DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to create a reusable Skill from a chat request with Muse Lite

Use the built-in Skill Creator to turn a repeated task into a skill the Agent can call on demand.

Who it is forA user who repeats the same kind of AI task, such as turning meeting notes into action items, and wants it packaged once.

The problemRe-explaining the same workflow in every chat wastes time and produces uneven results.

The outcomeA new enabled skill directory exists in the workspace, and the Agent uses it for matching requests.

What you need first

  • Windows x86-64 PC with Python 3.13 for the provided build script
  • Internet access for the first build to download Briefcase, the Android SDK, Gradle, and Maven dependencies
  • Android 11+ arm64 device or emulator
  • An OpenAI-compatible HTTPS provider base URL, model ID, and API key

Steps

  1. Open Settings > Skill to confirm Skill Creator is enabled; it is installed and enabled on first use.
  2. In a conversation, ask: "Create a skill that turns meeting notes into decisions and action items."
  3. Wait for the Agent to report the new skill directory and confirm it is enabled.
  4. Paste sample meeting notes and invoke the skill explicitly with $skill-name using the name the Agent created.
  5. Open Settings > Skill, select the new skill, and review its SKILL.md; fix the YAML name and description if a save is rejected.

Prompt for your agent

In the yxq953/MuseLite app, ask the Agent to create a skill that turns <task description> into a structured output. Expected output: a skill directory under /var/muselite/workspace/skills with a valid SKILL.md. Verify that the YAML name matches the directory name and that the skill is enabled.

Caveat. Skills only supplement the request and do not grant new tools or permissions, and Linux scripts in a skill run only on Android through the shell sandbox.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page