user interactions.
How TKSeller Works
- Execution Call: The user triggers the skill using /tkseller or via a TikTok video link. The agent initiates tool execution immediately with zero pre-announcement conversational noise.
- Authentication Handling: The script evaluates cached credentials at data/token.json. If missing or invalid (401), the tool prompts for login credentials and posts to
/api/v1/auth/loginto retrieve a bearer token. - Workflow Initiation: A video resource URL is submitted via POST
/api/v1/recommend. This action initializes the remote analysis and schedules a background polling cron trigger. - SaaS Event Polling: The registered cron script (
poll-events.mjs) calls/api/v1/events/pendingregularly to pull new storyboard reviews, rendering tasks, or publishing updates. - State-Driven Interactions: Task details are delivered to chat cards with integrated buttons. When clicked,
handle-button.mjsmaps interaction labels to the backend APIs, processing reviews and content state updates. - Deregistration: Once the final state is reached (video publication, rejection, or a 15-minute timeout), the polling cron task automatically unsubscribes to prevent resource drain.
TKSeller Setup
Installation
Install the skill files inside your active workspace using the command line:
clawhub install tkseller
Slash Command Registration
To bypass global propagation delays and activate the slash command interface immediately inside your Discord server:
node ./lib-js/register-discord.mjs
Configure your custom target API settings inside the config file (data_service.base_url) before running execution scripts.
TKSeller Data Schema & Taxonomy
The skill manages localized operational data files inside the data/ folder to maintain state alignment:
| File Name | Purpose | Core Schema elements |
|---|---|---|
data/token.json |
Stores the active SaaS JWT authentication and username data. | {"token": "string", "username": "string"} |
data/card_map.json |
Pairs interaction card tracking IDs with remote production video records. | {"date": "YYYY-MM-DD", "next_id": 3, "cards": {}} |
data/processed_events.json |
Logs acknowledged remote IDs to prevent duplicate actions. | {"ids": [1001, 1002, 1003]} |
data/poll_state.json |
Tracks runtime statuses and start timestamps for context management. | {"started_at": 1716180000, "active": true} |
This architecture keeps critical API metadata accessible without burdening active memory pools.
TKSeller Advanced Features
- Automated Cron Scheduling: Orchestrates recursive loop polling at sub-second intervals using native gateway features.
- Adaptive Client Framework: Standardizes rendering options to function seamlessly on both Discord button blocks and Webchat text triggers.
- Robust API Error Managers: Integrates fallback handlers to resolve rate limits, token expiration issues, and network server timeouts cleanly.
- Light Context Isolation: Avoids loading history parameters into background calls, preventing context bloat during automated updates.
- Short ID Resolution Engine: Resolves temporary local identification flags to remote database entries to speed up manual client triggers.
SKILL.md
Loading
Related Openclaw Skills
novel-master
A publication-grade Chinese novel writing skill pack designed for long-form fiction using a distributed multi-agent architecture.
biaoshu-writer-corp
An AI-powered bidding assistant that automates document parsing, docx generation, and strict compliance risk analysis via an asynchronous API connection.
novel-master
A publication-grade Chinese long-form novel creation framework powered by a unique distributed multi-agent architecture.
Taiwan Stock Exchange (TWSE) API
A developer integration that enables programmatic retrieval and analysis of Taiwan Stock Exchange open data without authentication.
DXF Generation and Validation
An AI agent skill to programmatically generate, update, and validate 2D DXF drawings and CAD projections from Python sources.
step-parts
A precision skill for searching, validating, and pulling off-the-shelf catalog component STEP files directly into CAD workflows.
Featured*
