Add Skill: unifai-workflow-execution

Extracted from: https://github.com/redhat-community-ai-tools/UnifAI.git Score: 1.0
2026-08-05 15:45:08 +00:00
21 changed files with 76 additions and 573 deletions
@@ -34,8 +34,8 @@ scout:
    - 'rag agent workflow'
    - 'tool calling workflow'
  filters:
-    stars_min: 10
+    stars_min: 15
-    pushed_after: 2026-02-01
+    pushed_after: 2026-05-01
    language: Python
    archived: false
    size_max_kb: 10000
@@ -52,18 +52,6 @@ def publish_skill(review_result, config):
        subprocess.run(["git", "config", "user.email", "hermes@agent.local"], cwd=repo_dir)
        subprocess.run(["git", "config", "user.name", "Hermes Pipeline"], cwd=repo_dir)
        # Check for duplicates in skills/ directory
        skills_dir = os.path.join(repo_dir, "skills")
        existing_skills = []
        if os.path.isdir(skills_dir):
            existing_skills = [d for d in os.listdir(skills_dir) if os.path.isdir(os.path.join(skills_dir, d))]
        if skill_name in existing_skills:
            return {
                "status": "SKIP",
                "reason": f"Skill '{skill_name}' already exists in skills/ directory",
            }
        # Create skill directory
        skill_dir = os.path.join(repo_dir, "skills", skill_name)
        os.makedirs(skill_dir, exist_ok=True)
@@ -137,8 +137,6 @@ def main():
        if publish_output.get("status") == "PUBLISHED":
            print(f"    ✓ Published! PR: {publish_output.get('pr_url', '')}")
            results["published"] += 1
        elif publish_output.get("status") == "SKIP":
            print(f"    ⏸ Skipped: {publish_output.get('reason', '')}")
        else:
            print(f"    ! {publish_output.get('status', '?')}: {publish_output.get('message', publish_output.get('error', ''))[:100]}")
@@ -1,84 +0,0 @@
 ---
 name: agent-supervisor
 version: 1.0.0
 description: Demonstrate a supervisor-worker architecture for intelligent task delegation
  and real-time decision-making.
 inputs:
 - name: OPENAI_API_KEY
  description: OpenAI API key for language models.
 - name: TAVILY_API_KEY
  description: Tavily API key for search functionality.
 steps:
 - step: 1
  action: Load environment variables.
  details: Set the OPENAI_API_KEY and TAVILY_API_KEY environment variables.
 - step: 2
  action: Configure LangChain tools.
  details: Initialize TavilySearchResults and PythonREPLTool.
 - step: 3
  action: Define agent nodes.
  details: Create functions for the Researcher and Coder agents that process state
    through their respective tasks.
 - step: 4
  action: Set up supervisor agent.
  details: Create a supervisor agent function that decides which worker should act
    next based on user input.
 - step: 5
  action: Build state graph.
  details: Construct the state graph with nodes for each agent and edges connecting
    them to the supervisor node.
 - step: 6
  action: Add conditional edges.
  details: Define conditions for transitioning between agents based on their responses.
 - step: 7
  action: Compile graph.
  details: Compile the state graph into a runnable workflow.
 - step: 8
  action: Run example queries.
  details: Stream through the workflow with example inputs to demonstrate its functionality.
 outputs:
 - name: 'Example 1: Code Hello World'
  description: A demonstration of coding a simple hello world program.
 - name: 'Example 2: Research Report'
  description: A demonstration of researching and writing a brief report on pikas.
 tags: []
 metadata:
  source_repo: https://github.com/extrawest/multi_agent_workflow_demo_in_langgraph.git
  extracted_at: ''
  confidence: 0.9
 ---
 # agent-supervisor
 Demonstrate a supervisor-worker architecture for intelligent task delegation and real-time decision-making.
 ## Steps
 1. {'step': 1, 'action': 'Load environment variables.', 'details': 'Set the OPENAI_API_KEY and TAVILY_API_KEY environment variables.'}
 2. {'step': 2, 'action': 'Configure LangChain tools.', 'details': 'Initialize TavilySearchResults and PythonREPLTool.'}
 3. {'step': 3, 'action': 'Define agent nodes.', 'details': 'Create functions for the Researcher and Coder agents that process state through their respective tasks.'}
 4. {'step': 4, 'action': 'Set up supervisor agent.', 'details': 'Create a supervisor agent function that decides which worker should act next based on user input.'}
 5. {'step': 5, 'action': 'Build state graph.', 'details': 'Construct the state graph with nodes for each agent and edges connecting them to the supervisor node.'}
 6. {'step': 6, 'action': 'Add conditional edges.', 'details': 'Define conditions for transitioning between agents based on their responses.'}
 7. {'step': 7, 'action': 'Compile graph.', 'details': 'Compile the state graph into a runnable workflow.'}
 8. {'step': 8, 'action': 'Run example queries.', 'details': 'Stream through the workflow with example inputs to demonstrate its functionality.'}
 ## Inputs
 - {'name': 'OPENAI_API_KEY', 'description': 'OpenAI API key for language models.'}
 - {'name': 'TAVILY_API_KEY', 'description': 'Tavily API key for search functionality.'}
 ## Outputs
 - {'name': 'Example 1: Code Hello World', 'description': 'A demonstration of coding a simple hello world program.'}
 - {'name': 'Example 2: Research Report', 'description': 'A demonstration of researching and writing a brief report on pikas.'}
 ## Failure Modes
 - {'mode': 'Invalid API keys', 'description': 'The workflow may fail if the provided API keys are invalid or expired.'}
 - {'mode': 'Insufficient permissions', 'description': 'The workflow may fail if the user does not have sufficient permissions to use the Tavily search functionality.'}
 ## Source
 Extracted from: [https://github.com/extrawest/multi_agent_workflow_demo_in_langgraph.git](https://github.com/extrawest/multi_agent_workflow_demo_in_langgraph.git)
 Confidence: 0.9
@@ -1,6 +0,0 @@
 # Commands: agent-supervisor
 ## Available Commands
 - `/skill agent-supervisor` — Load this skill
 - `/run agent-supervisor` — Execute workflow
@@ -1,10 +0,0 @@
 # Examples: agent-supervisor
 ## Usage Example
 ```python
 # How to use this skill
 # Inputs: {'name': 'OPENAI_API_KEY', 'description': 'OpenAI API key for language models.'}, {'name': 'TAVILY_API_KEY', 'description': 'Tavily API key for search functionality.'}
 # Process: {'step': 1, 'action': 'Load environment variables.', 'details': 'Set the OPENAI_API_KEY and TAVILY_API_KEY environment variables.'} → {'step': 2, 'action': 'Configure LangChain tools.', 'details': 'Initialize TavilySearchResults and PythonREPLTool.'} → {'step': 3, 'action': 'Define agent nodes.', 'details': 'Create functions for the Researcher and Coder agents that process state through their respective tasks.'}
 # Outputs: {'name': 'Example 1: Code Hello World', 'description': 'A demonstration of coding a simple hello world program.'}, {'name': 'Example 2: Research Report', 'description': 'A demonstration of researching and writing a brief report on pikas.'}
 ```
@@ -1,81 +0,0 @@
 {
  "name": "agent-supervisor",
  "version": "1.0.0",
  "goal": "Demonstrate a supervisor-worker architecture for intelligent task delegation and real-time decision-making.",
  "inputs": [
    {
      "name": "OPENAI_API_KEY",
      "description": "OpenAI API key for language models."
    },
    {
      "name": "TAVILY_API_KEY",
      "description": "Tavily API key for search functionality."
    }
  ],
  "steps": [
    {
      "step": 1,
      "action": "Load environment variables.",
      "details": "Set the OPENAI_API_KEY and TAVILY_API_KEY environment variables."
    },
    {
      "step": 2,
      "action": "Configure LangChain tools.",
      "details": "Initialize TavilySearchResults and PythonREPLTool."
    },
    {
      "step": 3,
      "action": "Define agent nodes.",
      "details": "Create functions for the Researcher and Coder agents that process state through their respective tasks."
    },
    {
      "step": 4,
      "action": "Set up supervisor agent.",
      "details": "Create a supervisor agent function that decides which worker should act next based on user input."
    },
    {
      "step": 5,
      "action": "Build state graph.",
      "details": "Construct the state graph with nodes for each agent and edges connecting them to the supervisor node."
    },
    {
      "step": 6,
      "action": "Add conditional edges.",
      "details": "Define conditions for transitioning between agents based on their responses."
    },
    {
      "step": 7,
      "action": "Compile graph.",
      "details": "Compile the state graph into a runnable workflow."
    },
    {
      "step": 8,
      "action": "Run example queries.",
      "details": "Stream through the workflow with example inputs to demonstrate its functionality."
    }
  ],
  "outputs": [
    {
      "name": "Example 1: Code Hello World",
      "description": "A demonstration of coding a simple hello world program."
    },
    {
      "name": "Example 2: Research Report",
      "description": "A demonstration of researching and writing a brief report on pikas."
    }
  ],
  "failure_modes": [
    {
      "mode": "Invalid API keys",
      "description": "The workflow may fail if the provided API keys are invalid or expired."
    },
    {
      "mode": "Insufficient permissions",
      "description": "The workflow may fail if the user does not have sufficient permissions to use the Tavily search functionality."
    }
  ],
  "confidence": 0.9,
  "explanation": "This workflow demonstrates a hierarchical multi-agent system where a supervisor agent makes routing decisions based on user input, delegating tasks to specialized worker agents (Researcher and Coder). It is designed to be reusable for similar task delegation scenarios.",
  "source_repo": "https://github.com/extrawest/multi_agent_workflow_demo_in_langgraph.git",
  "score": 1.0
 }
@@ -1,9 +0,0 @@
 # Tests: agent-supervisor
 ## Test Checklist
 - [ ] Workflow has at least 3 steps
 - [ ] All inputs are defined
 - [ ] All outputs are defined
 - [ ] Failure modes are documented
 - [ ] Skill can be loaded without errors
@@ -1,83 +0,0 @@
 ---
 name: langgraph-workflow-creation
 version: 1.0.0
 description: Create a LangGraph workflow to gather facts using SerperDevTool and process
  them with an AI agent.
 inputs:
 - API Key for SerperDevTool
 - Search Query
 steps:
 - 'Step 1: Import necessary modules from langgraph and langchain libraries'
 - 'Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function
  with SerperDevTool as the tool node'
 - 'Step 3: Define the search query and pass it to the agent for fact gathering'
 - 'Step 4: Process the gathered facts within the AI agent'
 outputs:
 - Processed Facts
 tags: []
 metadata:
  source_repo: https://github.com/jkmaina/LangGraphProjects.git
  extracted_at: ''
  confidence: 0.95
 ---
 # langgraph-workflow-creation
 Create a LangGraph workflow to gather facts using SerperDevTool and process them with an AI agent.
 ## Setup
 **Dependencies:**
 ```text
 pip install langchain serperdev
 ```
 **Setup steps:**
 1. Install required libraries: pip install langchain serperdev
 1. Add API key to .env file: OPENAPI_API_KEY=your_api_key
 ## Key Files
 - `agent.py - Contains the LangGraph agent creation logic`
 - `tool_node.py - Defines the SerperDevTool node`
 ## Steps
 1. Step 1: Import necessary modules from langgraph and langchain libraries
 2. Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function with SerperDevTool as the tool node
 3. Step 3: Define the search query and pass it to the agent for fact gathering
 4. Step 4: Process the gathered facts within the AI agent
 ## Implementation Details
 ```python
 import langgraph
 from serperdev import SerperDevTool
 def create_agent(api_key, query):
    tool = SerperDevTool(api_key)
    agent = langgraph.create_react_agent(tool=tool)
    facts = agent.run(query)
    return process_facts(facts)
 ```
 ## Inputs
 - API Key for SerperDevTool
 - Search Query
 ## Outputs
 - Processed Facts
 ## Failure Modes
 - API Key not provided
 - Invalid Search Query
 ## Source
 Extracted from: [https://github.com/jkmaina/LangGraphProjects.git](https://github.com/jkmaina/LangGraphProjects.git)
 Confidence: 0.95
@@ -1,6 +0,0 @@
 # Commands: langgraph-workflow-creation
 ## Available Commands
 - `/skill langgraph-workflow-creation` — Load this skill
 - `/run langgraph-workflow-creation` — Execute workflow
@@ -1,10 +0,0 @@
 # Examples: langgraph-workflow-creation
 ## Usage Example
 ```python
 # How to use this skill
 # Inputs: API Key for SerperDevTool, Search Query
 # Process: Step 1: Import necessary modules from langgraph and langchain libraries → Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function with SerperDevTool as the tool node → Step 3: Define the search query and pass it to the agent for fact gathering
 # Outputs: Processed Facts
 ```
@@ -1,26 +0,0 @@
 {
  "name": "langgraph-workflow-creation",
  "version": "1.0.0",
  "goal": "Create a LangGraph workflow to gather facts using SerperDevTool and process them with an AI agent.",
  "inputs": [
    "API Key for SerperDevTool",
    "Search Query"
  ],
  "steps": [
    "Step 1: Import necessary modules from langgraph and langchain libraries",
    "Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function with SerperDevTool as the tool node",
    "Step 3: Define the search query and pass it to the agent for fact gathering",
    "Step 4: Process the gathered facts within the AI agent"
  ],
  "outputs": [
    "Processed Facts"
  ],
  "failure_modes": [
    "API Key not provided",
    "Invalid Search Query"
  ],
  "confidence": 0.95,
  "explanation": "This workflow is specific to fact gathering and can be adapted for different search queries or tools.",
  "source_repo": "https://github.com/jkmaina/LangGraphProjects.git",
  "score": 1.0
 }
@@ -1,9 +0,0 @@
 # Tests: langgraph-workflow-creation
 ## Test Checklist
 - [ ] Workflow has at least 3 steps
 - [ ] All inputs are defined
 - [ ] All outputs are defined
 - [ ] Failure modes are documented
 - [ ] Skill can be loaded without errors
@@ -1,94 +0,0 @@
 ---
 name: three-tier-evaluation-pipeline
 version: 1.0.0
 description: Run tasks through three evaluation tiers (Run, Trace, Thread) to produce
  comprehensive reports with human-in-the-loop validation
 inputs:
 - query/input text for the task
 - search results (for trace tier evaluation)
 - evaluation criteria and thresholds
 steps:
 - 'Step 1: Execute the main task using the Run tier of the evaluation pipeline (agentkit/runtime/LangGraph
  engine) to generate initial outputs and results'
 - 'Step 2: Run the Trace tier where an LLM-as-Judge evaluates the output against defined
  criteria, generating detailed analysis and scoring'
 - 'Step 3: Execute the Thread tier which facilitates human-in-the-loop discussion,
  approval, and iterative refinement of the output'
 outputs:
 - Final consolidated report combining results from all three tiers
 - Detailed scores and metrics per tier
 - Threaded discussion logs for human review and approval
 tags: []
 metadata:
  source_repo: https://github.com/itszhaoziyan-n/AgentKit.git
  extracted_at: ''
  confidence: 0.95
 ---
 # three-tier-evaluation-pipeline
 Run tasks through three evaluation tiers (Run, Trace, Thread) to produce comprehensive reports with human-in-the-loop validation
 ## Setup
 **Dependencies:**
 ```text
 pip install langgraph>=0.3 langchain-core>=0.3 langchain-anthropic>=0.3 langfuse>=2.0 mcp[server]>=1.24 tenacity>=9.0 fastapi>=0.115 psycopg[binary]>=3.1
 ```
 **Setup steps:**
 1. Install dependencies with pip install -e .[dev]
 1. Start infrastructure: docker compose up -d (PostgreSQL, Langfuse, MCP server)
 1. Configure environment variables (DATABASE_URL, MCP_API_KEY, etc.)
 1. Run the pipeline: python -m eval.runner --tiers run,thread,trace
 ## Key Files
 - `eval/ - contains the three-tier evaluation logic`
 - `scripts/ci_gate.py - threshold update and benchmark validation`
 - `agentkit/runtime/ - LangGraph engine for state management and graph execution`
 ## Steps
 1. Step 1: Execute the main task using the Run tier of the evaluation pipeline (agentkit/runtime/LangGraph engine) to generate initial outputs and results
 2. Step 2: Run the Trace tier where an LLM-as-Judge evaluates the output against defined criteria, generating detailed analysis and scoring
 3. Step 3: Execute the Thread tier which facilitates human-in-the-loop discussion, approval, and iterative refinement of the output
 ## Implementation Details
 ```python
 The eval/ directory implements Run, Trace, and Thread stages with configurable tiers
 ```
 ```python
 Benchmark suite (40 test cases) validates the pipeline's reliability
 ```
 ```python
 CI/CD workflows (ci.yml, eval-fast.yml, eval-trace.yml) orchestrate the evaluation pipeline
 ```
 ## Inputs
 - query/input text for the task
 - search results (for trace tier evaluation)
 - evaluation criteria and thresholds
 ## Outputs
 - Final consolidated report combining results from all three tiers
 - Detailed scores and metrics per tier
 - Threaded discussion logs for human review and approval
 ## Failure Modes
 - If the Run tier fails (e.g., code execution error), the pipeline can retry but may produce incomplete outputs
 - If the Trace tier LLM-as-Judge produces low-quality evaluations, the Thread tier may need additional human intervention
 - Threshold mismatches between tiers could cause the pipeline to exit early or require manual adjustment
 ## Source
 Extracted from: [https://github.com/itszhaoziyan-n/AgentKit.git](https://github.com/itszhaoziyan-n/AgentKit.git)
 Confidence: 0.95
@@ -1,6 +0,0 @@
 # Commands: three-tier-evaluation-pipeline
 ## Available Commands
 - `/skill three-tier-evaluation-pipeline` — Load this skill
 - `/run three-tier-evaluation-pipeline` — Execute workflow
@@ -1,10 +0,0 @@
 # Examples: three-tier-evaluation-pipeline
 ## Usage Example
 ```python
 # How to use this skill
 # Inputs: query/input text for the task, search results (for trace tier evaluation), evaluation criteria and thresholds
 # Process: Step 1: Execute the main task using the Run tier of the evaluation pipeline (agentkit/runtime/LangGraph engine) to generate initial outputs and results → Step 2: Run the Trace tier where an LLM-as-Judge evaluates the output against defined criteria, generating detailed analysis and scoring → Step 3: Execute the Thread tier which facilitates human-in-the-loop discussion, approval, and iterative refinement of the output
 # Outputs: Final consolidated report combining results from all three tiers, Detailed scores and metrics per tier, Threaded discussion logs for human review and approval
 ```
@@ -1,29 +0,0 @@
 {
  "name": "three-tier-evaluation-pipeline",
  "version": "1.0.0",
  "goal": "Run tasks through three evaluation tiers (Run, Trace, Thread) to produce comprehensive reports with human-in-the-loop validation",
  "inputs": [
    "query/input text for the task",
    "search results (for trace tier evaluation)",
    "evaluation criteria and thresholds"
  ],
  "steps": [
    "Step 1: Execute the main task using the Run tier of the evaluation pipeline (agentkit/runtime/LangGraph engine) to generate initial outputs and results",
    "Step 2: Run the Trace tier where an LLM-as-Judge evaluates the output against defined criteria, generating detailed analysis and scoring",
    "Step 3: Execute the Thread tier which facilitates human-in-the-loop discussion, approval, and iterative refinement of the output"
  ],
  "outputs": [
    "Final consolidated report combining results from all three tiers",
    "Detailed scores and metrics per tier",
    "Threaded discussion logs for human review and approval"
  ],
  "failure_modes": [
    "If the Run tier fails (e.g., code execution error), the pipeline can retry but may produce incomplete outputs",
    "If the Trace tier LLM-as-Judge produces low-quality evaluations, the Thread tier may need additional human intervention",
    "Threshold mismatches between tiers could cause the pipeline to exit early or require manual adjustment"
  ],
  "confidence": 0.95,
  "explanation": "The AgentKit repository contains a production-ready three-tier evaluation pipeline (Run \u2192 Trace \u2192 Thread) that can be adapted to any task requiring multi-stage validation. This workflow uses LangGraph for orchestration and LangChain for tool integration, making it portable across different agent engineering scenarios. The pattern is reusable because it separates concerns into distinct stages with clear inputs/outputs, allowing teams to plug in different evaluation criteria or human reviewers as needed.",
  "source_repo": "https://github.com/itszhaoziyan-n/AgentKit.git",
  "score": 1.0
 }
@@ -1,9 +0,0 @@
 # Tests: three-tier-evaluation-pipeline
 ## Test Checklist
 - [ ] Workflow has at least 3 steps
 - [ ] All inputs are defined
 - [ ] All outputs are defined
 - [ ] Failure modes are documented
 - [ ] Skill can be loaded without errors
@@ -1,96 +1,62 @@
 ---
 name: unifai-workflow-execution
 version: 1.0.0
-description: Execute a multi-agent workflow on the UnifAI platform using a specified
+description: Execute a multi-agent AI workflow defined in YAML or through the UI's
-  blueprint and user prompt.
+  drag-and-drop editor.
 inputs:
- blueprint_id or blueprint_name
+- name: blueprint_path
- user_shortcut
+  description: Path to the blueprint file (YAML) defining the multi-agent workflow.
- user_question
+- name: execution_mode
  description: 'Execution mode: ''local'' or ''distributed''.'
 steps:
- 'Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id
+- step_name: Load Blueprint
-  method)'
+  description: Parse and validate the blueprint file to ensure it conforms to expected
- 'Step 2: Create a new session from the blueprint (create_session method)'
+    structure.
- 'Step 3: Submit the session for background execution with the user prompt (submit_session
+- step_name: Initialize Execution Engine
-  method)'
+  description: Set up the execution engine based on the selected mode ('local' or
- 'Step 4: Poll session status until execution completes (poll_session_status method)'
+    '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.
 outputs:
- session_id
+- name: execution_results
- workflow_id
+  description: The output of the executed workflow, streamed as NDJSON over HTTP.
 tags: []
 metadata:
  source_repo: https://github.com/redhat-community-ai-tools/UnifAI.git
  extracted_at: ''
-  confidence: 0.95
+  confidence: 0.9
 ---
 # unifai-workflow-execution
-Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt.
+Execute a multi-agent AI workflow defined in YAML or through the UI's drag-and-drop editor.
 ## 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 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method)
+1. {'step_name': 'Load Blueprint', 'description': 'Parse and validate the blueprint file to ensure it conforms to expected structure.'}
-2. Step 2: Create a new session from the blueprint (create_session method)
+2. {'step_name': 'Initialize Execution Engine', 'description': "Set up the execution engine based on the selected mode ('local' or 'distributed')."}
-3. Step 3: Submit the session for background execution with the user prompt (submit_session method)
+3. {'step_name': 'Execute Workflow', 'description': 'Run the multi-agent workflow, streaming node-by-node output as NDJSON over HTTP.'}
-4. Step 4: Poll session status until execution completes (poll_session_status method)
+4. {'step_name': 'Stream Results', 'description': 'Render and stream results in real time to clients subscribing to the event stream.'}
 ## 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
- blueprint_id or blueprint_name
+- {'name': 'blueprint_path', 'description': 'Path to the blueprint file (YAML) defining the multi-agent workflow.'}
- user_shortcut
+- {'name': 'execution_mode', 'description': "Execution mode: 'local' or 'distributed'."}
 - user_question
 ## Outputs
- session_id
+- {'name': 'execution_results', 'description': 'The output of the executed workflow, streamed as NDJSON over HTTP.'}
 - workflow_id
 ## Failure Modes
- Blueprint name not found or not unique - error during blueprint resolution
+- {'mode_name': 'Invalid Blueprint', 'description': 'Blueprint file is not valid YAML or does not conform to expected structure.'}
- Session creation fails - error from API response
+- {'mode_name': 'Execution Engine Initialization Failure', 'description': 'Failed to initialize the execution engine due to configuration issues or missing dependencies.'}
 - 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: 0.95
+Confidence: 0.9
@@ -4,7 +4,7 @@
 ```python
 # How to use this skill
-# Inputs: blueprint_id or blueprint_name, user_shortcut, user_question
+# 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 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)
+# 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: session_id, workflow_id
+# Outputs: {'name': 'execution_results', 'description': 'The output of the executed workflow, streamed as NDJSON over HTTP.'}
 ```
@@ -1,30 +1,53 @@
 {
  "name": "unifai-workflow-execution",
  "version": "1.0.0",
-  "goal": "Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt.",
+  "goal": "Execute a multi-agent AI workflow defined in YAML or through the UI's drag-and-drop editor.",
  "inputs": [
-    "blueprint_id or blueprint_name",
+    {
-    "user_shortcut",
+      "name": "blueprint_path",
-    "user_question"
+      "description": "Path to the blueprint file (YAML) defining the multi-agent workflow."
    },
    {
      "name": "execution_mode",
      "description": "Execution mode: 'local' or 'distributed'."
    }
  ],
  "steps": [
-    "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_name": "Load Blueprint",
-    "Step 3: Submit the session for background execution with the user prompt (submit_session method)",
+      "description": "Parse and validate the blueprint file to ensure it conforms to expected structure."
-    "Step 4: Poll session status until execution completes (poll_session_status method)"
+    },
    {
      "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."
    }
  ],
  "outputs": [
-    "session_id",
+    {
-    "workflow_id"
+      "name": "execution_results",
      "description": "The output of the executed workflow, streamed as NDJSON over HTTP."
    }
  ],
  "failure_modes": [
-    "Blueprint name not found or not unique - error during blueprint resolution",
+    {
-    "Session creation fails - error from API response",
+      "mode_name": "Invalid Blueprint",
-    "Session submission fails - error from API response",
+      "description": "Blueprint file is not valid YAML or does not conform to expected structure."
-    "Polling session status fails - error from API response"
+    },
    {
      "mode_name": "Execution Engine Initialization Failure",
      "description": "Failed to initialize the execution engine due to configuration issues or missing dependencies."
    }
  ],
-  "confidence": 0.95,
+  "confidence": 0.9,
-  "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.",
+  "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.",
  "source_repo": "https://github.com/redhat-community-ai-tools/UnifAI.git",
  "score": 1.0
 }