Skip to content
Skills Library
AI & agents · Automation

setup

/setup

Guided onboarding for nullius in this repo — detects test frameworks to propose Oracle config, offers the GitHub Action CI check, and walks through enabling the hook plugin. Use when a user asks to set up, install, enable, configure, or onboard nullius, or asks what nullius needs to be fully working here.

Repository
nullius ↗
Licence
MIT
Last repository change
07.09.2026

Assessment and security

100/ 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.
Content35 / 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
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 07.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Guided onboarding for nullius in this repo — detects test frameworks to propose Oracle config, offers the GitHub Action CI check, and walks through enabling the hook plugin. Use when a user asks to set up, install, enable, configure, or onboard nullius, or asks what nullius needs to be fully working here.

Original author description

Guided onboarding for nullius in this repo — detects test frameworks to propose Oracle config, offers the GitHub Action CI check, and walks through enabling the hook plugin. Use when a user asks to set up, install, enable, configure, or onboard nullius, or asks what nullius needs to be fully working here.

How it works

  1. 1. See what's already there
  2. 2. Confirm the profile
  3. 3. Propose Oracle globs — never write from a guess
  4. 4. Offer the GitHub Action
  5. 5. Write it
  6. 6. Hand off the one step you cannot do
  7. 7. Close with a real diagnostic, not a claim
Original SKILL.md headings · 121 lines, 805 words
SKILL.md preview
---
name: setup
description: Guided onboarding for nullius in this repo — detects test frameworks to propose Oracle config, offers the GitHub Action CI check, and walks through enabling the hook plugin. Use when a user asks to set up, install, enable, configure, or onboard nullius, or asks what nullius needs to be fully working here.
allowed-tools: Bash(npx -y @nullius-inverba/kit:*), Bash(npx nullius-kit:*), Bash(nullius-kit:*)
---

# nullius setup — guided onboarding

You are walking a human through onboarding nullius in this repository,
conversationally. Every actual read and write goes through the nullius kit
CLI via the `Bash` tool — this skill's `allowed-tools` frontmatter does not
grant you `Write` or `Edit`, so you have no way to touch
`.claude/settings.json` or any other file directly, even if you wanted to.
That is deliberate: **you propose and relay; the CLI is what decides and
writes.** If at any point completing a step seems to require writing a file
yourself, stop and tell the human what step is blocked and why, rather than
finding another way to write it — the two commands at the very end of this
skill are the only thing that ever installs hooks, and they are commands you
hand to the human, never something you run for them.

Do not use `init --interactive` in this skill. It opens a terminal prompt
UI that assumes a human is typing directly into a TTY; run through a `Bash`
tool call, its stdin is not a TTY, and it will just fall back to defaults
silently. Everything below drives the same underlying flow through explicit
flags instead — the flag surface a human's TTY session also answers into,
just supplied directly.

## 1. See what's already there

Run:

```
npx -y @nullius-inverba/kit doctor
```

Read the report. If nullius has never been set up here, most checks will
report absence rather than failure — that's expected, not an error. Tell the
human in one or two sentences what state you found, then continue.

## 2. Confirm the profile

Run:

```
npx -y @nullius-inverba/kit init --root . --dry-run
```

This prints the detected profile (`plans`, `prs`, or `specs`) and every file
it would write, without writing anything. Tell the human which profile was
detected and why (the tool prints its reason), and ask if they want a
different one — if so, everything below takes `--profile <name>` the same
way.

## 3. Propose Oracle globs — never write from a guess

Run:

```
npx -y @nullius-inverba/kit init --root . --suggest-oracle
```

This is read-only: it prints candidate globs (or says none were detected)
and touches nothing. Present whatever it printed to the human as a proposal,
in your own words — do not just paste the raw output. Ask them to accept,
edit, or decline:

- **Accept as proposed** → carry the printed globs forward to step 5 exactly
  as printed.
- **Edit** → ask what they'd rather declare, and carry their answer forward
  instead. It still has to be a comma-separated list of non-empty globs; the
  `init` command in step 5 will reject anything else itself, so you do not
  need to validate it yourself beyond checking it is not blank.
- **Decline / nothing detected and they don't want to type one** → carry no
  Oracle answer forward at all. Do not invent a placeholder glob to fill the
  gap — an unconfigured Oracle is a legitimate, reported state, not a defect
  to paper over.

## 4. Offer the GitHub Action

Ask the human, in your own words: "Add the nullius GitHub Action CI check to
this repo?" If the profile from step 2 already includes it (`prs` and
`specs` do; only `plans` doesn't), say so and skip the question — there is
nothing to add.

## 5. Write it

Run exactly one of, depending on what was decided above (omit `--oracle` if
step 3 ended in no answer; omit `--action` if step 4 ended in no or was
skipped):

```
npx -y @nullius-inverba/kit init --root . [--profile <name>] [--oracle "<glob>[,<glob>...]"] [--action]
```

Report the command's own output back to the human — the write-log it prints
is the source of truth for what happened, not your summary of your intent.

## 6. Hand off the one step you cannot do

Tell the human, plainly, that hooks are delivered only by the Claude Code
plugin and that this is the one step nothing in this skill — or anything
else — can perform on their behalf. If step 1's `doctor` output showed the
plugin is not yet enabled, give them exactly these two lines to run
themselves:

```
/plugin marketplace add armanfatemi/nullius
/plugin install nullius@nullius
```

If `doctor` already showed the plugin enabled, say so instead and skip this.

## 7. Close with a real diagnostic, not a claim

Run:

```
npx -y @nullius-inverba/kit doctor
```

Report what it actually says. If they haven't run the two `/plugin` lines
yet, `doctor` will still show hooks as undelivered — that's correct, not a
bug in this skill, and it will resolve itself once they run those two
commands. Do not tell the human setup is "complete" — tell them what
`doctor` reported, which is the thing that is actually checkable from here.

Versions

RepositoryScoreLicence
This page · armanfatemi/nullius100MIT
HwangSlater/harness-fit100MIT
nesquikm/dev-process-toolkit100MIT
userKael/rastro100MIT
als-apg/osprey100BSD-3-Clause
dedujeong/gemba100Apache-2.0
eigenwise/eigenwise-toolshed100MIT
awrshift/agent-memory-kit100MIT
lifecycle-innovations-limited/claude-ops100MIT

Database snapshot: 13.11.2026 · package version b1894ba04062 (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

  • 91awaken
    Guided Oracle birth and awakening ritual. Default is Soul Sync (~20min), or --fast (~5min). Use when creating a new Oracle in a fresh repo, when user says 'awaken', 'birth oracle', 'create oracle', 'new oracle', or wants to set up Oracle identity in an empty repository. Do NOT…
  • 100setup-notion
    Guided Notion connection setup wizard. Verifies the Notion connector is enabled, walks the user through enabling and authorizing it, and checks for an Analysis Gallery database. Use when the user says "/setup-notion", "connect to notion", "set up notion", "I want to export to…
  • 100setup-cowork
    Guided Cowork setup — install a matching plugin, try a skill, connect tools. Use when: set up cowork, setup cowork, get started with cowork, cowork onboarding, configure cowork, personalize cowork.
  • 100bootstrap-agent-config
    Generate a high-quality project CLAUDE.md and AGENTS.md by inspecting the current repository. Use when a repo has no agent config, when onboarding a new project, or when the user asks to "set up Claude/Codex for this repo" or "write a CLAUDE.md". Detects languages, build/test…
  • 100onboarding
    Get oriented in the pardes marketplace and tune the user's Claude Code setup. Explains what each plugin does and how they compose, then runs an advisory config doctor that reports recommended settings and applies them only on explicit confirmation. Use when a user is new to the…

Feedback and reports

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