agentleFS
tjmodetjmode/koovi/skills/settings/SKILL.md

settings

Skill1 starsChanged 21 days agoMITView on GitHub

See Koovi's main switches and change them by clicking. On or off, voice or screen light, quiet during calls, wait for research.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use help.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    help

    Entry point for the MedImageInsight plugin, covering the getting-started walkthrough, how the skills work, what MI2 is, and troubleshooting.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If it prints a line starting with ERROR, show that line to the user and stop.

    line 14
  2. Distinctive:

    Ask once, with the AskUserQuestion tool, all four questions in one call.

    line 16
  3. Distinctive:

    Write each option's description in plain words, as given in brackets above.

    line 27
  4. Distinctive:

    Leave alone every answer that matches the current value.

    line 33
  5. Very specific:

    If the AskUserQuestion tool is not available, show what step 1 printed, then the /koovi:set line that changes each switch (for example …

    line 40

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Show the user Koovi's main switches and change the ones they pick. Do nothing else.

  1. Run this command:

    ${CLAUDE_PLUGIN_ROOT}/koovi.sh settings

    If it prints a line starting with ERROR, show that line to the user and stop.

  2. Ask once, with the AskUserQuestion tool, all four questions in one call. In each question put the option that matches the current value first and add " (now)" to its label. Use these questions, headers and options, in this order:

    QuestionHeaderOptions, with the value each one sets
    Koovi on or off?Koovi"On" sets enabled true; "Off" sets enabled false (never speaks or flashes)
    How should Koovi reach you?Reach"Voice" sets mode voice (speaks out loud); "Screen light" sets mode quiet (a coloured frame flashes, no sound); "Auto" sets mode auto (speaks on headphones, flashes on speakers)
    Stay quiet while the microphone is in use, in calls and dictation?Calls"Stay quiet" sets wait_for_mic true; "May talk" sets wait_for_mic false
    Wait for research agents to finish before saying done?Research"Wait" sets wait_for_agents true; "Don't wait" sets wait_for_agents false

    Write each option's description in plain words, as given in brackets above.

  3. For every answer that differs from the current value, run:

    ${CLAUDE_PLUGIN_ROOT}/koovi.sh set KEY VALUE

    Leave alone every answer that matches the current value. If the user typed their own answer, use it only when it clearly means one of the options; otherwise leave that setting alone.

  4. Reply in one or two plain sentences: what changed, or that nothing changed. Then add this line: /koovi:mute silences this project, /koovi:test plays a sample line. On a Mac the same switches are in the Koovi icon in the menu bar.

If the AskUserQuestion tool is not available, show what step 1 printed, then the /koovi:set line that changes each switch (for example /koovi:set enabled false), and stop.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.