Add Skill: code-review-agent

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

skills/agent-creation-and-management/SKILL.md

@@ -1,73 +0,0 @@
----
-name: agent-creation-and-management
-version: 1.0.0
-description: Create and manage workplace AI agents using PipesHub's no-code agent
-  builder.
-inputs:
-- Agent name with description
-- Action to perform (e.g., 'Gather facts about a company')
-steps:
-- 'Step 1: Open the PipesHub UI at http://localhost:3000'
-- 'Step 2: Navigate to the Agents section and click on ''Create Agent'''
-- 'Step 3: Enter the agent name and description in the form'
-- 'Step 4: Define the actions for the agent, such as ''Gather facts about a company'',
-  using PipesHub''s no-code interface'
-- 'Step 5: Save and deploy the agent'
-outputs:
-- Agent created and deployed
-- Access URL for the new agent
-tags: []
-metadata:
-  source_repo: https://github.com/pipeshub-ai/pipeshub-ai.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# agent-creation-and-management
-
-Create and manage workplace AI agents using PipesHub's no-code agent builder.
-
-## Setup
-
-**Setup steps:**
-
-1. Ensure Docker and Compose are installed
-1. Clone the repository: git clone https://github.com/pipeshub-ai/pipeshub-ai.git
-1. Run the installer: ./install.sh
-
-## Key Files
-
-- `N/A - Workflow implemented via UI`
-
-## Steps
-
-1. Step 1: Open the PipesHub UI at http://localhost:3000
-2. Step 2: Navigate to the Agents section and click on 'Create Agent'
-3. Step 3: Enter the agent name and description in the form
-4. Step 4: Define the actions for the agent, such as 'Gather facts about a company', using PipesHub's no-code interface
-5. Step 5: Save and deploy the agent
-
-## Implementation Details
-
-```python
-N/A - Workflow implemented via UI
-```
-
-## Inputs
-
-- Agent name with description
-- Action to perform (e.g., 'Gather facts about a company')
-
-## Outputs
-
-- Agent created and deployed
-- Access URL for the new agent
-
-## Failure Modes
-
-- If the agent creation fails due to missing required fields, ensure all necessary details are provided correctly
-
-## Source
-
-Extracted from: [https://github.com/pipeshub-ai/pipeshub-ai.git](https://github.com/pipeshub-ai/pipeshub-ai.git)
-Confidence: 0.95

skills/agent-creation-and-management/commands.md

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

skills/agent-creation-and-management/examples.md

@@ -1,10 +0,0 @@
-# Examples: agent-creation-and-management
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: Agent name with description, Action to perform (e.g., 'Gather facts about a company')
-# Process: Step 1: Open the PipesHub UI at http://localhost:3000 → Step 2: Navigate to the Agents section and click on 'Create Agent' → Step 3: Enter the agent name and description in the form
-# Outputs: Agent created and deployed, Access URL for the new agent
-```

skills/agent-creation-and-management/metadata.json

@@ -1,27 +0,0 @@
-{
-  "name": "agent-creation-and-management",
-  "version": "1.0.0",
-  "goal": "Create and manage workplace AI agents using PipesHub's no-code agent builder.",
-  "inputs": [
-    "Agent name with description",
-    "Action to perform (e.g., 'Gather facts about a company')"
-  ],
-  "steps": [
-    "Step 1: Open the PipesHub UI at http://localhost:3000",
-    "Step 2: Navigate to the Agents section and click on 'Create Agent'",
-    "Step 3: Enter the agent name and description in the form",
-    "Step 4: Define the actions for the agent, such as 'Gather facts about a company', using PipesHub's no-code interface",
-    "Step 5: Save and deploy the agent"
-  ],
-  "outputs": [
-    "Agent created and deployed",
-    "Access URL for the new agent"
-  ],
-  "failure_modes": [
-    "If the agent creation fails due to missing required fields, ensure all necessary details are provided correctly"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow is specific but can be adapted for different agents and actions within PipesHub's platform.",
-  "source_repo": "https://github.com/pipeshub-ai/pipeshub-ai.git",
-  "score": 1.0
-}

skills/code-review-agent/SKILL.md

@@ -0,0 +1,76 @@
+---
+name: code-review-agent
+version: 1.0.0
+description: Automate code review process using a multi-step workflow with human-in-the-loop
+  approval.
+inputs:
+- Repository diff or code changeset (string)
+- User ID (string)
+steps:
+- 'Step 1: Build the code review graph using `build_graph()` from `agentkit.workflow.code_review.graph`'
+- 'Step 2: Invoke the graph with initial parameters including the repository diff
+  and user ID, and set thread_id as a configurable parameter'
+- 'Step 3: The graph processes the input through various steps until completion or
+  human approval is needed'
+outputs:
+- Review result (dictionary containing messages, issues, etc.)
+tags: []
+metadata:
+  source_repo: https://github.com/itszhaoziyan-n/AgentKit.git
+  extracted_at: ''
+  confidence: 0.95
+---
+
+# code-review-agent
+
+Automate code review process using a multi-step workflow with human-in-the-loop approval.
+
+## Setup
+
+**Dependencies:**
+
+```text
+pip install langgraph>=0.3 langchain-core>=0.3 langchain-anthropic>=0.3 langfuse>=2.0 mcp[server]>=1.24,<2.0 langchain-mcp-adapters>=0.1 tenacity>=9.0
+```
+
+**Setup steps:**
+
+1. cp .env.example .env
+1. docker compose up -d
+1. pip install -e '.[dev]'
+
+## Key Files
+
+- `agentkit/workflow/code_review/graph.py - Defines the code review graph and its invocation method.`
+
+## Steps
+
+1. Step 1: Build the code review graph using `build_graph()` from `agentkit.workflow.code_review.graph`
+2. Step 2: Invoke the graph with initial parameters including the repository diff and user ID, and set thread_id as a configurable parameter
+3. Step 3: The graph processes the input through various steps until completion or human approval is needed
+
+## Implementation Details
+
+```python
+graph = build_graph()
+thread_id = str(uuid.uuid4())
+result = graph.invoke(...)
+```
+
+## Inputs
+
+- Repository diff or code changeset (string)
+- User ID (string)
+
+## Outputs
+
+- Review result (dictionary containing messages, issues, etc.)
+
+## Failure Modes
+
+- Specific failure scenario with mitigation: If the graph invocation fails due to an unexpected state, it will halt and require manual intervention.
+
+## Source
+
+Extracted from: [https://github.com/itszhaoziyan-n/AgentKit.git](https://github.com/itszhaoziyan-n/AgentKit.git)
+Confidence: 0.95

skills/code-review-agent/commands.md

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

skills/code-review-agent/examples.md

@@ -0,0 +1,10 @@
+# Examples: code-review-agent
+
+## Usage Example
+
+```python
+# How to use this skill
+# Inputs: Repository diff or code changeset (string), User ID (string)
+# Process: Step 1: Build the code review graph using `build_graph()` from `agentkit.workflow.code_review.graph` → Step 2: Invoke the graph with initial parameters including the repository diff and user ID, and set thread_id as a configurable parameter → Step 3: The graph processes the input through various steps until completion or human approval is needed
+# Outputs: Review result (dictionary containing messages, issues, etc.)
+```

skills/code-review-agent/metadata.json

@@ -0,0 +1,24 @@
+{
+  "name": "code-review-agent",
+  "version": "1.0.0",
+  "goal": "Automate code review process using a multi-step workflow with human-in-the-loop approval.",
+  "inputs": [
+    "Repository diff or code changeset (string)",
+    "User ID (string)"
+  ],
+  "steps": [
+    "Step 1: Build the code review graph using `build_graph()` from `agentkit.workflow.code_review.graph`",
+    "Step 2: Invoke the graph with initial parameters including the repository diff and user ID, and set thread_id as a configurable parameter",
+    "Step 3: The graph processes the input through various steps until completion or human approval is needed"
+  ],
+  "outputs": [
+    "Review result (dictionary containing messages, issues, etc.)"
+  ],
+  "failure_modes": [
+    "Specific failure scenario with mitigation: If the graph invocation fails due to an unexpected state, it will halt and require manual intervention."
+  ],
+  "confidence": 0.95,
+  "explanation": "This workflow is reusable for any code review process that requires a multi-step analysis with human-in-the-loop approval.",
+  "source_repo": "https://github.com/itszhaoziyan-n/AgentKit.git",
+  "score": 1.0
+}

skills/code-review-agent/tests.md

@@ -1,4 +1,4 @@
-# Tests: agent-creation-and-management
+# Tests: code-review-agent
 
 ## Test Checklist