PikaBoard is a specialized task and kanban dashboard designed to serve as the primary source of truth for AI agents and automated development teams.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pikaboard
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 pikaboard 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 PikaBoard?
PikaBoard is a developer-centric task management system built with an agent-first philosophy. It provides a robust API and a visual kanban interface, allowing both humans and AI agents to collaborate on the same project backlog. By utilizing this tool within the ecosystem of Openclaw Skills, teams can ensure that their autonomous agents have a structured, reliable way to track progress, handle high-priority bugs, and manage sprint cycles without manual intervention.
The system is split into a high-performance backend and a streamlined frontend dashboard. This architecture allows agents to interact with tasks via simple RESTful commands while providing developers with a clear view of the state of the project at http://localhost:3001. As a key component of Openclaw Skills, PikaBoard bridges the gap between raw code execution and high-level project management.
PikaBoard Use Cases
- Centralizing task tracking for autonomous AI agents across different repositories.
- Implementing multi-agent workflows where each agent manages its own dedicated kanban board.
- Automating status updates for bug fixes and feature requests during the development lifecycle.
- Providing a human-in-the-loop dashboard to monitor AI agent productivity and task completion.
- Synchronizing backlogs across local and remote development environments using a unified API.
How PikaBoard Works
- The PikaBoard backend is started, initializing a SQLite database (pikaboard.db) to store persistent task data.
- Developers configure an authentication token to secure the API and dashboard.
- AI agents are mapped to specific boards using environment variables like PIKABOARD_API and AGENT_NAME.
- Agents perform CRUD operations via the API to fetch tasks from the inbox, update status to in_progress, or move completed items to done.
- The frontend dashboard reflects these changes in real-time, allowing for visual management of the agent-led sprint.
PikaBoard Setup
To get started with PikaBoard, ensure you have Node.js and npm installed. Follow these steps to deploy the skill:
# Clone the repository
git clone https://github.com/angelstreet/pikaboard
cd pikaboard
# Setup the backend
cd backend && npm install && npm run build
# Setup the frontend
cd ../frontend && npm install && npm run build
# Configure your environment
# Create a .env file in the backend directory with:
# DATABASE_PATH=./pikaboard.db
# PIKABOARD_TOKEN=your-secret-token
# Start the server
npm start
PikaBoard Data Schema & Taxonomy
PikaBoard organizes data through a relational structure optimized for fast API access. The following table outlines the core data fields for tasks:
| Field | Type | Supported Values |
|---|---|---|
| status | Enum | inbox, up_next, in_progress, testing, in_review, done, rejected |
| priority | Enum | low, medium, high, urgent |
| tags | Array | Custom strings (e.g., bug, backend, frontend) |
| board_id | Integer | Unique identifier for agent-specific boards |
Configuration is handled via environment variables, ensuring compatibility with various Openclaw Skills deployment patterns.
PikaBoard Advanced Features
- Multi-agent isolation: Separate boards for different AI agents (e.g., Bulbi, Mew, Evoli) to prevent task collisions.
- Automated board mapping: A helper script (setup-agent-board.sh) that automatically creates and verifies boards for new agents.
- Canonical API documentation: A single source of truth for all endpoints located in the backend/API.md file.
- Granular task referencing: Support for quick task lookups and status changes using shorthand syntax like #12 to done.
- Health check endpoints: Built-in validation tools to ensure the API is reachable and authentication is functioning correctly.
SKILL.md
Loading
Related Openclaw Skills
Konto Personal Finance API
A comprehensive financial interface for querying bank accounts, investments, assets, and loans through a programmatic API.
Konto Personal Finance API
A comprehensive financial interface for querying bank accounts, investments, assets, and loans through a unified API.
ClawsGames
An AI-powered gaming skill that lets agents compete in strategic games to earn ELO rankings on a public leaderboard.
Zeelin Deep Research
An asynchronous deep research agent that automates complex information gathering and professional report generation.
Play HeartClaws AI Strategy Game
A headless AI strategy game where agents compete for territory and resources on a persistent hex grid via REST API.
Smoobu Property Management
An automation skill for managing Smoobu vacation rental properties, reservations, and real-time availability across multiple booking channels.
METADATA
Featured*
