Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Migrate Python applications from LiteLLM to Portkey AI Gateway. Covers litellm.completion, Router, Proxy, fallbacks, caching, retries, callbacks, embeddings, and image generation. Use when the user wants to replace LiteLLM with Portkey or switch from LiteLLM to Portkey.
Complete reference for the Portkey AI Gateway Python SDK with unified API access to 200+ LLMs, automatic fallbacks, caching, and full observability. Use when building Python applications that need LLM integration with production-grade reliability.
Use when writing Python code that imports from inkbox, uses pip install inkbox, or when adding email, phone, or agent identity features using the Inkbox Python SDK.
Standardize Python function docstrings to a team format with a short summary, optional second-paragraph logic notes, optional Args/Returns sections. Default coding style uses four-space indentation and an object-oriented design mindset. Use when adding or normalizing docstrings in Python files, including class methods…
Add a new module / CLI command / service function / loader the way this Python codebase already does it. Use when building a public surface, a command entry point, a data loader, a validator, or a new package module in a Python / uv repo. Finds the one canonical example and mirrors its layering, typing, error model…
House conventions for writing code in a Django codebase: formatter and linter compliance (black, isort, djlint, flake8), imports at module top with real refactors for circular imports, docstrings over comment blocks, maintained libraries over hand-rolled code, full test coverage as a merge gate, N+1 queries caught at…
Handle the mechanics of a summonpot pull request: changelog fragments, stacked branches, restacking after a squash-merged parent, verifying no tests were lost, and reading review comments already addressed. Use when opening, updating, rebasing, or landing a pull request.
Review a summonpot change for the defects this codebase actually produces: docs claiming unshipped behaviour, guards that reject valid code, failures raised too late, tests that pass for the wrong reason, and internal detail leaking into responses. Use before opening a pull request or when reviewing a diff.
Provision and verify this uv-managed Python project using mise and uv. Use when asked to install dependencies, bootstrap the pinned Python toolchain, sync the lockfile environment, and confirm tests pass with pytest in this repository.
Scaffolding and setting up Python applications, FastAPI APIs, FastMCP servers, and project structures in this workspace. ALWAYS trigger this skill whenever the user mentions creating a new Python project, setting up a Python service, scaffolding FastAPI/FastMCP, initializing a Python app from scratch, or asking for…
FastAPI best practices and conventions. Use when working with FastAPI APIs and Pydantic models for them. Keeps FastAPI code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.
Subagent skill for making changes to the FastAPI backend. Use when the task involves editing Python files in backend/, running backend tests, modifying the Dockerfile, or changing backend configuration.
★not rated 2 5mo agoA41 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: