Skip to content
Skills Library
Programming · Building & coding

setup

/setup

Prepares a project for craft. Configures the test runner, a linter with size and complexity limits (function, class, parameters, nesting), and the `test` and `lint` scripts. Use when you start a new project, or when the project has no lint with limits or no test script yet.

Repository
craft ↗
Licence
MIT
Last repository change
13.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Prepares a project for craft. Configures the test runner, a linter with size and complexity limits (function, class, parameters, nesting), and the `test` and `lint` scripts. Use when you start a new project, or when the project has no lint with limits or no test script yet.

Arguments

/setup [stack, if it cannot be detected]
Original author description

Prepares a project for craft. Configures the test runner, a linter with size and complexity limits (function, class, parameters, nesting), and the `test` and `lint` scripts. Use when you start a new project, or when the project has no lint with limits or no test script yet.

How it works

  1. How to proceed
  2. Limits
  3. By stack
  4. CLAUDE.md
  5. Out of scope
Original SKILL.md headings · 59 lines, 549 words
SKILL.md preview
---
name: setup
description: Prepares a project for craft. Configures the test runner, a linter with size and complexity limits (function, class, parameters, nesting), and the `test` and `lint` scripts. Use when you start a new project, or when the project has no lint with limits or no test script yet.
argument-hint: "[stack, if it cannot be detected]"
disable-model-invocation: true
---

# Quality setup

This skill gets the project ready for `craft:craft` and its ATDD flow. What is a visual review today becomes a rule that the linter enforces.

## How to proceed

1. **Detect the stack** from the manifests (`package.json`, `composer.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`) and from the package manager (lockfile). If the project runs in a container, run the commands there.
2. **List what already exists**: test runner, linter, configs, scripts. Never replace: complete what is missing and **never loosen** a limit that is already stricter.
3. **Show the plan and wait for the ok**: dependencies to install, files to create or edit, limits. Use a short table.
4. **Apply**: install with the package manager of the project, write the configs, create the `test` and `lint` scripts.
5. **Run the lint** once. Do **not** fix violations in existing code now. Report the count per rule and suggest `/craft:craft` per module. If there are many, set the size rules as warnings (`warn`) and say so in the report.
6. **Report**: touched files, `test` and `lint` commands, existing violations.

## Limits

These are the same numbers that the craft skills use as a sign, so the linter and the screening speak the same language.

| Limit | Value | Skill that fixes the violation |
|---|---|---|
| Lines per function | 20 (not counting blank lines and comments) | `../craft/references/functions.md` |
| Lines per file/class | 200 | `../craft/references/single-responsibility.md` |
| Parameters | 3 | `../craft/references/arguments.md` |
| Nesting | 2 levels | `../craft/references/guard-clauses.md` |
| Cyclomatic complexity | 10 | `../craft/references/functions.md`, `../craft/references/guard-clauses.md` |

Test files are outside the limits of lines per function and per file (a `describe` is long by nature).

## By stack

The tool and the rules of each stack are in `references/stacks.md`.

Vue or React frontend: ask whether the production build must remove `data-testid`. If yes, configure the plugin of the stack listed in `../craft/references/test-ids.md`. Never remove the attribute from the build that runs the E2E.

Test runner: the one the project already uses. If there is none, use the default of the stack (vitest, pest, pytest, `go test`, `cargo test`). Check that it runs filtered (`../craft/references/filtered-tests.md`).

## CLAUDE.md

Create or complete a minimal CLAUDE.md with the project context that the setup found:

```markdown
A reference, decision or choice about the project lives in the repo (CLAUDE.md, `docs/`, `.claude/memory/`), with a relative path. Never in the local memory of Claude (`~/.claude/`) and never with an absolute path: it would hold only on this machine and the team would not see it.

## Commands

- Tests: `<command>`, filtered: `<filtered command>`
- Lint: `<command>`
```

Add one more line only if something departs from the stack default (tests inside a container, a service that must be up).

The reference line exists because, without it, the model writes project decisions to its local memory. That memory does not go to the repo or to the team.

Do not list the craft skills, agents, hooks, principles or the lint limits. The user starts craft with `/craft:plan` and `/craft:craft`, and the limits are in the config file. Repeating them spends context in every session and goes out of date.

## Out of scope

CI, pre-commit hooks and formatting of existing code. If the user asks, do it in a separate change.
Files in this package (2)
  • SKILL.md 4 KB
  • references/stacks.md 1 KB

Versions

RepositoryScoreLicence
This page · kamoca-labs/craft100MIT
HwangSlater/harness-fit100MIT
nesquikm/dev-process-toolkit100MIT
userKael/rastro100MIT
als-apg/osprey100BSD-3-Clause
dedujeong/gemba100Apache-2.0
eigenwise/eigenwise-toolshed100MIT
awrshift/agent-memory-kit100MIT
lifecycle-innovations-limited/claude-ops100MIT

Database snapshot: 13.11.2026 · package version 41e1629664ab (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 85agent-skill-linter
    Lint a codebase on code quality, best practices, design principles, build and test status, per-test speed (slow at or above 5s), cyclomatic complexity, and expressive naming, then render the results as a modern web report. Use when the user runs /lint or /lint-site, or asks to…
  • 100setup-linter
    USE WHEN setup automatic linting, add linter hook, configure code formatting on completion, enable lint on save. Auto-detects project type (JS/Python/Rust/Go/Deno/Biome), installs linter if missing, creates config with sensible defaults, wires a Stop hook in .claude/settings.json.
  • 100test-studio-script-runner
    Explains the dev/test-studio Script Runner tool. Use when adding, editing, running, or documenting scripts in dev/test-studio/src/script-runner, or when the user mentions the Scripts tool, Studio runner scripts, script variables, or browser-side Sanity Studio scripts.
  • 95stacks
    Start a new project from a stack or add fragments to an existing repo, then drive it to a verified working state. Use for project setup, tests, lint, CI and agent configuration, or when the user mentions stacks.
  • 92fix-linter-test
    Debug and fix a failing MegaLinter linter test. Use when a linter test fails in CI or locally.
  • 100javascript-linter
    Use when reviewing scripts, client components, bundles, or runtime behavior related to Lint JavaScript code. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.