696 skills · sorted by relevance
Delegate code changes and multi-step development tasks to OpenHands CLI using a model supported by LiteLLM, a connection layer for model providers. Run tasks without an interactive interface, inspect progress events, and resume previous conversations.
Create a presenter video from a topic or script and an authorized adult image. Generate narration, check lip sync, add captions, and export loudness-normalized master and sharing versions with technical and visual review reports.
Investigate Python bugs by pausing execution, inspecting variables, and stepping through code. Choose pdb for local inspection or debugpy for remote connections, with guidance for failing tests, crash analysis, and already running processes.
Guide an AI coding agent through frontend design work using 23 subcommands and examples of design patterns to avoid. A separate command-line detector checks 61 fixed rules without requiring an LLM or an API key.
Generate complete songs locally from lyrics and tags describing mood, instruments, or genre. The skill guides setup, input formatting, memory-saving settings, and MP3 output using the open-source HeartMuLa music models.
Create an interactive isometric map of a system’s architecture, with clickable structures and inspectable data flows. Generate matching text documentation from the same data file and track design decisions and open questions across review rounds.
Have an agent join Google Meet, collect live captions, and use the transcript for summaries and follow-up tasks. An optional voice mode lets it speak during calls after additional audio setup.
Build or refine a 3D scene by comparing live screenshots with a target image. This skill repeatedly evaluates composition, lighting, materials, and detail, then guides revisions while checking that rendering speed remains acceptable for the target platform.
Create animated explanations of mathematical concepts, equation derivations, and algorithms with Manim Community Edition. The skill guides scene planning, Python animation code, rendering, and clip assembly into a finished explainer video.
Inspect a codebase with pygount to measure code lines, file counts, language composition, and comment ratios. Exclude dependency folders, focus on selected languages, and get summaries or file-level results for understanding project size.
Search X posts, publish updates, reply, send direct messages, and upload media through the official xurl command line tool. Retrieve post IDs and text, check timelines, and work across multiple apps or accounts.
Set up and operate Hermes Agent across terminal, desktop, and messaging interfaces. This guide covers model configuration, themes, extensions, and coordination of independent agent instances, with references for task-specific settings and troubleshooting.
Turn audio files into spectrograms, images showing frequencies over time, and charts of loudness, pitch, tempo, and other features. Combine several views in one image or visualize a selected time segment for comparison.
Search and update Notion pages and databases, read or write Markdown, and upload files through the API or ntn CLI. Also build Workers, programs hosted by Notion, for scheduled syncing, agent tools, and incoming events.
Search, read, create, and edit notes in an Obsidian vault, the folder that stores your notes. Add content to existing Markdown files and connect related notes with Obsidian links.
Convert videos and images into colored character art, or create animations that react to music. Add lyrics or text, combine visual effects across scenes, and export the result as MP4, GIF, or image sequences.
Automate clicks, typing, scrolling, and dragging in desktop apps through Hermes. The skill starts with background actions that preserve the user's focus, checks results, and switches interaction methods when an action fails.
Convert Markdown files into formatted PDFs with page numbers, controlled page breaks, optional covers, clickable contents, and watermarks. Render diagrams and local images within the document, preview the layout, or export to HTML and Word.
Review Paperclip interface changes using Storybook, a catalog of component examples, alongside production source and existing browser tests. Report rendering, interaction, visual comparison, and production evidence separately, making simulated behavior and untested areas clear.
Start and repair isolated Paperclip development workspaces through managed services. Restore a full database clone when needed, then verify login, populated data, health, service visibility, and whether the process using the port belongs to the intended workspace.
Work with Jira issues through Orca's command-line interface. Search issues, move them through workflow states, create follow-up issues, and record completion with a PR or MR link and a comment using guidance matched to the installed Orca version.
Coordinate multiple Orca workers by assigning tasks, exchanging threaded messages, and waiting for results or escalations. Use task dependency graphs and decision gates to supervise work that needs ongoing coordination across agents.
Manage Linear issues through Orca’s command-line interface. Find tickets, move them through workflow states, create follow-up tickets linked to a parent, and record completion with a PR/MR link and a comment.
Set up an ESP32-S3/C6 sensing node for RuView by choosing firmware, checking and flashing binaries, and configuring WiFi and capture settings. Use boot logs to confirm CSI, measurements of the WiFi channel, is being captured.