A terminal-first project bootstrapper and workspace context manager that synchronizes local task management with Trello.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install project-router
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 project-router 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 Project Router?
Project Router serves as the canonical control plane for managing project metadata and switching between development contexts effortlessly. By utilizing a local SQLite database for speed and queryability, and a Trello backend for visual tracking, it ensures your project briefs, build targets, and task statuses remain consistent across your CLI and project management tools.
This tool is designed for developers using Openclaw Skills who require a deterministic way to load the right documentation, code, and index for any given task. It treats project management as a local-first, queryable operation while providing robust integration with external tracking tools.
Project Router Use Cases
- Initialize and manage standardized project bundles using .project directories for consistent workspace layouts.
- Rapidly switch between different project contexts to automatically load relevant documentation and artifacts.
- Synchronize local task management with Trello boards to maintain a visual UI for stakeholders while keeping a local source of truth.
- Execute standardized build, test, and deployment targets via a unified CLI interface across multiple repositories.
- Index and manage project-specific artifacts and metadata for quick retrieval during development sessions.
How Project Router Works
- The user initializes a project bundle using the project init command to create the .project directory and manifest files.
- Project metadata and tasks are stored in a local SQLite database, acting as the canonical source of truth for the workspace.
- Developers use the CLI or the mcp-project-router MCP server to detect the current project context and run predefined targets.
- Tasks added via the CLI are managed locally and can be synchronized with Trello, where cards are automatically updated with labels and machine-readable metadata.
- The focus command allows developers to jump into specific task contexts, automatically loading linked files and artifacts for the active session.
Project Router Setup
To get started with this skill in your environment, follow these installation steps:
# Initialize a project bundle (creates a plan)
project init
# Apply the generated plan to set up the .project structure
project apply <planId>
# Add the project to the canonical management database
project pm project add <slug> --name "My Project" --root $(pwd)
# Sync with your Trello board
project pm trello sync --project <slug>
Ensure your SQLite database is located at the path defined in your environment configuration, typically within your workspace data directory.
Project Router Data Schema & Taxonomy
The skill organizes its data using a combination of a project-local bundle and a global SQLite database:
| Location | Component | Description |
|---|---|---|
.project/project.json |
Manifest | Structured identification and metadata for the project. |
.project/targets.json |
Targets | Command definitions for build, test, and lint actions. |
pm.sqlite (Table) |
projects |
Stores project slugs, names, and absolute root paths. |
pm.sqlite (Table) |
tasks |
Tracks task titles, priority (P0-P3), and status. |
.project/index/ |
Artifacts | A local index for project-specific files and URLs. |
Project Router Advanced Features
- Multi-agent support via the mcp-project-router server, allowing AI agents to query project context and run targets.
- Idempotent Trello synchronization that uses machine-readable YAML headers in card descriptions to prevent duplication.
- Plan and Apply workflow for all project-local modifications, ensuring transparency and safety for file system changes.
- Integrated context switching that loads task-linked files and updates activity logs automatically.
- Standardized artifact management for indexing external references like documentation URLs or local build outputs.
SKILL.md
Loading
Related Openclaw Skills
Knowledge Graph
Maintain a deterministic, file-based knowledge graph by adding, superseding, and summarizing atomic facts for entities.
Finance Skill
A personal finance memory layer that enables AI agents to parse statements, store transaction history, and perform spending analysis.
Equity Analyst
A professional-grade AI agent skill for analyzing Korean stocks using a rigorous financial-first evaluation framework.
Equity Analyst
A professional AI investment analyst that provides systematic evaluation and scoring for Korean stocks listed on the KRX.
stdio-skill
A secure filesystem-backed bridge for exchanging files between users and AI agents via MCP.
Vision Tagger
A local macOS image analysis tool leveraging Apple's Vision framework to detect faces, text, poses, and objects without external API calls.
Featured*
