diff --git a/skills/code-review-agent/SKILL.md b/skills/code-review-agent/SKILL.md
new file mode 100644
index 0000000..292360c
--- /dev/null
+++ b/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
diff --git a/skills/code-review-agent/commands.md b/skills/code-review-agent/commands.md
new file mode 100644
index 0000000..d7e5fb1
--- /dev/null
+++ b/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
diff --git a/skills/code-review-agent/examples.md b/skills/code-review-agent/examples.md
new file mode 100644
index 0000000..e41d98c
--- /dev/null
+++ b/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.)
+```
diff --git a/skills/code-review-agent/metadata.json b/skills/code-review-agent/metadata.json
new file mode 100644
index 0000000..655d49d
--- /dev/null
+++ b/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
+}
\ No newline at end of file
diff --git a/skills/code-review-agent/tests.md b/skills/code-review-agent/tests.md
new file mode 100644
index 0000000..24de42f
--- /dev/null
+++ b/skills/code-review-agent/tests.md
@@ -0,0 +1,9 @@
+# Tests: code-review-agent
+
+## 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