Describe your edit to an agent to trim videos, add music, subtitles, or crops — no timeline or GUI. Install two skills, then editing is done by conversation.
This skill sketches 2–3 interactive, disposable HTML mockups of a UI idea so you can compare design directions side-by-side before committing to one, then presents an opinionated head-to-head comparison.
Structure song lyrics with rhyme, meter and dynamic contrast, then describe the intended emotional journey in a style field so AI music generation follows your performance map.
The public Autonovel repo runs a Hermes-driven pipeline that generated, reviewed, illustrated, type-set in LaTeX, and voiced a complete 19-chapter novel, House of Bells, as an audiobook.
Create Excalidraw diagrams by writing element JSON saved as .excalidraw files, which can be viewed or edited on excalidraw.com or uploaded there for shareable links without an account.
Edit a specific page of a PDF with a natural-language instruction using the nano-pdf CLI.
Generate spectrograms and multi-panel audio feature visualizations from audio files using the songsee command-line tool.
Set up a multi-agent content pipeline inside Discord: a research agent finds trending topics, a writing agent drafts scripts, and a thumbnail agent generates images, each in its own channel, running automatically on a schedule.
An agent chain that turns an episode topic into research, an outline, timestamped show notes, descriptions, and social media promo posts.
Give Hermes a raw screen recording and it generates the tutorial script, produces the finished video on HeyGen with your AI avatar, and saves your preferences in memory for follow-up videos.
Search and download GIFs directly through the Tenor API using curl, with no extra tools needed.
Rewrite technical text following ASD-STE100 Simplified Technical English, the controlled language used in aerospace and defense maintenance documentation, with a check mode that audits existing text for STE compliance and reports each violation with a compliant rewrite.
Turn a photo of handwritten letters into an installable TTF font: the user does the seeing (finding and labeling letters, judging quality) while the CLI handles all geometry such as tracing, metrics and font assembly, without editing SVG paths manually.
Hermes writes HTML video compositions with Open Design and renders them to finished MP4 files through HyperFrames, using Chrome headless plus FFmpeg instead of a timeline editor.
No use cases found