Add Skill: multi-agent-sequential-workflow

Extracted from: https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git
Score: 1.0

skills/multi-agent-sequential-workflow/SKILL.md

@@ -9,10 +9,10 @@ steps:
 - 'Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel
   to gather raw facts about the destination.'
 - 'Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into
-  a structured travel guide based on the user''s request and raw information provided
+  a structured travel guide based on the user''s request and the raw information provided
   by the researcher.'
 - 'Step 3: Writer agent (agent.py) formats the final response, including the structured
-  guide content and prominently features the ''Suggested Web Pages'' section.'
+  travel guide content and prominently featuring the ''Suggested Web Pages'' section.'
 outputs:
 - Structured travel guide with key sections
 - Final client response
@@ -32,24 +32,23 @@ Gather and process information from multiple agents to generate a comprehensive
 **Dependencies:**
 
 ```text
-pip install python3 fastapi uvicorn strands bedrock-model
+pip install python langchain strands
 ```
 
 **Setup steps:**
 
-1. Install required dependencies using pip
-1. Set up environment variables for API keys and model IDs
+1. Install required dependencies using pip and ensure the BedrockModel is properly configured.
 
 ## Key Files
 
-- `agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/agent.py - Contains the multi-agent workflow logic.`
-- `agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/app.py - FastAPI app to handle user queries.`
+- `agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/agent.py - Contains the sequential workflow logic for gathering and processing information.`
+- `agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/app.py - Provides a FastAPI endpoint to interact with the multi-agent system.`
 
 ## Steps
 
 1. Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination.
-2. Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and raw information provided by the researcher.
-3. Step 3: Writer agent (agent.py) formats the final response, including the structured guide content and prominently features the 'Suggested Web Pages' section.
+2. Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and the raw information provided by the researcher.
+3. Step 3: Writer agent (agent.py) formats the final response, including the structured travel guide content and prominently featuring the 'Suggested Web Pages' section.
 
 ## Implementation Details
 
@@ -76,7 +75,7 @@ final_response = writer_agent(writer_prompt, stream=False)
 
 ## Failure Modes
 
-- Network issues during API calls could lead to incomplete data collection or processing failures
+- Specific failure scenario with mitigation: If any of the agents fail to process their tasks (e.g., network issues, model errors), the workflow will fail. Mitigation involves robust error handling and fallback mechanisms.
 
 ## Source
 

skills/multi-agent-sequential-workflow/examples.md

@@ -5,6 +5,6 @@
 ```python
 # How to use this skill
 # Inputs: User query with location
-# Process: Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination. → Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and raw information provided by the researcher. → Step 3: Writer agent (agent.py) formats the final response, including the structured guide content and prominently features the 'Suggested Web Pages' section.
+# Process: Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination. → Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and the raw information provided by the researcher. → Step 3: Writer agent (agent.py) formats the final response, including the structured travel guide content and prominently featuring the 'Suggested Web Pages' section.
 # Outputs: Structured travel guide with key sections, Final client response
 ```

skills/multi-agent-sequential-workflow/metadata.json

@@ -7,18 +7,18 @@
   ],
   "steps": [
     "Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination.",
-    "Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and raw information provided by the researcher.",
-    "Step 3: Writer agent (agent.py) formats the final response, including the structured guide content and prominently features the 'Suggested Web Pages' section."
+    "Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and the raw information provided by the researcher.",
+    "Step 3: Writer agent (agent.py) formats the final response, including the structured travel guide content and prominently featuring the 'Suggested Web Pages' section."
   ],
   "outputs": [
     "Structured travel guide with key sections",
     "Final client response"
   ],
   "failure_modes": [
-    "Network issues during API calls could lead to incomplete data collection or processing failures"
+    "Specific failure scenario with mitigation: If any of the agents fail to process their tasks (e.g., network issues, model errors), the workflow will fail. Mitigation involves robust error handling and fallback mechanisms."
   ],
   "confidence": 0.95,
-  "explanation": "This workflow is specific but can be adapted for other types of guides or information gathering tasks.",
+  "explanation": "This workflow is specific to generating travel guides but can be adapted for other types of structured content creation.",
   "source_repo": "https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git",
   "score": 1.0
 }

skills/unifai-workflow-execution/SKILL.md

@@ -1,62 +1,96 @@
 ---
 name: unifai-workflow-execution
 version: 1.0.0
-description: Execute a multi-agent AI workflow defined in YAML or through the UI's
-  drag-and-drop editor.
+description: Execute a multi-agent workflow on the UnifAI platform using a specified
+  blueprint and user prompt.
 inputs:
-- name: blueprint_path
-  description: Path to the blueprint file (YAML) defining the multi-agent workflow.
-- name: execution_mode
-  description: 'Execution mode: ''local'' or ''distributed''.'
+- blueprint_id or blueprint_name
+- user_shortcut
+- user_question
 steps:
-- step_name: Load Blueprint
-  description: Parse and validate the blueprint file to ensure it conforms to expected
-    structure.
-- step_name: Initialize Execution Engine
-  description: Set up the execution engine based on the selected mode ('local' or
-    'distributed').
-- step_name: Execute Workflow
-  description: Run the multi-agent workflow, streaming node-by-node output as NDJSON
-    over HTTP.
-- step_name: Stream Results
-  description: Render and stream results in real time to clients subscribing to the
-    event stream.
+- 'Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id
+  method)'
+- 'Step 2: Create a new session from the blueprint (create_session method)'
+- 'Step 3: Submit the session for background execution with the user prompt (submit_session
+  method)'
+- 'Step 4: Poll session status until execution completes (poll_session_status method)'
 outputs:
-- name: execution_results
-  description: The output of the executed workflow, streamed as NDJSON over HTTP.
+- session_id
+- workflow_id
 tags: []
 metadata:
   source_repo: https://github.com/redhat-community-ai-tools/UnifAI.git
   extracted_at: ''
-  confidence: 0.9
+  confidence: 0.95
 ---
 
 # unifai-workflow-execution
 
-Execute a multi-agent AI workflow defined in YAML or through the UI's drag-and-drop editor.
+Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt.
+
+## Setup
+
+**Dependencies:**
+
+```text
+pip install requests urllib3
+```
+
+**Setup steps:**
+
+1. Install required dependencies using pip install requests urllib3
+1. Ensure the environment variables are set correctly (BLUEPRINT_ID, BLUEPRINT_NAME, USER_SHORTCUT, POLLING_INTERVAL, UNIFAI_BASE_URL)
+
+## Key Files
+
+- `scripts/execution_workflow.py - Main script for workflow execution`
 
 ## Steps
 
-1. {'step_name': 'Load Blueprint', 'description': 'Parse and validate the blueprint file to ensure it conforms to expected structure.'}
-2. {'step_name': 'Initialize Execution Engine', 'description': "Set up the execution engine based on the selected mode ('local' or 'distributed')."}
-3. {'step_name': 'Execute Workflow', 'description': 'Run the multi-agent workflow, streaming node-by-node output as NDJSON over HTTP.'}
-4. {'step_name': 'Stream Results', 'description': 'Render and stream results in real time to clients subscribing to the event stream.'}
+1. Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method)
+2. Step 2: Create a new session from the blueprint (create_session method)
+3. Step 3: Submit the session for background execution with the user prompt (submit_session method)
+4. Step 4: Poll session status until execution completes (poll_session_status method)
+
+## Implementation Details
+
+```python
+resolve_blueprint_id(client: UnifAIClient) -> str
+{...}
+# Resolve the blueprint ID from either direct ID or name lookup.
+```
+
+```python
+create_session(client: UnifAIClient, blueprint_id: str) -> str
+{...}
+# Create a new session from the blueprint.
+```
+
+```python
+submit_session(client: UnifAIClient, session_id: str) -> dict
+{...}
+# Submit the session for background execution with the user prompt.
+```
 
 ## Inputs
 
-- {'name': 'blueprint_path', 'description': 'Path to the blueprint file (YAML) defining the multi-agent workflow.'}
-- {'name': 'execution_mode', 'description': "Execution mode: 'local' or 'distributed'."}
+- blueprint_id or blueprint_name
+- user_shortcut
+- user_question
 
 ## Outputs
 
-- {'name': 'execution_results', 'description': 'The output of the executed workflow, streamed as NDJSON over HTTP.'}
+- session_id
+- workflow_id
 
 ## Failure Modes
 
-- {'mode_name': 'Invalid Blueprint', 'description': 'Blueprint file is not valid YAML or does not conform to expected structure.'}
-- {'mode_name': 'Execution Engine Initialization Failure', 'description': 'Failed to initialize the execution engine due to configuration issues or missing dependencies.'}
+- Blueprint name not found or not unique - error during blueprint resolution
+- Session creation fails - error from API response
+- Session submission fails - error from API response
+- Polling session status fails - error from API response
 
 ## Source
 
 Extracted from: [https://github.com/redhat-community-ai-tools/UnifAI.git](https://github.com/redhat-community-ai-tools/UnifAI.git)
-Confidence: 0.9
+Confidence: 0.95

skills/unifai-workflow-execution/examples.md

@@ -4,7 +4,7 @@
 
 ```python
 # How to use this skill
-# Inputs: {'name': 'blueprint_path', 'description': 'Path to the blueprint file (YAML) defining the multi-agent workflow.'}, {'name': 'execution_mode', 'description': "Execution mode: 'local' or 'distributed'."}
-# Process: {'step_name': 'Load Blueprint', 'description': 'Parse and validate the blueprint file to ensure it conforms to expected structure.'} → {'step_name': 'Initialize Execution Engine', 'description': "Set up the execution engine based on the selected mode ('local' or 'distributed')."} → {'step_name': 'Execute Workflow', 'description': 'Run the multi-agent workflow, streaming node-by-node output as NDJSON over HTTP.'}
-# Outputs: {'name': 'execution_results', 'description': 'The output of the executed workflow, streamed as NDJSON over HTTP.'}
+# Inputs: blueprint_id or blueprint_name, user_shortcut, user_question
+# Process: Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method) → Step 2: Create a new session from the blueprint (create_session method) → Step 3: Submit the session for background execution with the user prompt (submit_session method)
+# Outputs: session_id, workflow_id
 ```

skills/unifai-workflow-execution/metadata.json

@@ -1,53 +1,30 @@
 {
   "name": "unifai-workflow-execution",
   "version": "1.0.0",
-  "goal": "Execute a multi-agent AI workflow defined in YAML or through the UI's drag-and-drop editor.",
+  "goal": "Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt.",
   "inputs": [
-    {
-      "name": "blueprint_path",
-      "description": "Path to the blueprint file (YAML) defining the multi-agent workflow."
-    },
-    {
-      "name": "execution_mode",
-      "description": "Execution mode: 'local' or 'distributed'."
-    }
+    "blueprint_id or blueprint_name",
+    "user_shortcut",
+    "user_question"
   ],
   "steps": [
-    {
-      "step_name": "Load Blueprint",
-      "description": "Parse and validate the blueprint file to ensure it conforms to expected structure."
-    },
-    {
-      "step_name": "Initialize Execution Engine",
-      "description": "Set up the execution engine based on the selected mode ('local' or 'distributed')."
-    },
-    {
-      "step_name": "Execute Workflow",
-      "description": "Run the multi-agent workflow, streaming node-by-node output as NDJSON over HTTP."
-    },
-    {
-      "step_name": "Stream Results",
-      "description": "Render and stream results in real time to clients subscribing to the event stream."
-    }
+    "Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method)",
+    "Step 2: Create a new session from the blueprint (create_session method)",
+    "Step 3: Submit the session for background execution with the user prompt (submit_session method)",
+    "Step 4: Poll session status until execution completes (poll_session_status method)"
   ],
   "outputs": [
-    {
-      "name": "execution_results",
-      "description": "The output of the executed workflow, streamed as NDJSON over HTTP."
-    }
+    "session_id",
+    "workflow_id"
   ],
   "failure_modes": [
-    {
-      "mode_name": "Invalid Blueprint",
-      "description": "Blueprint file is not valid YAML or does not conform to expected structure."
-    },
-    {
-      "mode_name": "Execution Engine Initialization Failure",
-      "description": "Failed to initialize the execution engine due to configuration issues or missing dependencies."
-    }
+    "Blueprint name not found or not unique - error during blueprint resolution",
+    "Session creation fails - error from API response",
+    "Session submission fails - error from API response",
+    "Polling session status fails - error from API response"
   ],
-  "confidence": 0.9,
-  "explanation": "This workflow is designed to execute multi-agent AI workflows defined in YAML blueprints or through the UI's drag-and-drop editor, providing real-time streaming of results.",
+  "confidence": 0.95,
+  "explanation": "This workflow is specific to the UnifAI platform and its multi-agent system, but can be adapted for similar systems with a similar architecture.",
   "source_repo": "https://github.com/redhat-community-ai-tools/UnifAI.git",
   "score": 1.0
 }