agentleFS
vale-clivale-cli/agent-tools/skills/setup/SKILL.md

setup

Skill8 starsChanged 3 months agoMITView on GitHub

Install Vale, write a .vale.ini, sync styles, and get a first run. Use when the user says "set up vale", "add vale", "add prose linting", or "lint our docs" in a repository that has no Vale config yet.

  • Installs packages

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

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    1. Install: if vale --version fails: brew install vale, choco install vale, or a binary from <https://docs.vale.sh/topics/installation.md>.

    line 22
  2. Very specific:

    Do not commit the StylesPath directory.

    line 72
  3. Distinctive:

    Do not pick the style package without asking.

    line 73
  4. Very specific:

    Do not set MinAlertLevel = error to make the first run look clean.

    line 74

“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

Set up Vale in this repository

When to use this

The repository has no .vale.ini, or has one that does not resolve. If a working config already exists, the user probably wants fix or triage instead — check before writing anything.

Prerequisites

  1. vale ls-config — if it resolves, a config already exists. Fix what it reports rather than starting over, and say that is what you are doing.
  2. Know where the prose lives. Ask if it is not obvious.

Workflow

1. Install if vale --version fails: brew install vale, choco install vale, or a binary from https://docs.vale.sh/topics/installation.md.

2. Find the prose. docs/, content/, *.md at the root. Do not point Vale at the whole repository: vendored directories, changelogs and generated reference pages produce alerts nobody will act on, and the first run is what decides whether the team keeps it.

3. Write .vale.ini in the repository root:

StylesPath = styles
MinAlertLevel = suggestion

Packages = Microsoft

[*.md]
BasedOnStyles = Vale, Microsoft

Match the section glob to the formats actually present — [*.{md,mdx}], [*.adoc], [*.rst]. A section that matches nothing lints nothing, and Vale will not warn you about it.

4. Ask before choosing the style package. Microsoft and Google disagree about things teams care about — contractions, headings, the Oxford comma. It is their editorial decision, not a default you pick for them. The https://vale.sh/explorer listing has the rest.

5. Add StylesPath to .gitignore. It is build output.

6. vale sync, then lint one file to confirm the setup resolves.

7. Report the first run honestly.

Vale setup summary
==================
Config:      .vale.ini  ([*.md] → Vale, Microsoft)
Styles:      styles/ (gitignored), 1 package synced
First run:   docs/ → 0 errors, 214 warnings, 1,988 suggestions

A large corpus commonly produces thousands of suggestions on day one. Say the number, and offer triage. Do not quietly raise MinAlertLevel to make it look smaller.

Do not

  • Do not commit the StylesPath directory.
  • Do not pick the style package without asking.
  • Do not set MinAlertLevel = error to make the first run look clean. Nothing has been decided by hiding the output.

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.