google-agents-cli-scaffold
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
ca-django-linters
ALWAYS use this skill proactively for Consumer Affairs Django repositories (located in ../ca/ directory) when ANY of these occur - (1) After writing or modifying ANY Python code files in CA repos (2) After tests pass and before telling user work is complete (3) User mentions linting, formatting, ...
Full skill instructions
This skill runs code formatters and linters on Consumer Affairs repositories to ensure code quality and style compliance before commits.
AUTOMATIC ACTIVATION TRIGGERS - Activate this skill immediately when:
CRITICAL WORKFLOW RULE:
🚨 NEVER tell the user "implementation is complete" or "work is done" UNTIL you have:
This skill should ALWAYS run automatically after code changes and BEFORE declaring work complete.
CRITICAL: This skill should run AFTER:
DO NOT tell the user implementation is complete until:
Run these two commands in order:
ca exec ruff format --config pyproject.toml .
This command:
ca exec ruff check --fix --config pyproject.toml .
This command:
--fix flag)ca exec (PREFERRED)ca exec ruff format --config pyproject.toml .
ca exec ruff check --fix --config pyproject.toml .
This is the preferred method - it uses containers that are already running.
ca bash then run commandsca bash
# Inside container:
ruff format --config pyproject.toml .
ruff check --fix --config pyproject.toml .
Use this if ca exec doesn't work for some reason.
docker compose run - this starts a separate containerca script - it uses already running containersMany errors are automatically fixed by ruff:
After running ruff check --fix, these will be corrected automatically.
Some errors require manual intervention:
Undefined names / unused variables
# Before
def my_function(arg1, arg2):
return arg1 # arg2 is unused
# After
def my_function(arg1, arg2):
_ = arg2 # Explicitly mark as unused
return arg1
Line too long
# Before
result = some_function(very_long_argument_1, very_long_argument_2, very_long_argument_3)
# After
result = some_function(
very_long_argument_1,
very_long_argument_2,
very_long_argument_3
)
Missing docstrings
# Before
def complex_function(data):
return process(data)
# After
def complex_function(data):
"""Process data and return result."""
return process(data)
Complexity issues (too many branches)
--fix)When user asks to "implement a new authentication feature":
Implement the feature - write the code
Write tests - use the ca-django-tests skill
Run tests - ensure they pass with ca magictest
Run linters - use this skill:
ca exec ruff format --config pyproject.toml .
ca exec ruff check --fix --config pyproject.toml .
Fix any linting errors that require manual intervention
Re-run linters to confirm all issues are resolved
Verify tests still pass after code formatting changes
Tell the user the implementation is complete and ready
Before telling the user work is complete:
Sometimes you need to ignore a specific rule for a line:
# noqa: E501 - ignore line too long
very_long_line_that_cannot_be_broken = "some value" # noqa: E501
The pyproject.toml contains ruff configuration:
Do not modify these without discussing with the team.
Error: Imports are incorrectly sorted
Solution: Run ruff check --fix - it will auto-fix import order
Error: `UserModel` imported but unused
Solution: Remove the import or use it in the code
Error: Line too long (120 > 88 characters)
Solution: Break the line into multiple lines
Error: Missing docstring in public function
Solution: Add a docstring explaining what the function does
✅ Always run linters before telling user work is complete
✅ Run both ruff format and ruff check --fix
✅ Fix all errors before finishing
✅ Use ca exec for running linters
✅ Verify tests still pass after formatting
✅ Clean code = ready for commit
✅ Don't modify pyproject.toml without discussion
✅ Fix errors in files you modified first
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.
Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.
Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.
Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.
Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.
Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.