agentleFS
jinhuang712jinhuang712/claude-code-broom/skills/setup/SKILL.md

setup

Skill0 starsChanged yesterdayMITView on GitHub

Set up broom for this repo. Finds missing formatters, linters, type checkers and language servers, asks the user, installs what they agree to and adds default configs. Use for /broom:setup, when broom's session note says the repo has gaps, or when the user asks to set up linting, formatting or language servers.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-atomic-chat-tool, add-dashboard 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.
  • MicrosoftSkill

    add-atomic-chat-tool

    Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

    Also in 8 projects that use this

  • MicrosoftSkill

    add-dashboard

    Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.

    Also in 8 projects that use this

  • +10 more from microsoft

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only before acting on the user's machine or repo: installing tools and adding config files.

    line 23
  2. Distinctive:

    Ask only what applies. Never install or change anything the user didn't pick.

    line 40
  3. Very specific:

    Run the picked commands (fix / configure, or their _global versions) from the repo root, one at a time, and stop on a failure.

    line 45
  4. Very specific:

    Run broom doctor again and show the result.

    line 64
  5. Very specific:

    run broom setup --done when the user went through with setup, even if they left some gaps on purpose

    line 66
  6. Very specific:

    run broom setup --dismiss when they declined

    line 67

“Common” is measured: kept by at least 6 in 10 of the 169 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

1. Diagnose

broom doctor --json

items lists every tool and config with a status: ok, missing, broken (on PATH but doesn't run), off (no config, so broom leaves formatting alone) or conflict (another plugin starts a language server for the same files). fix and configure hold the exact commands, in order; fix_global and configure_global are the same with JS/TS tools installed machine-wide. If healthy is true, tell the user everything is in place, run broom setup --done, and stop.

Setup answers hold in every repo. An item with answered: true is a kind of gap the user already left alone somewhere; don't raise it again unless the user asks for everything.

2. Ask

Ask only before acting on the user's machine or repo: installing tools and adding config files. Never ask the user to pick settings. They start at defaults (format at commit, check at each turn end and at commit, format only the changed lines), and the user changes one in /config or .broom.json when they object.

Summarize the gaps in plain words, then ask with AskUserQuestion, in one call, only the questions that apply:

  1. Install the missing tools? Show the commands. Options: install all, once for every repo (recommended): fix_global, a project's own node_modules still wins where it has one; install JS/TS and CSS tools into this project as devDependencies instead: fix (changes package.json, best when the team shares the setup); let me pick; skip. Offer the devDependency option only when fix and fix_global differ. stylelint-config-recommended-scss and -less stay devDependencies either way: stylelint only finds them in the project.
  2. Turn on formatting where it's off? Show the configure commands (configure_global if they picked the once-for-every-repo install): broom init <dir> adds default configs and never overwrites. Options: yes (recommended); yes, and reformat the whole repo now (a large diff); no. Configs live in the repo, so this is the one question a new repo can raise again, and only if the user said yes before.

Ask only what applies. Never install or change anything the user didn't pick. If nothing applies, say so and go to step 4.

3. Act

  • Run the picked commands (fix / configure, or their _global versions) from the repo root, one at a time, and stop on a failure. xcode-select --install opens macOS's installer and returns at once: ask the user to finish it before going on.
  • Change a setting only when the user objects to its default. For all repos:

    claude plugin install broom@claude-code-broom --config <name>=<value>

    For this repo only, write it to .broom.json at the repo root, for example {"check_on": "commit"}; it overrides the user settings here. Paths broom should never touch (generated code, vendored code) go in "exclude" as globs relative to the repo root, for example ["vendor/**", "**/*.pb.go"].

  • Whole-repo reformat, if picked: broom sweep --all --fix.
  • A conflict means another plugin serves the same files. Offer its claude plugin disable … command; the change applies after /reload-plugins.

4. Verify and record

Run broom doctor again and show the result. Then:

  • run broom setup --done when the user went through with setup, even if they left some gaps on purpose
  • run broom setup --dismiss when they declined

Either way the gaps left are remembered by kind for every repo: broom raises setup again only for a kind of gap it hasn't asked about anywhere. Tell the user this, and that broom setup --reset makes it ask about everything again.

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.