القائمة
Pi extension for workflow automation enabling resilient server startup procedures and agent-based workflow orchestration.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/MauricioPerera/pi-extension-data-architect --skill flow-engineيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
عرض SKILL.md
استنادا إلى تصنيف SOC المهني
| name | flow-engine |
| version | 1.0.0 |
| tags | flow,workflow,automation,orchestration,pi-extension |
| description | Pi extension for workflow automation enabling resilient server startup procedures and agent-based workflow orchestration. |
| author | Pi Agent |
This extension provides a robust workflow automation system for Pi that enables:
Pi agents often need to orchestrate complex workflows involving multiple steps:
Prior to this extension, users had to manually manage these workflows using custom scripts or complex prompt engineering.
The flow-engine extension introduces:
dependsOn relationships${variable} syntax to map outputs from previous nodes as inputs to subsequent nodesflows tableflow_runs tabletask_instances tablerun_bootstrap toolThe extension is installed as a standard Pi extension:
# From anywhere, install the extension
pi install git:https://github.com/MauricioPerera/pi-extension-data-architect
# Or install locally if you have the repo cloned
pi install -l /path/to/pi-extension-data-architect
Once installed, the extension provides several custom tools:
Store a new workflow definition.
Parameters:
name (string, required): Unique name for the workflowdefinition (string, required): JSON string representing the workflow definitiondescription (string, optional): Human-readable descriptiontags (string, optional): Comma-separated tags for categorizationversion (string, optional): Semantic version (default: "1.0.0")Example:
/tool:flow_create
{
"name": "server_startup_check",
"definition": "{\"nodes\":[{\"id\":\"check_server\",\"type\":\"tool\",\"tool\":\"bash\",\"inputMapping\":{\"command\":\"curl -s http://localhost:3000/public/tables || echo 'SERVER_DOWN'\"}},{\"id\":\"start_if_needed\",\"type\":\"agent\",\"agent\":\"server-watchdog\",\"inputMapping\":{\"command\":\"start\"},\"dependsOn\":[\"check_server\"]}]}",
"description": "Check js-doc-store-server status and start if needed",
"tags": "server,startup,automation",
"version": "1.0.0"
}
List all stored workflow definitions.
Parameters:
tags (string, optional): Comma-separated tags to filter byExample:
/tool:flow_list
# Lists all workflows
/tool:flow_list
{
"tags": "server,startup"
}
# Lists only workflows with server and startup tags
Execute a workflow by name.
Parameters:
flowName (string, required): Name of the workflow to executevariables (string, optional): JSON string of variables to pass to the workflowExample:
/tool:flow_run
{
"flowName": "server_startup_check"
}
Check the status of a workflow run.
Parameters:
runId (string, required): ID of the workflow run to checkExample:
/tool:flow_status
{
"runId": "abc123def456"
}
Ensure essential tables exist for the flow engine to operate.
Parameters: None
Example:
/tool:run_bootstrap
# Creates tables: flows, flow_runs, task_instances, skills, messages if they don't exist
A workflow definition is a JSON object with the following structure:
{
"nodes": [
{
"id": "unique_node_id",
"type": "agent|skill|tool",
"agent": "agent_name", // Required for agent type
"skill": "skill_name", // Required for skill type
"tool": "tool_name", // Required for tool type
"dependsOn": ["node_id1", "node_id2"], // Optional: array of node IDs this node depends on
"inputMapping": { // Optional: mapping of inputs for this node
"param1": "${previous_node.output}",
"param2": "literal_value",
"param3": "${context.variable}"
},
"outputMapping": { // Optional: mapping of outputs to context
"context_key": "${node.output}",
"another_key": "literal_value"
},
"maxRetries": 3 // Optional: maximum retry attempts (default: 0)
}
]
}
Execute Pi subagents:
{
"id": "process_data",
"type": "agent",
"agent": "data-processor",
"inputMapping": {
"inputData": "${fetch_data.output}"
},
"dependsOn": ["fetch_data"]
}
Load and invoke Pi skills:
{
"id": "validate_input",
"type": "skill",
"skill": "input-validator",
"inputMapping": {
"dataToValidate": "${user_input}",
"rules": "${validation_rules}"
}
}
Execute Pi tools:
{
"id": "save_results",
"type": "tool",
"tool": "write",
"inputMapping": {
"path": "./results/${workflow_id}.json",
"content": "${process_data.output}"
},
"dependsOn": ["process_data"]
}
This extension works seamlessly with the embedded server startup procedure in the skill-registry skill (version 2.2.0):
server-startup procedure{
"nodes": [
{
"id": "check_server",
"type": "tool",
"tool": "bash",
"inputMapping": {
"command": "curl -s http://localhost:3000/public/tables || echo 'DOWN'"
}
},
{
"id": "start_server_if_needed",
"type": "skill",
"skill": "server-startup",
"dependsOn": ["check_server"]
},
{
"id": "verify_server_started",
"type": "tool",
"tool": "bash",
"inputMapping": {
"command": "curl -s http://localhost:3000/public/tables"
},
"dependsOn": ["start_server_if_needed"]
}
]
}
On f