O
omnigami-ai/skills
The omnigami catalogue: free and paid skills for Claude Code and other agents, each in its own repository
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
Client config (built from the install command this repo gives)
{
"mcpServers": {
"omnigami-ai-skills": {
"command": "npx",
"args": ["skills"]
}
}
}Parsed from the README we fetched on 2026-10-28; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"omnigami-ai-skills": {
"command": "npx",
"args": ["skills"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio omnigami-ai-skills -- npx skills
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 3 ★ · omnigami-ai/skills · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-10-28 · last seen 2026-11-14 · seen 19× · listed by 1 sources
- Score
- score 103 · 3 ★ · 1 sources · repo
- Install
npx skills
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
npx skills. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: Agent 技能. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
omnigami-ai/skills;first catalogued 2026-10-28;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# omnigami skills
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Agent Skills for Claude Code and other agents, starting with video. Each skill
teaches your agent one kind of work for your own product or project. The first
ones make videos from your real screens, words and colours: whole films and
single scenes, built in code and rendered to MP4, wide and tall (most also
square). Each brings a finished example, a style guide, a critique rubric and
the scripts to check its own work. Most are free; a few are paid, bought once
at omnigami.ai and shared with the buyer's GitHub account. This repository is
the catalogue; each skill is in its own. Watch every skill play live, and edit
it, at omnigami.ai.
Product film (omnigami-ai/product-film): Make a 34-second launch video for a product from its real screens, in five acts (the problem, the promise, four proof steps of the product in action, the result, the ask), with a big cursor, a moving camera, captions and sound, in square, wide and tall.
Cutout film (omnigami-ai/cutout-film, paid: $4.99 once, private to buyers): Make a 30–40 second launch film of a software product's real UI in a stepped, illustrated cutout style - 12 fps with every frame a new drawing and no motion blur, flat colour fields changed by hard cuts, the product's own screens redrawn large as vectors, an oversized leaning cursor, mock-3D cutout objects with thickness, an ink outline and a hard shadow, devices taken only from the product's own world, and room to read every beat.
Device film (omnigami-ai/device-film, paid: $7.99 once, private to buyers): Make a 40–48 second launch film of a software product's real screens on photoreal 3D devices (a laptop and a phone), with captions as their own shots centred on a light field with one word in the brand's colour, dark hardware large at strong angles that eases hard into place, a laptop that glides in and opens with its lid sweeping across the words, the real UI full frame, phones that spin into a lineup, cuts on the music's bar lines.
UI morph (omnigami-ai/ui-morph): Make a 16-second square UI-morph film of one real job in the user's product.
Chat launch (omnigami-ai/chat-launch): Make a 23-second chat-style launch video for a product in code, one continuous take at 130 BPM, on the product's real screens - a request typed into its own composer with a glow around it, the send flooding the screen and landing as the message, the product working one step a beat, a colour flood on the drop that bursts into its own result cards, the best one flying back into the chat, a click on its real action, and an outro where the button grows into the page and ends on the brand mark.
Unfold (omnigami-ai/unfold, paid: $4.99 once, private to buyers): Make a 27-second keynote-style launch video for a product in code, as one continuous take.
Language launch (omnigami-ai/language-launch): Make a 15-second announcement video that a product now speaks more languages, on its real screens - the headline " now speaks" over each language's own name, a carousel of the product's real screen, one phone per language, swiping one over as each name rolls in, each held long enough to read, then every phone flying into one row under the count, and the end card.
teaches your agent one kind of work for your own product or project. The first
ones make videos from your real screens, words and colours: whole films and
single scenes, built in code and rendered to MP4, wide and tall (most also
square). Each brings a finished example, a style guide, a critique rubric and
the scripts to check its own work. Most are free; a few are paid, bought once
at omnigami.ai and shared with the buyer's GitHub account. This repository is
the catalogue; each skill is in its own. Watch every skill play live, and edit
it, at omnigami.ai.
Product film (omnigami-ai/product-film): Make a 34-second launch video for a product from its real screens, in five acts (the problem, the promise, four proof steps of the product in action, the result, the ask), with a big cursor, a moving camera, captions and sound, in square, wide and tall.
Cutout film (omnigami-ai/cutout-film, paid: $4.99 once, private to buyers): Make a 30–40 second launch film of a software product's real UI in a stepped, illustrated cutout style - 12 fps with every frame a new drawing and no motion blur, flat colour fields changed by hard cuts, the product's own screens redrawn large as vectors, an oversized leaning cursor, mock-3D cutout objects with thickness, an ink outline and a hard shadow, devices taken only from the product's own world, and room to read every beat.
Device film (omnigami-ai/device-film, paid: $7.99 once, private to buyers): Make a 40–48 second launch film of a software product's real screens on photoreal 3D devices (a laptop and a phone), with captions as their own shots centred on a light field with one word in the brand's colour, dark hardware large at strong angles that eases hard into place, a laptop that glides in and opens with its lid sweeping across the words, the real UI full frame, phones that spin into a lineup, cuts on the music's bar lines.
UI morph (omnigami-ai/ui-morph): Make a 16-second square UI-morph film of one real job in the user's product.
Chat launch (omnigami-ai/chat-launch): Make a 23-second chat-style launch video for a product in code, one continuous take at 130 BPM, on the product's real screens - a request typed into its own composer with a glow around it, the send flooding the screen and landing as the message, the product working one step a beat, a colour flood on the drop that bursts into its own result cards, the best one flying back into the chat, a click on its real action, and an outro where the button grows into the page and ends on the brand mark.
Unfold (omnigami-ai/unfold, paid: $4.99 once, private to buyers): Make a 27-second keynote-style launch video for a product in code, as one continuous take.
Language launch (omnigami-ai/language-launch): Make a 15-second announcement video that a product now speaks more languages, on its real screens - the headline " now speaks" over each language's own name, a carousel of the product's real screen, one phone per language, swiping one over as each name rolls in, each held long enough to read, then every phone flying into one row under the count, and the end card.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/omnigami-ai-skills/)
- Source
- github · https://github.com/omnigami-ai/skills
- Browse by field
- Agent skills
- Traction
- 3 ★
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.