Skip to content
Skills Library
AI & agents · Planning

protocol-setup-options

/protocol-setup-options

Use when the owner wants to choose which AI to set up on a machine that has a stored analysis. It reads that analysis, asks the owner closed questions, build the options with code's filters and explain each one.

Licence
Apache-2.0
Last repository change
04.11.2026

Assessment and security

85/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content20 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 04.11.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Use when the owner wants to choose which AI to set up on a machine that has a stored analysis. It reads that analysis, asks the owner closed questions, build the options with code's filters and explain each one.

Original author description

Use when the owner wants to choose which AI to set up on a machine that has a stored analysis. It reads that analysis, asks the owner closed questions, build the options with code's filters and explain each one.

How it works

  1. One step
  2. Language
Original SKILL.md headings · 13 lines, 187 words
SKILL.md preview
---
name: protocol-setup-options
description: Use when the owner wants to choose which AI to set up on a machine that has a stored analysis. It reads that analysis, asks the owner closed questions, build the options with code's filters and explain each one.
---

# Choosing which AI to set up (a harness run on the coordinator)

Start only for a machine whose analysis is stored (the coordinator refuses otherwise). You do not probe the machine again: `load_analysis` reads what the analysis found.

Each turn you choose ONE action from the menu. The owner's questions are closed (their ids and options come from `references/questions.json`, never from you). Ask which AI the owner wants (`which_ai`), and which CLI, which API provider or the sensitivity when it matters. Code builds the options with fixed filters and a fixed order (`build_options`); you explain EACH option in plain words (`explain_option`): why it is there and what limits it. You do not rank them. The owner picks.

## One step
`options` has two exits. `done` needs every option explained; `no_options` needs the fact that no option survived the filters. `build_options` and `explain_option` close the step when an exit's evidence is in. Nothing is installed.

## Language
The owner reads English. Write every sentence meant for the owner (an explanation, a finding, a reason) in English, in plain words. Names, ids and numbers stay as they are.
Files in this package (3)
  • SKILL.md 1 KB
  • skill.meta.json 2 KB
  • references/questions.json 1 KB

Versions

The database has no other skills named protocol-setup-options.

Database snapshot: 13.11.2026 · package version d76e8222a555 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 85setup-options
    Use when options for which AI to use on a machine have to be built from what the machine has, with hard filters and a written ordering that no model can change.
  • 85protocol-connect-chats
    Use when the owner asks to connect a chat host to Multi Auto Setup. Code finds which hosts are on this computer, the owner chooses, code builds the plan from the recipes, and each step is approved by the owner.
  • 100run
    Run the agent-config eval suite locally and compare with the stored baseline; explain why a case went red. Use when the user says "run the evals", "run config-drift-checker", "did the Claude Code update break my setup", "why is the eval red", or "compare against baseline". Do…
  • 100a2ui-ask
    When the user must choose among options or fill in structured config, spawn a browser form (powered by schemaui Web UI, bound to 0.0.0.0), open the user's browser, and write the result to .schemaui/answers/. Never use a terminal/TUI prompt — the agent process has no TTY…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.