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
- openstory-so/openstorytheir own version, first seen Nov 16, 2026
- furkandvrc/conductortheir own version, first seen Nov 16, 2026
- futorio/red-greentheir own version, first seen Nov 16, 2026
- JCodesMore/jobs-for-ai-agentstheir own version, first seen Nov 16, 2026
- finolabs/finolabs-vibecodetheir own version, first seen Nov 16, 2026
- vincentventalon/claude-code-video-editing-skilltheir own version, first seen Nov 15, 2026
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.
MicrosoftSkilladd-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
MicrosoftSkilladd-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
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 192
- anthropics/knowledge-work-plugins★ 36ksame name
- garrytan/gbrain★ 33ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.4ksame name
- pytorch/executorch★ 5.2ksame name
- aws/agent-toolkit-for-aws★ 3.5ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
182 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- Distinctive: line 23
Ask only before acting on the user's machine or repo: installing tools and adding config files.
- Distinctive: line 40
Ask only what applies. Never install or change anything the user didn't pick.
- Very specific: line 45
Run the picked commands (fix / configure, or their _global versions) from the repo root, one at a time, and stop on a failure.
- Very specific: line 64
Run broom doctor again and show the result.
- Very specific: line 66
run broom setup --done when the user went through with setup, even if they left some gaps on purpose
- Very specific: line 67
run broom setup --dismiss when they declined
“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.
Files
1. Diagnose
broom doctor --jsonitems 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:
- Install the missing tools? Show the commands. Options: install all, once for every repo (recommended):
fix_global, a project's ownnode_modulesstill wins where it has one; install JS/TS and CSS tools into this project as devDependencies instead:fix(changespackage.json, best when the team shares the setup); let me pick; skip. Offer the devDependency option only whenfixandfix_globaldiffer.stylelint-config-recommended-scssand-lessstay devDependencies either way: stylelint only finds them in the project. - Turn on formatting where it's off? Show the
configurecommands (configure_globalif 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_globalversions) from the repo root, one at a time, and stop on a failure.xcode-select --installopens 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.jsonat 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
conflictmeans another plugin serves the same files. Offer itsclaude 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 --donewhen the user went through with setup, even if they left some gaps on purpose - run
broom setup --dismisswhen 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.
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
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.

