Sithu Aung sithu

# Claude Skill: Airflow → Temporal Migration Assistant (Python)

## Summary
A semi-automated migration skill that converts an Apache Airflow DAG (Python) into a **Temporal Python SDK** workflow + activities **safely**, producing:
- a migration plan
- generated scaffolding code (workflow/activity stubs + typed interfaces)
- test skeletons (replay/golden)
- a checklist for determinism, retries, idempotency, and scheduling

Leveraging Gemini CLI + LangGraph + Terraform + GitHub PR automation is a solid pattern that can scale across many developer productivity use cases. Here's how you can apply this architecture to other scenarios, broken down by common workflows, efficiency gains, and tailored examples:

🔁 Generalized Pattern (Your Current Flow):

Input intent (natural language) →
Agent interprets and formulates prompt →
Gemini CLI modifies code/config →
PR created with reasoning trace →

To use a browser with Google Agent Developer Kit (ADK) to scrape a Tableau report, you’ll typically need to combine:

Google ADK (to receive and interpret the natural language intent),
A headless browser (like Puppeteer or Playwright),
And possibly an MCP server or tool plugin to expose scraping functionality to the agent.

✅ Example Workflow: Google ADK + Puppeteer + MCP Server

Hello World

	from sklearn.datasets import make_blobs
	import matplotlib.pyplot as plt
	from sklearn.cluster import KMeans
	import numpy as np
	from matplotlib import cm
	from sklearn.metrics import silhouette_samples
	import pandas as pd
	from scipy.spatial.distance import pdist, squareform
	from scipy.cluster.hierarchy import linkage
	from scipy.cluster.hierarchy import dendrogram

	import pandas as pd
	import numpy as np
	from matplotlib import pyplot as plt
	import utils

	from sklearn.tree import DecisionTreeClassifier
	from sklearn import tree

	np.random.seed(0)

	import numpy as np
	from matplotlib import pyplot

	# Some functions to plot our points and draw the lines
	def plot_points(features, labels, fix_margins=True):
	X = np.array(features)
	y = np.array(labels)
	spam = X[np.argwhere(y==1)]
	ham = X[np.argwhere(y==0)]
	if fix_margins:

	import pandas as pd
	import numpy as np
	from matplotlib import pyplot

	# Some functions to plot our points and draw the lines
	def plot_points(features, labels):
	X = np.array(features)
	y = np.array(labels)
	spam = X[np.argwhere(y==1)]
	ham = X[np.argwhere(y==0)]

	# Loading the one_circle dataset
	# ploy_svm.csv: https://gist.github.com/sithu/1a3c2dfbca74540fb2ee5a1aca1c4a0f
	circular_data = pd.read_csv('poly_svm.csv')
	features = np.array(circular_data[['x_1', 'x_2']])
	labels = np.array(circular_data['y'])
	utils.plot_points(features, labels)

	# TODO: Degree = 2 vs Degree = 4
	# Which one gives better accuracy?
	svm_degree_2 = SVC(kernel='poly', degree=2)

	description: Change BigQuery table permission
	group: cli_gcp_qb
	cmd: gsutil [table_name] [service_account]