Agent Skills by Patty
Showing 83 vetted skills indexed across 1 GitHub repositories.
yuanbao
Send @mentions, direct messages, and query member info in Yuanbao groups.
hermes-desktop-plugins
Write JavaScript ESM plugins that add UI panes and commands to the Hermes desktop app.
computer-use
Drives desktop applications via background clicking, typing, and scrolling without stealing cursor focus.
dogfood
Tests web applications via browser automation and generates structured bug reports with screenshots.
apple-apps
Automate Apple Notes, Reminders, iMessage, FindMy, and Calendar on macOS via CLIs and osascript.
macos-computer-use
Drive the macOS desktop with background screenshots, clicks, typing, and scrolling via the computer_use tool.
blogwatcher
Monitor blogs and RSS/Atom feeds using the blogwatcher-cli command-line tool.
polymarket
Query Polymarket prediction markets for prices, orderbooks, and price history via public REST APIs.
llm-wiki
Build and maintain an interlinked markdown knowledge base from ingested sources.
research-paper-writing
Guides end-to-end ML research paper production from experiment design through conference submission.
minecraft-modpack-server
Configures and hosts modded Minecraft servers from CurseForge and Modrinth server packs.
pokemon-player
Plays Pokemon games via headless PyBoy emulation with RAM state reads and screenshot verification.
xurl
Post, search, and manage X/Twitter content via the official xurl CLI.
cua-driver
Automates native macOS apps via accessibility-tree snapshots and element-indexed clicks without stealing focus.
kanban-worker
Guides Hermes Kanban workers through task lifecycle pitfalls, handoffs, and retry diagnostics.
kanban-orchestrator
Decompose goals into Kanban task graphs routed to specialist agent profiles.
stable-daily-log
Reviews daily agent sessions and writes structured Obsidian daily log entries.
macos-launchd-service
Configure persistent macOS services with launchd watchdogs and Colima containerized datastores.
cron-briefing-script
Build scheduled multi-source briefing scripts delivered via Hermes cron in no_agent mode.
document-to-dataset-pipeline
Build labeled ML datasets from emailed PDF reports and spreadsheet labels, then validate a classifier.
jupyter-live-kernel
Execute stateful Python code through a live Jupyter kernel via the hamelnb CLI.
hermes-s6-container-supervision
Modify and debug the s6-overlay supervision tree inside the Hermes Agent Docker image.
android-app-development
Scaffold and build native Android apps with Kotlin and Jetpack Compose from the command line.
test-driven-development
Enforces red-green-refactor TDD workflow with failing tests before production code.
Frequently Asked Questions About Patty
FAQPage SchemaWhat tasks can I accomplish with patty-chow's skill registry?▼
You can serve and quantize local models (vLLM, llama.cpp), benchmark them (lm-evaluation-harness), manage GitHub repos and PRs, drive macOS/Windows/Linux desktops via computer-use, generate media with ComfyUI and Manim, and integrate Notion, Linear, Airtable, Spotify, and Google Workspace.
Who is the target audience for these skills?▼
ML engineers running local inference and evaluations, developers enforcing TDD and code-review discipline, Hermes Agent operators configuring gateways and cron briefings, and creative coders building generative art, infographics, and ASCII or pixel-art media.
How do I install and run these skills?▼
Skills load inside the Hermes Agent runtime on Linux, macOS, or Windows. Some require prerequisite binaries (blogwatcher-cli, himalaya, openhue, xurl), Python dependencies (torch, transformers, dspy), or credential files such as Google OAuth tokens and API keys.
Are these skills open source and free to use?▼
Nearly all skills carry the MIT license, including vLLM serving, DSPy, ComfyUI, and the GitHub suite. One exception is the PowerPoint skill, which is proprietary with terms defined in its bundled LICENSE.txt file.
What prerequisites or dependencies are required?▼
Dependencies vary: ML skills need torch, transformers, and vllm; ComfyUI needs python3 and comfy-cli; Strava and Linear require API keys or OAuth tokens; Teams pipeline needs Microsoft Graph credentials; desktop control skills require the computer_use tool capability.