Add Skill: three-tier-evaluation-pipeline

Extracted from: https://github.com/itszhaoziyan-n/AgentKit.git
Score: 1.0

config/settings.yaml

@@ -34,8 +34,8 @@ scout:
     - 'rag agent workflow'
     - 'tool calling workflow'
   filters:
-    stars_min: 15
-    pushed_after: 2026-05-01
+    stars_min: 10
+    pushed_after: 2026-02-01
     language: Python
     archived: false
     size_max_kb: 10000

skills/langgraph-workflow-creation/SKILL.md

@@ -0,0 +1,83 @@
+---
+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

skills/langgraph-workflow-creation/commands.md

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

skills/langgraph-workflow-creation/examples.md

@@ -0,0 +1,10 @@
+# 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
+```

skills/langgraph-workflow-creation/metadata.json

@@ -0,0 +1,26 @@
+{
+  "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
+}

skills/langgraph-workflow-creation/tests.md

@@ -0,0 +1,9 @@
+# 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

skills/three-tier-evaluation-pipeline/SKILL.md

@@ -0,0 +1,94 @@
+---
+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

skills/three-tier-evaluation-pipeline/commands.md

@@ -0,0 +1,6 @@
+# Commands: three-tier-evaluation-pipeline
+
+## Available Commands
+
+- `/skill three-tier-evaluation-pipeline` — Load this skill
+- `/run three-tier-evaluation-pipeline` — Execute workflow

skills/three-tier-evaluation-pipeline/examples.md

@@ -0,0 +1,10 @@
+# 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
+```

skills/three-tier-evaluation-pipeline/metadata.json

@@ -0,0 +1,29 @@
+{
+  "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
+}

skills/three-tier-evaluation-pipeline/tests.md

@@ -0,0 +1,9 @@
+# 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