configure-plugin/skills/configure-select/SKILL.md
Interactive selector for infrastructure standards. Use when setting up specific components or building infrastructure incrementally instead of running /configure:all.
npx skillsauth add laurigates/claude-plugins configure-selectInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Interactively select which infrastructure standards checks to run.
| Use this skill when... | Use another approach when... |
|------------------------|------------------------------|
| Setting up selected components interactively | Running all components (use /configure:all) |
| Choosing specific standards to implement | Checking status only (use /configure:status) |
| Customizing configuration scope for project | Single component needed (use specific /configure:X skill) |
| User wants control over which components to configure | Automated full setup preferred |
| Building configuration incrementally | Complete infrastructure setup needed immediately |
find . -maxdepth 1 -name \'.project-standards.yaml\'find . -maxdepth 1 -name '.project-standards.yaml' -exec grep -m1 "^project_type:" {} +find . -maxdepth 2 \( -name '*.tf' -o -type d -name 'terraform' \) -print -quitfind . -maxdepth 1 -name \'package.json\'find . -maxdepth 1 -name \'pyproject.toml\'find . -maxdepth 1 -name \'Cargo.toml\'Parse from $ARGUMENTS:
--check-only: Report status without offering fixes (CI/CD mode)--fix: Apply fixes automatically to all selected componentsExecute this interactive component selection workflow:
.project-standards.yaml if it exists (check project_type field)terraform/, helm/, argocd/, or *.tf filespackage.json with vue/react dependenciespyproject.toml or requirements.txtCargo.tomlThe component roster lives in the sibling manifest configure-all/components.yaml. Run the lister to get the current domains and their components:
bash "${CLAUDE_SKILL_DIR}/../configure-all/scripts/list-components.sh"
DOMAIN=<key> TITLE=<title> lines are the selectable domains;
COMPONENT=<name> DOMAIN=<key> ... lines are their members. Never
hand-maintain a category table here — the manifest is the single source of
truth.
Use AskUserQuestion with multiSelect, building the questions from the lister output:
TITLE, description = that
domain's component names from the lister output.TYPES excludes the detected project type.Map each selected domain to its components' /configure:X commands (a
COMPONENT=configure-tests row runs /configure:tests).
Run each selected command with appropriate flags:
--check-only first, then offer --fix--check-only flag: Only audit, no fixes offered--fix flag: Apply fixes automaticallyReport results as each check completes.
Print a summary for selected components only:
Selected Components Summary:
+-----------------+----------+---------------------------------+
| Component | Status | Notes |
+-----------------+----------+---------------------------------+
| Pre-commit | WARN | 2 outdated hooks |
| Linting | PASS | Biome configured |
| Formatting | PASS | Biome configured |
+-----------------+----------+---------------------------------+
| Context | Command |
|---------|---------|
| Interactive component selection | /configure:select |
| Select and auto-fix | /configure:select --fix |
| Check mode only | /configure:select --check-only |
| Detect project type | test -f .project-standards.yaml && grep "^project_type:" .project-standards.yaml \| sed 's/.*:[[:space:]]*//' |
| Flag | Description |
|------|-------------|
| --check-only | Report status without offering fixes |
| --fix | Apply fixes automatically to all selected |
| Command | Use Case |
|---------|----------|
| /configure:all | Run everything (CI, full audit) |
| /configure:select | Choose specific components interactively |
| /configure:status | Quick read-only overview |
| /configure:<component> | Single component only |
/configure:all - Run all checks/configure:status - Read-only status overviewdevelopment
Debug HTTP APIs: trace requests, inspect headers. Use when a request fails: check status first.
documentation
Render architecture diagrams from text sources. Use when documenting system topology.
tools
Inspect JSON payloads and extract nested fields. Use when parsing API responses.
tools
--- name: no-description allowed-tools: Read --- # No Description This skill has no description and must be dropped with a warning.