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

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

name	version	description	inputs	steps	outputs	tags	metadata
code-review-agent	1.0.0	Automate code review process using a multi-step workflow with human-in-the-loop approval.	Repository diff or code changeset (string) User ID (string)	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	Review result (dictionary containing messages, issues, etc.)		source_repo extracted_at confidence https://github.com/itszhaoziyan-n/AgentKit.git 0.95

code-review-agent

Automate 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

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 - 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

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 Confidence: 0.95