agentleFS
Aquilo-Solution-SAquilo-Solution-S/tesla-valve/skills/prepare/SKILL.md

prepare

Skill1 starsChanged 18 days agoMIT-0View on GitHub

Prepare a project for Tesla Valve: install the compiler settings, linters and CI steps that enforce its shapes, and prove that each one fires. Run it only when the user asks for it, once per project and again when a language is added: it writes configs and CI.

  • Installs packages

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. samueltuoyo15/Dokugen★ 345same name
    2. iliasedelkin/jobissimo★ 8same name
    3. 2389-research/git-repo-prep★ 2same name
    4. mik2win/foureyes★ 2same name
    5. Mharbulous/probanda-dev★ 1same name

    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.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add the commands to the CI the project already runs, in the style of its other steps.

    line 54
  2. Distinctive:

    Add one small file that breaks exactly that rule.

    line 63
  3. Very specific:

    Run the checks. They must fail, and the output must name the rule or the error code the file's expect: line gives.

    line 65
  4. Distinctive:

    Delete the copy. The bad file never enters the project.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 5 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

Prepare

The tesla-valve skill trusts a shape only where the project's compiler or CI enforces it. Everywhere else it keeps the runtime check. This skill puts the enforcers in place, once, and proves that each one fires, so the shapes start to count.

It changes the project's configs and CI, so it runs only when the user asks, never in the middle of another task.

1. Survey

Find the languages the project builds (Cargo.toml, go.mod, pyproject.toml, package.json with tsconfig.json), and read the reference for each: Rust, Go, TypeScript, Python.

For each enforcer in the reference, find out whether the project has it, lacks it, or has it weaker: strict off, default-signifies-exhaustive: true, a lint set to warn where CI does not fail on warnings. Find the CI the project already runs and what it calls.

Show the survey as a table before changing anything: enforcer, state, file.

2. Propose

  • One diff per file, merged into what is there. Never replace a config whole, and never drop a rule the project already has.
  • Where the project already runs another tool for the same job, such as Biome instead of ESLint, look for its rule first and prove it the same way. Add a second tool only for what the first cannot hold.
  • Pin every new tool the way the project pins the rest: a lockfile, a requirements file, go install ...@version.
  • Count each new rule's findings on the existing code, in a temporary copy with the proposed config, and with any missing tool installed outside the project. A rule with findings stays off for now: the report lists them for the reshape skill, and a later run of prepare turns the rule on once they are gone. Until then its shape does not count, and the checks it would replace stay.
  • Change nothing until the user agrees to the diff.

3. Wire into CI

Add the commands to the CI the project already runs, in the style of its other steps. A failed check must fail the build. Add no new CI system.

4. Prove that each enforcer fires

A config that loads but enforces nothing looks the same as one that works. For each enforcer:

  1. Copy the project to a temporary directory, without build output.
  2. Add one small file that breaks exactly that rule. Each reference shows one per enforcer; rewrite it in the project's own types.
  3. Run the checks. They must fail, and the output must name the rule or the error code the file's expect: line gives.
  4. Delete the copy. The bad file never enters the project.

Match on the tool's message, not on your own comment: leave the expect: line out of the copy, because some tools print the source they refuse.

5. Report

One line per enforcer: what it holds, and whether it is now on and proven. Then the shapes that do not count yet, because their enforcer is off or its proof failed, with the findings that keep each rule off. Their runtime checks stay until it is on.

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.