agentleFS
BSSE23047BSSE23047/nauraiz-dev/skills/setup/SKILL.md

setup

Skill2 starsChanged 13 days agoMITView on GitHub

Check and fix the machine for nauraiz-dev: Node, Claude Code, superpowers installed and enabled, hooks registered once, auto-memory on; offer a user-level CLAUDE.md. Run on a new machine or when something looks off. Not a project setup (use init).

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 0 are distinctive, and 9 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 9

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check this machine for nauraiz-dev and offer the fixes.

    line 10
  2. Very specific:

    Ask before running each fix and before writing ~/.claude/CLAUDE.md.

    line 16
  3. Very specific:

    Never edit ~/.claude/settings.json yourself.

    line 18
  4. Very specific:

    Run node "${CLAUDE_PLUGIN_ROOT}/scripts/setup/check.mjs" and read the JSON.

    line 23
  5. Very specific:

    Add an update line from update: update.behind false is "up to date" (installed).

    line 32
  6. Very specific:

    If fixes is empty and userClaudeMd is true, say the machine is ready and stop.

    line 37
  7. Very specific:

    When the line installs nauraiz-dev, add --scope user to it.

    line 43
  8. Very specific:

    If userClaudeMd is false, offer to create ~/.claude/CLAUDE.md from the template.

    line 51
  9. Very specific:

    Ask the user for the commit identity, preferred models, review style and a line or two about themselves, fill every {{...}} from the …

    line 52

“Common” is measured: kept by at least 6 in 10 of the 171 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

setup

Check this machine for nauraiz-dev and offer the fixes. Get the user-level template with node "${CLAUDE_PLUGIN_ROOT}/scripts/show.mjs" templates/user-CLAUDE.md; never Read plugin files directly.

Two limits apply to every step:

  • Ask before running each fix and before writing ~/.claude/CLAUDE.md. One question per fix; a no skips it and the rest carry on.
  • Never edit ~/.claude/settings.json yourself. Print the exact change and let the user make it.

Steps

  1. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/setup/check.mjs" and read the JSON.
  2. Show a table, one row per check, with ok, missing or off: Node (node.version, ok when node.ok), Claude Code (claude.version), superpowers (installed and enabled), nauraiz-dev (installed and enabled), hooks registered once (ok when duplicateHooks is empty), auto-memory (autoMemory), cross-marketplace dependencies (crossMarketplace.allowed), user ~/.claude/CLAUDE.md (userClaudeMd). Recommend installing nauraiz-dev at user scope, claude plugin install nauraiz-dev@nauraiz-dev --scope user, because then every folder shows the nauraiz-dev header, not only repos that enable it. Add an update line from update: update.behind false is "up to date" (installed); true is "behind: installed X, latest Y", then the update command from fixes (claude plugin marketplace update nauraiz-dev && claude plugin update nauraiz-dev@nauraiz-dev) and the note in update.reason (start a new session; auto-update can be turned on in /plugin); null is "could not check" with update.reason, which is not a failure of the machine. If fixes is empty and userClaudeMd is true, say the machine is ready and stop.
  3. Go through fixes in order, one at a time:
    • A line that starts with claude plugin is a command: show it, ask, and on yes run it with Bash (Claude Code asks for permission on its own, since only the check script is pre-approved). If claude.version is null, say so before running anything. When the line installs nauraiz-dev, add --scope user to it. The update line is run as given, without --scope.
    • Any other line is an instruction about a file (a hook to remove from settings.json, a setting to add). Print it as given, with the exact text to add or remove, and ask the user to make that change themselves. Do not edit the file.
    • The cross-marketplace line applies only if installing nauraiz-dev reports a dependency error; say that, and do not ask the user to do it otherwise.
  4. If userClaudeMd is false, offer to create ~/.claude/CLAUDE.md from the template. Ask the user for the commit identity, preferred models, review style and a line or two about themselves, fill every {{...}} from the answers (leave none), show the result, and write it only after a yes. Never overwrite an existing file. This file holds things about the user, not about a project.
  5. Print what was run, what was skipped and what the user still has to do by hand. Finish with: restart Claude Code, so plugin and settings changes take effect.

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.