stvlynn/skills
Thirteen agent skills: stickers, speech synthesis and recognition, SearXNG search, Atlassian design and Claude Code operation.
- 58 ★ on the repository
- Last commit
Broad access
Why this level
- Some skills drive the desktop, spawn Claude Code and install a network proxy client, so each skill should be reviewed on its own
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/stvlynn-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Some skills drive the desktop, spawn Claude Code and install a network proxy client, so each skill should be reviewed on its own
This is third-party code. Review the repository files before installing.
What it does
A collection of modular agent skills installed one at a time: `npx skills add stvlynn/skills --skill create-sticker`. Media covers `create-sticker` (LINE-style stickers with background removal via Gemini), `pv-tool` (a kinetic typography app for lyric videos) and `tsticker` (Telegram sticker packs). Speech has `qwen-tts` with nine voices and `qwen-asr`, both built for Apple Silicon and MLX. For search and data there are `searxng` over 70-plus engines through Docker and `xiaohongshu`. Interfaces include `atlassian-design` and `scroll-fade-mask`, writing and docs has `product-doc-writing-spec`, and developer tools hold `claude-code-operator`, `tip-gui-skill` and `clashctl-linux`. A command with the `--list` flag shows the contents before installing.
Who it is for. People picking individual skills for Claude Code and Codex by task: stickers, speech, private search or a design system reference.
Good fit when
- A Telegram sticker set is needed from a ready character image
- Lines must be voiced locally on a Mac with voices and emotion
- An agent needs private web search through its own SearXNG instance
- A React interface is built in a Jira style following Atlaskit rules
Not a fit when
- One coordinated set for a whole team is needed, since the skills are independent and installed one by one
- Work is not on an Apple Silicon Mac, which the speech skills target
- Skills with support and a compatibility promise are needed, while one author maintains the repository
Example request
List the skills in stvlynn/skills and install create-sticker to make a sticker set from this drawing.Limitations
The skills are independent and each has its own requirements: `create-sticker` needs `GEMINI_API_KEY`, `tsticker` a Telegram bot token, `qwen-tts` and `qwen-asr` an Apple Silicon computer with MLX, `searxng` Docker and `xiaohongshu` the xiaohongshu-mcp service. `tip-gui-skill` drives the desktop through Youtu-Tip on macOS, and `clashctl-linux` installs and configures a Clash or Mihomo proxy client from a vendored copy of a third-party project, with compliance with local rules resting on you. The repository is small and one author maintains it.
How to disable. Delete the folder of the skill from the agent skills directory. For a global install through `npx skills` use the same manager, and remove keys and tokens from the environment.
FAQ
How do I install all the skills at once?
Run `npx skills add stvlynn/skills --skill='*' -g`. For one skill give its name in `--skill`.
What do I need for speech?
An Apple Silicon computer with MLX. `qwen-tts` gives nine voices and emotion control, and `qwen-asr` recognizes speech through a local FastAPI service.
Is a key needed for stickers?
For `create-sticker` yes, `GEMINI_API_KEY`. Managing Telegram packs through `tsticker` needs a bot token.
What does the search skill do?
`searxng` searches through 70-plus engines and works with your own Docker instance, so queries do not go to a single provider.
Is there Russian documentation?
The repository has READMEs in English and Chinese and no Russian version.
Discussion
No questions or reviews yet.
Related
Skillscafe3310's personal skill collection: spec-driven project work, reviews, reports, browser, 3D and video in one repository
18 portable skills for work where AI is weakest: messy voice input, message tone, small trend tests and safe shipping.
AGT Skill Pack gives an agent 24 free skills: review by another model, idea screening, UI checks and decision tracking
Twenty-two standalone skills: Notion, Todoist, Tavily, Context7, image generation, converting documents to Markdown
A set of everyday agent skills: web search, browser automation, Gmail, Google Calendar and Drive, speech transcription and YouTube transcripts
Seven skills for research, HTML explainers and source citation, installable all at once or one at a time through npx.
README in short
The repository is grouped by theme: media, speech, search, interfaces, writing and developer tools. Each skill is installed separately and has its own requirements.