Operational workflow automation skill with task sequencing, approval routing, and exception handling
Automates operational workflows with task sequencing, approval routing, and exception handling.
npx claudepluginhub a5c-ai/babysitterThis skill is limited to using the following tools:
The Workflow Automator skill provides comprehensive capabilities for automating operational workflows. It supports task sequencing, approval routing, notification automation, exception handling, and audit trail generation.
skill: workflow-automator
inputs:
workflow_name: "Engineering Change Request"
trigger:
type: "form_submission"
source: "ecr_form"
steps:
- name: "Initial Review"
assignee_role: "Engineering Manager"
action: "approve_reject"
sla: 2 # business days
- name: "Impact Assessment"
assignee_role: "Cross-functional Team"
action: "complete_assessment"
sla: 5
- name: "Final Approval"
assignee_role: "Director"
action: "approve_reject"
sla: 2
notifications:
- event: "assignment"
recipient: "assignee"
method: ["email", "slack"]
- event: "sla_warning"
recipient: "assignee_manager"
method: ["email"]
escalation:
- threshold: "sla_breach"
action: "notify_director"
outputs:
- workflow_definition
- notification_templates
- escalation_rules
- audit_configuration
- integration_specs
| Type | Description | Example |
|---|---|---|
| Form submission | User completes form | ECR request |
| Schedule | Time-based | Daily report |
| Event | System event | Order received |
| Condition | Data condition | Inventory low |
| Type | Description | Example |
|---|---|---|
| Approval | Yes/No decision | Manager approval |
| Task | Work to complete | Update document |
| Notification | Send message | Alert stakeholder |
| Integration | System action | Update ERP |
| Type | Description | Use Case |
|---|---|---|
| Sequential | One after another | Approval chain |
| Parallel | Multiple simultaneous | Concurrent reviews |
| Conditional | Based on data | Amount threshold |
| Dynamic | Based on rules | Skill-based |
exceptions:
- condition: "assignee_unavailable"
action: "reassign_to_backup"
- condition: "sla_breach"
action: "escalate_to_manager"
- condition: "rejection"
action: "return_to_initiator"
- condition: "system_error"
action: "notify_admin_and_retry"
| Stage | SLA | Warning | Escalation |
|---|---|---|---|
| Initial Review | 2 days | 1.5 days | 2.5 days |
| Assessment | 5 days | 4 days | 6 days |
| Approval | 2 days | 1.5 days | 2.5 days |
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.