Files
stack/packages/skills/gantt/SKILL.md
2026-01-29 21:18:14 -06:00

144 lines
4.2 KiB
Markdown

---
name: mosaic-plugin-gantt
description: Query and analyze project timelines, task dependencies, and schedules from Mosaic Stack's Gantt/Project API
license: MIT
---
This skill enables querying project timelines, task dependencies, critical path analysis, and project status from Mosaic Stack's API.
## Overview
The Mosaic Stack provides project management capabilities with support for:
- Project timelines with start/end dates
- Task dependencies and scheduling
- Task status tracking (NOT_STARTED, IN_PROGRESS, PAUSED, COMPLETED, ARCHIVED)
- Priority levels (LOW, MEDIUM, HIGH, URGENT)
- Project status (PLANNING, ACTIVE, ON_HOLD, COMPLETED, ARCHIVED)
## API Endpoints
**Base URL**: Configured via `MOSAIC_API_URL` environment variable (default: `http://localhost:3000/api`)
### Projects
- `GET /api/projects` - List all projects with pagination
- `GET /api/projects/:id` - Get project details with tasks
### Tasks
- `GET /api/tasks` - List all tasks with optional filters
- Query params: `projectId`, `status`, `priority`, `assigneeId`, `page`, `limit`
## Authentication
Requests require authentication headers:
- `X-Workspace-Id`: Workspace UUID (from `MOSAIC_WORKSPACE_ID` env var)
- `Authorization`: Bearer token (from `MOSAIC_API_TOKEN` env var)
## Usage Patterns
### Query Project Timeline
When the user asks to "show project X timeline" or "what's the status of project Y":
1. List projects to find the matching project (by name or ID)
2. Get full project details including tasks
3. Present timeline information with task dates and status
### Check Task Dependencies
When asked "what blocks task X" or "what are the dependencies for task Y":
1. Search tasks to find the target task
2. Check `metadata.dependencies` field (array of task IDs)
3. Fetch blocking tasks and present the dependency chain
### Get Project Status Overview
When asked for "project status" or "project overview":
1. Get project with task count
2. Calculate status distribution (completed/in-progress/not-started)
3. Identify tasks approaching or past due dates
4. Present summary statistics
### Identify Critical Path
When asked to "find critical path" or "identify blockers":
1. Get all project tasks with dependencies
2. Build dependency graph from `metadata.dependencies`
3. Calculate longest path through dependencies
4. Identify tasks with no slack time (critical tasks)
## Data Models
### Project
```typescript
{
id: string;
name: string;
description?: string;
status: 'PLANNING' | 'ACTIVE' | 'ON_HOLD' | 'COMPLETED' | 'ARCHIVED';
startDate?: Date;
endDate?: Date;
color?: string;
tasks?: Task[];
_count: { tasks: number; events: number };
}
```
### Task
```typescript
{
id: string;
title: string;
description?: string;
status: 'NOT_STARTED' | 'IN_PROGRESS' | 'PAUSED' | 'COMPLETED' | 'ARCHIVED';
priority: 'LOW' | 'MEDIUM' | 'HIGH' | 'URGENT';
dueDate?: Date;
completedAt?: Date;
projectId?: string;
assigneeId?: string;
metadata: {
startDate?: Date;
dependencies?: string[]; // Array of task IDs
[key: string]: any;
};
}
```
## Helper Scripts
Use `gantt-api.sh` for API queries:
```bash
# List all projects
./gantt-api.sh projects
# Get project by ID
./gantt-api.sh project <project-id>
# Get tasks for a project
./gantt-api.sh tasks <project-id>
# Find critical path
./gantt-api.sh critical-path <project-id>
# Get dependency chain for a task
./gantt-api.sh dependencies <task-id>
```
## PDA-Friendly Language
When presenting information, use supportive, non-judgmental language:
- **"Target passed"** instead of "OVERDUE" or "LATE"
- **"Approaching target"** for near-deadline tasks
- **"Paused"** not "BLOCKED" or "STUCK"
- Focus on what's accomplished and what's next, not what's behind
## Implementation Notes
1. **Environment Setup**: Ensure `.env` has required variables:
- `MOSAIC_API_URL` - API base URL
- `MOSAIC_WORKSPACE_ID` - Workspace UUID
- `MOSAIC_API_TOKEN` - Authentication token
2. **Error Handling**: API returns 401 for auth errors, 404 for not found
3. **Pagination**: Projects and tasks are paginated (default 50 items/page)
4. **Dependencies**: Task dependencies are stored in `metadata.dependencies` as array of task IDs
5. **Date Handling**: Start dates may be in `metadata.startDate` or fall back to `createdAt`