Add Skill: agent-builder-workflow

Extracted from: https://github.com/pipeshub-ai/pipeshub-ai.git
Score: 1.0

skills/agent-builder-workflow/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: agent-builder-workflow
+version: 1.0.0
+description: Build no-code AI agents that connect to enterprise knowledge sources,
+  perform unified search and deep research, and generate explainable answers with
+  citations
+inputs:
+- Task description and agent objectives (e.g., answer Q&A, research specific topics,
+  generate reports)
+- Knowledge sources (documents, databases, enterprise systems) to connect to
+- Retrieval strategy configuration (graph-based knowledge graph vs. vector search)
+- Output requirements (citation format, response structure, code execution needs)
+steps:
+- 'Step 1: Define agent task and objectives - Specify what the agent should do (e.g.,
+  answer a question, perform deep research on a topic, generate a report with citations)'
+- 'Step 2: Configure knowledge sources - Connect to enterprise documents, databases,
+  or external systems that will serve as the agent''s context'
+- 'Step 3: Build LangGraph chain - Create a workflow chain using LangGraph that combines
+  retrieval (graph/vector) and LLM response generation with citation capabilities'
+- 'Step 4: Execute agent - Run the LangGraph chain to process the task and generate
+  responses with grounded citations'
+- 'Step 5: (Optional) Code execution sandbox - If the agent needs to generate or execute
+  code, deploy it to a safe sandbox environment for verification'
+outputs:
+- Agent execution logs showing retrieval steps and LLM responses
+- Grounded answers with block citations to source documents
+- Generated reports or artifacts (if code execution was performed)
+- Structured task completion status and results
+tags: []
+metadata:
+  source_repo: https://github.com/pipeshub-ai/pipeshub-ai.git
+  extracted_at: ''
+  confidence: 0.95
+---
+
+# agent-builder-workflow
+
+Build no-code AI agents that connect to enterprise knowledge sources, perform unified search and deep research, and generate explainable answers with citations
+
+## Setup
+
+**Dependencies:**
+
+```text
+pip install langchain langgraph serper-dev-tool qdrant-client redis fastapi pydantic
+```
+
+**Setup steps:**
+
+1. Install dependencies: pip install langchain langgraph serper-dev-tool qdrant-client redis fastapi
+1. Configure knowledge sources in .env (graph DB connection, vector DB, document paths)
+1. Define agent task in agent_builder.py with objectives and retrieval strategy
+1. Run agent chain: python agent_chain.py --task "research_quantum_computing"
+1. For code execution: add sandbox step to agent_chain.py with code generation and safe execution
+
+## Key Files
+
+- `pipeshub-ai/backend/agent_chain.py - LangGraph chain definition for agent workflows`
+- `pipeshub-ai/backend/retrieval_pipeline.py - Knowledge graph and vector search implementation`
+- `pipeshub-ai/workflows/agent_builder.py - No-code agent creation interface`
+- `pipeshub-ai/workflows/citation_generator.py - Block citation generation from retrieved sources`
+
+## Steps
+
+1. Step 1: Define agent task and objectives - Specify what the agent should do (e.g., answer a question, perform deep research on a topic, generate a report with citations)
+2. Step 2: Configure knowledge sources - Connect to enterprise documents, databases, or external systems that will serve as the agent's context
+3. Step 3: Build LangGraph chain - Create a workflow chain using LangGraph that combines retrieval (graph/vector) and LLM response generation with citation capabilities
+4. Step 4: Execute agent - Run the LangGraph chain to process the task and generate responses with grounded citations
+5. Step 5: (Optional) Code execution sandbox - If the agent needs to generate or execute code, deploy it to a safe sandbox environment for verification
+
+## Implementation Details
+
+```python
+LangGraph chain with retrieval (graph/vector) and LLM response stages
+```
+
+```python
+Knowledge graph construction from enterprise documents
+```
+
+```python
+Citation formatting using block references to source documents
+```
+
+## Inputs
+
+- Task description and agent objectives (e.g., answer Q&A, research specific topics, generate reports)
+- Knowledge sources (documents, databases, enterprise systems) to connect to
+- Retrieval strategy configuration (graph-based knowledge graph vs. vector search)
+- Output requirements (citation format, response structure, code execution needs)
+
+## Outputs
+
+- Agent execution logs showing retrieval steps and LLM responses
+- Grounded answers with block citations to source documents
+- Generated reports or artifacts (if code execution was performed)
+- Structured task completion status and results
+
+## Failure Modes
+
+- Insufficient retrieval results due to poor knowledge graph connectivity or vector embedding quality
+- Permission errors when accessing enterprise knowledge sources
+- LLM context window overflow when generating long explanations with citations
+- Sandbox execution failures for code generation or execution tasks
+- Timeout errors during multi-step agent chain execution
+
+## Source
+
+Extracted from: [https://github.com/pipeshub-ai/pipeshub-ai.git](https://github.com/pipeshub-ai/pipeshub-ai.git)
+Confidence: 0.95

skills/agent-builder-workflow/commands.md

@@ -0,0 +1,6 @@
+# Commands: agent-builder-workflow
+
+## Available Commands
+
+- `/skill agent-builder-workflow` — Load this skill
+- `/run agent-builder-workflow` — Execute workflow

skills/agent-builder-workflow/examples.md

@@ -0,0 +1,10 @@
+# Examples: agent-builder-workflow
+
+## Usage Example
+
+```python
+# How to use this skill
+# Inputs: Task description and agent objectives (e.g., answer Q&A, research specific topics, generate reports), Knowledge sources (documents, databases, enterprise systems) to connect to, Retrieval strategy configuration (graph-based knowledge graph vs. vector search), Output requirements (citation format, response structure, code execution needs)
+# Process: Step 1: Define agent task and objectives - Specify what the agent should do (e.g., answer a question, perform deep research on a topic, generate a report with citations) → Step 2: Configure knowledge sources - Connect to enterprise documents, databases, or external systems that will serve as the agent's context → Step 3: Build LangGraph chain - Create a workflow chain using LangGraph that combines retrieval (graph/vector) and LLM response generation with citation capabilities
+# Outputs: Agent execution logs showing retrieval steps and LLM responses, Grounded answers with block citations to source documents, Generated reports or artifacts (if code execution was performed), Structured task completion status and results
+```

skills/agent-builder-workflow/metadata.json

@@ -0,0 +1,35 @@
+{
+  "name": "agent-builder-workflow",
+  "version": "1.0.0",
+  "goal": "Build no-code AI agents that connect to enterprise knowledge sources, perform unified search and deep research, and generate explainable answers with citations",
+  "inputs": [
+    "Task description and agent objectives (e.g., answer Q&A, research specific topics, generate reports)",
+    "Knowledge sources (documents, databases, enterprise systems) to connect to",
+    "Retrieval strategy configuration (graph-based knowledge graph vs. vector search)",
+    "Output requirements (citation format, response structure, code execution needs)"
+  ],
+  "steps": [
+    "Step 1: Define agent task and objectives - Specify what the agent should do (e.g., answer a question, perform deep research on a topic, generate a report with citations)",
+    "Step 2: Configure knowledge sources - Connect to enterprise documents, databases, or external systems that will serve as the agent's context",
+    "Step 3: Build LangGraph chain - Create a workflow chain using LangGraph that combines retrieval (graph/vector) and LLM response generation with citation capabilities",
+    "Step 4: Execute agent - Run the LangGraph chain to process the task and generate responses with grounded citations",
+    "Step 5: (Optional) Code execution sandbox - If the agent needs to generate or execute code, deploy it to a safe sandbox environment for verification"
+  ],
+  "outputs": [
+    "Agent execution logs showing retrieval steps and LLM responses",
+    "Grounded answers with block citations to source documents",
+    "Generated reports or artifacts (if code execution was performed)",
+    "Structured task completion status and results"
+  ],
+  "failure_modes": [
+    "Insufficient retrieval results due to poor knowledge graph connectivity or vector embedding quality",
+    "Permission errors when accessing enterprise knowledge sources",
+    "LLM context window overflow when generating long explanations with citations",
+    "Sandbox execution failures for code generation or execution tasks",
+    "Timeout errors during multi-step agent chain execution"
+  ],
+  "confidence": 0.95,
+  "explanation": "PipesHub provides a reusable agent builder workflow that combines LangGraph orchestration with graph-based and vector-based retrieval. This pattern can be adapted to any enterprise context where AI agents need to search across multiple knowledge sources, generate explainable answers with citations, and optionally execute code in a safe sandbox. The workflow is defined by specific configuration files (LangGraph chain definitions) and follows a standard pattern: task definition \u2192 knowledge source connection \u2192 retrieval strategy \u2192 response generation \u2192 optional code sandbox.",
+  "source_repo": "https://github.com/pipeshub-ai/pipeshub-ai.git",
+  "score": 1.0
+}

skills/agent-builder-workflow/tests.md

@@ -1,4 +1,4 @@
-# Tests: graph-based-node-workflow
+# Tests: agent-builder-workflow
 
 ## Test Checklist
 

skills/graph-based-node-workflow/SKILL.md

@@ -1,100 +0,0 @@
----
-name: graph-based-node-workflow
-version: 1.0.0
-description: Create and execute typed node graphs for AI/robotics workflows by defining
-  nodes with inputs/outputs and connecting them with edges, then cooking the graph
-  to run the workflow.
-inputs:
-- bn.Graph() - the graph container for the workflow
-- Node definitions (Literal, Text, LLMAgent, Concat, Output, etc.) with specified
-  inputs and outputs
-- Edge connections mapping from_port to to_port between nodes
-steps:
-- 'Step 1: Initialize a bn.Graph() instance to serve as the workflow container'
-- 'Step 2: Define individual nodes with their required inputs and outputs (e.g., Literal
-  for data, LLMAgent for inference, Concat for combining, Output for final results)'
-- 'Step 3: Create edges connecting nodes by specifying source from_port and destination
-  to_port for each data flow'
-- 'Step 4: Execute the graph by calling g.cook() to process the defined workflow and
-  produce results'
-outputs:
-- Executed workflow results stored in the graph's output nodes
-- Cooked graph ready for inspection, replay, or deployment
-- Potential error states if node dependencies are missing or ports don't match
-tags: []
-metadata:
-  source_repo: https://github.com/temiroff/Blacknode.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# graph-based-node-workflow
-
-Create and execute typed node graphs for AI/robotics workflows by defining nodes with inputs/outputs and connecting them with edges, then cooking the graph to run the workflow.
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install blacknode (core Python package) anthropic, openai, docker, petgraph (dependencies) Rust extensions in blacknode-core, blacknode-runtime (optional)
-```
-
-**Setup steps:**
-
-1. Install blacknode with Python 3.11+ and required dependencies
-1. Clone repository and navigate to project directory
-1. Run examples/converted_text_pipeline.py to see basic graph execution
-1. Modify node definitions and edges to create custom workflows
-
-## Key Files
-
-- `examples/converted_text_pipeline.py - basic pipeline pattern`
-- `examples/hello_agent.py - LLM agent workflow pattern`
-- `examples/research_pipeline.py - multi-node research workflow`
-- `blacknode.py - main CLI entry point`
-
-## Steps
-
-1. Step 1: Initialize a bn.Graph() instance to serve as the workflow container
-2. Step 2: Define individual nodes with their required inputs and outputs (e.g., Literal for data, LLMAgent for inference, Concat for combining, Output for final results)
-3. Step 3: Create edges connecting nodes by specifying source from_port and destination to_port for each data flow
-4. Step 4: Execute the graph by calling g.cook() to process the defined workflow and produce results
-
-## Implementation Details
-
-```python
-g = bn.Graph()
-```
-
-```python
-g._edges = [{"from": "model", "from_port": "value", "to": "agent", "to_port": "model"}]
-```
-
-```python
-result = g.cook(output, "value")
-```
-
-## Inputs
-
-- bn.Graph() - the graph container for the workflow
-- Node definitions (Literal, Text, LLMAgent, Concat, Output, etc.) with specified inputs and outputs
-- Edge connections mapping from_port to to_port between nodes
-
-## Outputs
-
-- Executed workflow results stored in the graph's output nodes
-- Cooked graph ready for inspection, replay, or deployment
-- Potential error states if node dependencies are missing or ports don't match
-
-## Failure Modes
-
-- Missing node dependencies causing undefined variable errors
-- Port mismatch in edge connections leading to no data flow
-- Incomplete graph definition causing cook() to fail
-- Model API key missing or invalid for LLMAgent nodes
-
-## Source
-
-Extracted from: [https://github.com/temiroff/Blacknode.git](https://github.com/temiroff/Blacknode.git)
-Confidence: 0.95

skills/graph-based-node-workflow/commands.md

@@ -1,6 +0,0 @@
-# Commands: graph-based-node-workflow
-
-## Available Commands
-
-- `/skill graph-based-node-workflow` — Load this skill
-- `/run graph-based-node-workflow` — Execute workflow

skills/graph-based-node-workflow/examples.md

@@ -1,10 +0,0 @@
-# Examples: graph-based-node-workflow
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: bn.Graph() - the graph container for the workflow, Node definitions (Literal, Text, LLMAgent, Concat, Output, etc.) with specified inputs and outputs, Edge connections mapping from_port to to_port between nodes
-# Process: Step 1: Initialize a bn.Graph() instance to serve as the workflow container → Step 2: Define individual nodes with their required inputs and outputs (e.g., Literal for data, LLMAgent for inference, Concat for combining, Output for final results) → Step 3: Create edges connecting nodes by specifying source from_port and destination to_port for each data flow
-# Outputs: Executed workflow results stored in the graph's output nodes, Cooked graph ready for inspection, replay, or deployment, Potential error states if node dependencies are missing or ports don't match
-```

skills/graph-based-node-workflow/metadata.json

@@ -1,31 +0,0 @@
-{
-  "name": "graph-based-node-workflow",
-  "version": "1.0.0",
-  "goal": "Create and execute typed node graphs for AI/robotics workflows by defining nodes with inputs/outputs and connecting them with edges, then cooking the graph to run the workflow.",
-  "inputs": [
-    "bn.Graph() - the graph container for the workflow",
-    "Node definitions (Literal, Text, LLMAgent, Concat, Output, etc.) with specified inputs and outputs",
-    "Edge connections mapping from_port to to_port between nodes"
-  ],
-  "steps": [
-    "Step 1: Initialize a bn.Graph() instance to serve as the workflow container",
-    "Step 2: Define individual nodes with their required inputs and outputs (e.g., Literal for data, LLMAgent for inference, Concat for combining, Output for final results)",
-    "Step 3: Create edges connecting nodes by specifying source from_port and destination to_port for each data flow",
-    "Step 4: Execute the graph by calling g.cook() to process the defined workflow and produce results"
-  ],
-  "outputs": [
-    "Executed workflow results stored in the graph's output nodes",
-    "Cooked graph ready for inspection, replay, or deployment",
-    "Potential error states if node dependencies are missing or ports don't match"
-  ],
-  "failure_modes": [
-    "Missing node dependencies causing undefined variable errors",
-    "Port mismatch in edge connections leading to no data flow",
-    "Incomplete graph definition causing cook() to fail",
-    "Model API key missing or invalid for LLMAgent nodes"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow pattern is reusable across different AI/robotics applications because it provides a standardized way to compose complex pipelines from typed nodes. The pattern can be adapted to various use cases like research pipelines, agent workflows, or robotics control graphs by simply adding/removing nodes and edges while maintaining the same graph-cooking execution model.",
-  "source_repo": "https://github.com/temiroff/Blacknode.git",
-  "score": 1.0
-}