Open source alternatives to graphic-overlays
24 open source AI Skills apps to use instead, best rated first.
Top picks
- G
github-ops
Launchgithub-ops is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It manages a GitHub repository with a focus on community health, CI reliability and the experience of contributors. It covers triaging issues by classify
Open source
- O
opensource-pipeline
Launchopensource-pipeline is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It prepares a private project for safe public release through a three-stage pipeline. The fork stage strips secrets from a copy. The sanitise st
Open source
- A
andrej-karpathy-skills
Launchandrej-karpathy-skills is a single CLAUDE.md file from the multica-ai project that is meant to improve how Claude Code behaves on coding tasks. It is derived from Andrej Karpathy's public observations about LLM coding pitfalls. The file dis
Open source
- M
microsoft/markitdown
Launchmarkitdown-mcp is the MCP server package for MarkItDown, Microsoft's tool for converting many file formats to Markdown for language models. It is a lightweight server that runs over stdio, Streamable HTTP or SSE, and exposes one tool, conve
Open source
- O
od-contribute
Launchod-contribute is an agent skill in the OpenDesign project that provides a guided, one-click contribution flow to the OpenDesign repository, written so that people without a coding background can send a real pull request. It is locked to the
Open source
- G
github-deep-research
Launchgithub-deep-research is an agent skill from the DeerFlow project that researches a single GitHub repository in several rounds and writes a report in Markdown. It is for requests that need more than a README summary, such as a comprehensive
Open source
More AI Skills apps
modelcontextprotocol/server-memory
Knowledge graph-based persistent memory for maintaining context
netdata/netdata#Netdata
Discovery, exploration, reporting and root cause analysis over Netdata metrics
Learn Claude Code
by shareAI-lab - A really interesting analysis of how coding agents like Claude
About graphic-overlays
graphic-overlays
Package an existing talking-head / interview / podcast video by layering timed
graphic-overlays is an agent skill from HeyGen's HyperFrames project that packages an existing talking-head, interview or podcast video by layering timed, designed graphic cards on top of it. The video plays in full, and the cards are timed to what is being said: titles, lower-thirds, data callouts, quotes, side panels and picture-in-picture. The agent designs each card's timing and content, writes the card HTML in the conversation, assembles a single composition, and renders it to MP4 with HyperFrames. There is no fixed list of card types, so the overlays come from what the transcript says. The skill sets a routing rule first. If the user wants plain captions or subtitles, the request goes to a captions skill, and if it is a single short element, such as one logo sting or lower-third, it goes to a motion graphics skill. The clip itself plays untouched, so re-timing, recoloring, reframing, reordering and audio editing are out of scope and belong to an editor. A request to build a video from a URL, a topic or a pull request goes to the creation workflows. It is a graphic-packaging sibling of the embedded captions skill, which adds the spoken words as a readable subtitle. It suits creators who have a recording and want on-screen graphics added to it. It passes Gen Agent Trust Hub, Socket and Snyk on skills.sh, and has about 29,100 installs. Install it with npx skills add https://github.com/heygen-com/hyperframes --skill graphic-overlays.
- Price
- Free
- Made by
- heygen-com
- Category
- AI Skills
- Website
- github.com/heygen-com/hyperframes/graphic-overlays