agent-skills/skills/code-review-agent-workflow/SKILL.md

name, version, description, inputs, steps, outputs, tags, metadata

name	version	description	inputs	steps	outputs	tags	metadata
code-review-agent-workflow	1.0.0	Automate the code review process using a multi-step workflow with human-in-the-loop approval.	Sample diff of code changes (str) Repo context (dict)	Step 1: Build the graph for the code review agent using `build_graph()` from `agentkit.workflow.code_review.graph` Step 2: Invoke the graph with initial parameters including sample diff, repo context, user ID, and other metadata Step 3: The graph processes the input through a series of steps, generating messages and issues as it progresses	Final result containing processed messages and issues (dict)		source_repo extracted_at confidence https://github.com/itszhaoziyan-n/AgentKit.git 0.95

code-review-agent-workflow

Automate the code review process using a multi-step workflow with human-in-the-loop approval.

Setup

Dependencies:

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 fastapi>=0.115 uvicorn[standard]>=0.32 psycopg[binary]>=3.1 langgraph-checkpoint-postgres>=2.0 httpx>=0.27 python-dotenv>=1.0 redis>=5.0

Setup steps:

1. cp .env.example .env
2. docker compose up -d
3. pip install -e '.[dev]'

Key Files

• agentkit/workflow/code_review/graph.py - Contains the build_graph function and graph invocation logic.
• examples/run_code_review.py - Example script demonstrating how to run the code review agent.

Steps

1. Step 1: Build the graph for the code review agent using build_graph() from agentkit.workflow.code_review.graph
2. Step 2: Invoke the graph with initial parameters including sample diff, repo context, user ID, and other metadata
3. Step 3: The graph processes the input through a series of steps, generating messages and issues as it progresses

Implementation Details

graph = build_graph()
thread_id = str(uuid.uuid4())
result = graph.invoke(...)

Inputs

• Sample diff of code changes (str)
• Repo context (dict)

Outputs

• Final result containing processed messages and issues (dict)

Failure Modes

• Specific failure scenario with mitigation: If the build_graph() function fails to initialize properly, ensure all required dependencies are correctly installed.

Source

Extracted from: https://github.com/itszhaoziyan-n/AgentKit.git Confidence: 0.95