Agent skill

Shopware CLI

by shopware in shopware/shopware-cli

Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with…

MITAuto-check passedTesting & QA

Install Shopware CLI

skills CLI
$ npx skills add shopware/shopware-cli --skill shopware-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shopware/shopware-cli shopware-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shopware/shopware-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/shopware-cli .claude/skills/shopware-cli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
shopware-cli
GitHub stars
123
Token cost
~4.9k tokens
SKILL.md length
2,384 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with…

  • Works in 2 steps: Shopware CLI does not expose the… → troubleshooting requires inspecting the…
  • Contributing to shopware/shopware-cli and reasoning about the CLIs user-facing behavior
  • SKILL.md covers Start with the current CLI, Command areas, Plugin scaffolding and Prefer Shopware CLI abstractions, plus 9 more sections
  • Calls composer

What it does

Shopware CLI is an agent skill from shopware/shopware-cli. Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with --only/--exclude and --format json, junit, github, gitlab for CI), develop, build, upgrade, and troubleshoot. Also use when contributing to shopware/shopware-cli and reasoning about the CLI's user-facing behavior.

Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Unit testing. It works with GitHub, GitLab, JUnit and Go. The repository describes itself as: CLI for Shopware Account and Shopware 6. The licence is MIT.

When your agent uses it

  • Contributing to shopware/shopware-cli and reasoning about the CLIs user-facing behavior
  • Tasks that involve Unit testing

Example prompts

  • “/shopware-cli”

Requirements

  • Docker

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Shopware CLI does not expose the required operation; or
  2. troubleshooting requires inspecting the underlying operation.

What it can do on your machine

Read from SKILL.md and the folder at commit f20f5ba. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • composer

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Shopware CLI loads about 4.9k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 2,384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shopware/shopware-cli at commit f20f5ba, republished under its MIT licence (© shopware). 2,384 words, ~4,862 tokens.

Download SKILL.mdSave it as .claude/skills/shopware-cli/SKILL.md (or your agent's skills folder).
name
shopware-cli
description
Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with --only/--exclude and --format json, junit, github, gitlab for CI), develop, build, upgrade, and troubleshoot. Also use when contributing to shopware/shopware-cli and reasoning about the CLI's user-facing behavior.

Shopware CLI

Use Shopware CLI as the preferred interface for supported Shopware project, extension, and account workflows.

When contributing to shopware/shopware-cli, use this skill to reason from the user's perspective: what the CLI can do, which command a user should choose, how commands should behave, and where safety boundaries belong. Use the repository's AGENTS.md for implementation conventions, architecture, testing, and Go-specific contributor guidance.

Start with the current CLI

Treat the current CLI binary as authoritative for commands and flags.

bash
command -v shopware-cli
shopware-cli --version
shopware-cli --help
shopware-cli project --help
shopware-cli extension --help
shopware-cli account --help

For a specific command:

bash
shopware-cli <group> <command> --help

When working on unreleased functionality in a shopware/shopware-cli checkout, inspect or run the checked-out code instead of assuming the installed release behaves the same way. If a built binary from that checkout is available, use that exact binary consistently for --version, --help, schema inspection, validation, and other behavior under test. Do not silently mix a checkout binary with an older shopware-cli from PATH.

Do not invent commands, flags, configuration fields, or behavior from memory.

Command areas

The CLI has three primary user-facing areas:

  • project: create, configure, develop, inspect, build, maintain, and upgrade Shopware projects.
  • extension: build, validate, format, package, and maintain Shopware extensions.
  • account: authenticated Shopware Account and extension producer workflows.

This is orientation, not a complete command catalog. Use --help for the current command surface.

Plugin scaffolding

extension create writes the foundation of a plugin (composer.json, .gitignore, a minimal plugin class, PHPUnit bootstrap). PHPUnit stays on create; there is no extension add tests. The bootstrap uses Shopware TestBootstrapper (addActivePlugins, setForceInstallPlugins(true)).

extension add <generator> adds one example feature inside an existing plugin. Generators are individual commands, not a plugin:create questionnaire or Core make:plugin:* wrappers. Run them from the plugin directory in a Shopware project on 6.7.13.0 or newer (declarative custom-fields.xml). Unsupported versions fail before any files are written.

Available generators: admin-module, command, custom-fieldset, entity, event-subscriber, javascript-plugin, plugin-config, scheduled-task, store-api-route, storefront-controller.

Intentional differences from Shopware Core scaffolding:

  • PHP src/Resources/config/services.php and routes.php instead of XML.
  • Admin snippets as en.json / de.json instead of en-GB / de-DE.
  • Existing main.js is appended, not overwritten.
  • Existing plugin files are never overwritten; duplicate service/route blocks are skipped.
  • Interactive and non-interactive extension add share the same code path (flags/args only; no questionnaire).

Prefer Shopware CLI abstractions

When Shopware CLI provides a command for a task, prefer it over manually reconstructing the workflow with Composer, bin/console, Docker, npm, PHP, or direct filesystem changes.

The CLI may already understand:

  • the current Shopware project;
  • project and extension configuration;
  • the selected environment;
  • Docker versus local execution;
  • extension structure and type;
  • supported build, validation, maintenance, and upgrade workflows.

Use lower-level tools only when:

  1. Shopware CLI does not expose the required operation; or
  2. troubleshooting requires inspecting the underlying operation.

If the task involves a Docker-backed project or deciding where a command should execute, use the shopware-cli-docker skill when available.

Understand command risk

Before executing a command, understand what it can change.

Usually low risk

Inspection-oriented actions such as help, version checks, status, diagnostics, schema inspection, validation, and reading logs are normally appropriate while investigating a task.

Still inspect command help when behavior is unclear.

Local file changes

Commands that create, generate, format, fix, upgrade, package, install dependencies, or rewrite configuration may change files.

Before running them:

  • inspect --help;
  • understand which files may change;
  • use a preview or dry-run when the command actually supports one;
  • preserve unrelated user changes;
  • review the resulting diff.

Do not assume every command supports --dry-run.

When the user asks for inspection only or explicitly says not to modify files, do not temporarily rewrite project files just to probe validation behavior. Prefer help/schema/source inspection or a separate disposable fixture.

Database and application-state changes

Treat commands that can change the database, Shopware application state, installed extensions, caches, indexes, migrations, or configuration as higher risk.

shopware-cli project console (and the swx alias) is an execution bridge to Symfony Console and to custom scripts from the project composer.json. Its safety depends on the command or script passed to it.

Before running an unfamiliar or state-changing Symfony command:

bash
shopware-cli project console <command> --help

Discover Composer scripts from the project composer.json or shopware-cli project console list. Do not pass --help to a Composer script to inspect it; that argument is forwarded to the script and can still run it.

Know which environment will be affected before proceeding.

Remote changes

Treat account operations that authenticate, log out, upload, push, publish, or otherwise modify remote Shopware Account state as external side effects.

Do not infer permission or user intent simply because credentials are available.

Validation workflows

Use shopware-cli project validate or shopware-cli extension validate to run validation checks against a project or extension.

Always inspect current flags and available checks:

bash
shopware-cli project validate --help
shopware-cli extension validate --help
Project validation
bash
shopware-cli project validate [flags]

Validates the Shopware project against the checks implemented by the current CLI and configured tools. It copies the project to a temporary directory and installs its toolset first, so a first run can be slow; --no-copy validates in place and skips the copy.

Common flags include:

  • --only <tools> — run only specific checkers (comma-separated).
  • --exclude <tools> — skip specific tools (comma-separated).
  • --format <format> — choose an output format supported by the current CLI (--reporter is a deprecated alias).
  • --local-only — limit extension discovery to plugins in custom/* (for the project toolset); does not add per-extension metadata validation.
  • --no-copy — do not copy project files to a temporary directory before validation.
  • --verbose — show debug output.

Use current --help rather than treating this list as exhaustive.

project validate is not extension validate. It runs the project code-quality toolset (PHPStan, ESLint, Twig linters, …) over the discovered extensions' source directories; it does not run per-extension manifest/metadata validation, so a clean run (0 problems) does not mean the custom extensions are valid. To validate a custom extension's structure and metadata, run shopware-cli extension validate <path> on it directly (e.g. each custom/plugins/<Name>).

Extension validation
bash
shopware-cli extension validate [path] [flags]

The extension path is required; use . for the current extension.

Normal extension validation runs the built-in checks implemented by the current CLI. Store-compliance mode can add Store-specific checks; do not assume that every metadata or quality rule is Store-only.

Common flags include:

  • --only <tools> — run only the named checkers (comma-separated).
  • --exclude <tools> — remove checkers from the selected set.
  • All checkers run by default, including PHPStan, ESLint, and Stylelint. --full is deprecated and has no effect. To do a quick validation use --only builtin (sw-cli remains accepted as a legacy alias and emits a deprecation warning).
  • --check-against <mode> — highest (default) or lowest: which supported Shopware version to check against.
  • --store-compliance — enable Store-compliance mode while the current CLI supports the flag. Prefer validation.store_compliance: true in .shopware-extension.yml for persistent Store intent.
  • --format <format> — choose an output format supported by the current CLI (--reporter is a deprecated alias).
  • --no-copy — do not copy extension files to a temporary directory.
  • --verbose — show debug output.

For Store-distribution workflows, use the shopware-cli-extension-store skill when available.

Each command selects only tools that support its operation. For example, extension validate --only prettier is an error because Prettier formats but does not check; the error lists available checkers. The extension command summaries show invoked or skipped: these describe selection and invocation, not whether files were applicable, findings were produced, or fixes were made.

Fresh results beat saved reports

Saved outputs such as validation.json, JUnit XML, or markdown reports can become stale after files are fixed or changed.

Before diagnosing a validation failure, rerun validation against the current working tree. If a saved report contradicts the current files or a fresh run, treat the saved report as stale.

CI and reporters

In automated environments, prefer machine-readable output when useful:

bash
shopware-cli project validate --format json > validation-results.json
shopware-cli project validate --format junit > validation-results.xml
shopware-cli extension validate . --format github
shopware-cli extension validate . --format gitlab

Reporters format emitted output. They do not by themselves post comments or annotations to pull requests or merge requests; CI configuration must consume the output appropriately.

Use the process exit code as the validation result. A reporter can change formatting, but validation errors still make the command fail.

Domain-specific routing

When validation fails in a specific area, route users to relevant skills when available:

  • PHP test failures → php-testing skill.
  • JavaScript/Admin failures → admin-testing skill.
  • Acceptance test failures → acceptance-testing skill.
  • Accessibility findings → accessibility-testing skill.
  • Architecture or LSP findings → architecture-review skill.
Validation troubleshooting

When validate produces unexpected results:

  1. Verify the exact CLI binary and version.

    • Use command -v shopware-cli and shopware-cli --version.
    • When testing a checkout, use its built binary consistently.
  2. Verify the working directory and project configuration.

    • Ensure .shopware-project.yml or .shopware-extension.yml is present and correct.
    • Check --verbose output when useful.
  3. Regenerate validation output.

    • Do not diagnose current files from an old saved report.
  4. Check installed and locked tool versions.

    • Full validation can depend on external tools such as PHPStan, ESLint, and Stylelint.
    • Verify relevant dependencies and configuration.
  5. Understand tool statuses.

    • skipped means a tool was not selected or was excluded; the status note gives the reason.
    • invoked means the tool was called, not that it analyzed files or succeeded. Use findings and the exit code for the validation result.
  6. Avoid ad hoc workarounds.

    • Do not bypass validation with manual lower-level commands before understanding why the CLI behaved as it did.
  7. Check environment and runtime prerequisites.

    • Some checks may require Docker, PHP, npm dependencies, or other tooling.
Show full SKILL.md (890 more words)Show less

Creating a new project

Use shopware-cli project create to scaffold a new Shopware project.

bash
shopware-cli project create --help
shopware-cli project create [name] [version] [flags]

Always check current --help first; treat the flag list below as orientation, not the source of truth.

Ask the user; do not guess

When this skill drives project creation, you typically run create non-interactively (-n), so the CLI's own prompts never appear and it silently applies defaults — some of which differ from the interactive ones (Elasticsearch defaults on non-interactively but off in the prompts). Do not inherit those defaults blind. Confirm the choices with the user first, then pass them as explicit flags. Frame each option by what it does for the user, not by errors it prevents or internal codes — e.g. justify skipping Elasticsearch as "simpler setup, only needed for large catalogs or advanced search", never with a 500 or index error. Walk through:

  • Name ([name]) — the project directory. Ask for it; do not default to the current directory (it must be empty or non-existent).
  • Version (--version) — e.g. 6.6.0.0 or latest.
  • Docker (--docker) — recommended. Runs the local setup in Docker instead of relying on a local PHP/toolchain.
  • Local domain (--local-domain) — recommended (requires --docker). Serves the shop at a stable <name>.shopware.local via the shared proxy instead of a port. First time on a machine it needs a one-time shopware-cli project proxy setup (sudo: DNS + HTTPS trust) — non-interactive create never runs this, so plan to run it separately.
  • PHP version (--php-version) — 8.2–8.5; usually leave it to the CLI. Ask only if the user needs a specific one; it must satisfy the chosen Shopware version's PHP constraint.
  • Elasticsearch/OpenSearch (--with-elasticsearch) — recommend leaving it off unless the user needs it (large catalogs or advanced search). It is enabled by default non-interactively, so to disable it pass --with-elasticsearch=false (omitting the flag leaves it on under -n; the separate --without-elasticsearch flag is deprecated).
  • AMQP (--with-amqp) — ask; enable only if they need queue/messaging support.
  • Deployment (--deployment) — none|container|deployer|platformsh|shopware-paas (default none).
  • CI/CD (--ci) — none|github|gitlab (default none).
  • Git (--git) — initialize a repository.
  • Audit (--no-audit) — do not set preemptively; only use it if security advisories block the install and the user accepts the risk.

With --docker, create runs for several minutes: it pulls the dev image and runs composer install, autoload generation, and post-install scripts inside the container. This is expected, not a hang. Surface progress to the user — stream the command's output, or run it in the background and report the current stage from the log — rather than blocking silently.

create scaffolds; it does not install the shop. It writes the project, runs composer install, and creates .shopware-project.yml (plus compose file / git when requested). The database is not set up yet. To install afterwards:

  • shopware-cli project dev install — non-interactive: starts the environment, runs the install, and saves admin credentials to the project config (defaults admin / shopware, en-GB, EUR; override with --admin-username/--admin-password/--locale/--currency). Idempotent — skips when the shop is already installed.
  • shopware-cli project dev — the interactive TUI dashboard when you want to drive it by hand.

Other gotchas

  • Security advisories block a non-interactive install unless --no-audit is set; interactive mode prompts instead.
  • The target folder must be empty; hostname collisions (a <name>.shopware.local already in use) surface at proxy/dev time, not at create.

Inspect the project before deciding

Relevant files can include:

  • .config/shopware-project.yml / .shopware-project.yaml / .shopware-project.yml (shop URL and Admin API credentials live under environments; empty -e targets environments.local)
  • .config/shopware-extension.yml / .shopware-extension.yml / .shopware-extension.yaml
  • composer.json
  • composer.lock
  • manifest.xml

Do not infer the project type, extension type, target environment, or Shopware version solely from the user's wording.

Only the first found yml / yaml is used in the specified order above, prefer the first one for new projects.

Prefer CLI-provided configuration schemas over remembered configuration fields.

Non-interactive and agent execution

For unattended or agent-driven execution, prefer:

bash
shopware-cli --no-interaction <command>

or:

bash
shopware-cli -n <command>

If required values are missing, inspect --help and provide them explicitly rather than guessing answers to prompts.

Prefer machine-readable output when the command explicitly supports it.

Credentials and sensitive data

Never expose access tokens, passwords, client secrets, database credentials, or other secret values in responses, logs, examples, or committed files.

Prefer Shopware CLI's supported authentication and configuration mechanisms instead of manipulating credential storage directly.

Database dumps and other exports may contain sensitive customer or shop data. Treat their creation, storage, and sharing accordingly.

Generated files

Distinguish source files from generated files before editing them.

When Shopware CLI owns generation of an artifact, prefer regenerating it through the appropriate CLI command instead of manually editing generated output.

Inspect command help before regenerating anything that may overwrite existing files.

Troubleshooting

When a Shopware CLI command fails:

  1. Capture the exact command and error.
  2. Check the exact binary path and --version.
  3. Inspect the command's --help.
  4. Verify the working directory and relevant project or extension configuration.
  5. Retry with --verbose when useful.
  6. Check whether the correct project environment is selected and available.
  7. Inspect the underlying Composer, Symfony, Docker, npm, PHP, or API operation only after establishing what Shopware CLI attempted to do.

Do not work around a failing Shopware CLI command with lower-level tooling until you understand what CLI behavior or configuration would be bypassed.

Information priority

When behavior is unclear, use this order:

  1. the current CLI binary and fresh runtime output;
  2. project configuration and CLI-provided schemas;
  3. the current shopware/shopware-cli source and tests when implementation details are required;
  4. official Shopware CLI documentation.

Prefer version-correct facts over remembered Shopware behavior or stale generated reports.

© shopware, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/shopware-cli of shopware/shopware-cli.

Open the folder on GitHubat commit f20f5ba

Compare with similar skills

Shopware CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Shopware CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Shopware CLI this skillshopware/shopware-cli123—~4.9kAutomated safety check: PassMIT
File Test Bugmicrosoft/GitHub-Copilot-for-Azure255—~628Automated safety check: PassMIT
Deploy To Hostinghostinger/api-mcp-server159—~2.7kAutomated safety check: NotesMIT
Test GuardamElnagdy/guard-skills1.3k2 repos~2.1kAutomated safety check: PassMIT
Debug Playwright Prowquay/quay2.8k—~2.2kAutomated safety check: PassApache-2.0
Skill Doli Test PhpunitDolibarr/dolibarr7.7k1 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • File Test Bug

    microsoft/GitHub-Copilot-for-Azure

    Official

    File a GitHub issue for local integration test failures. An agent skill from microsoft/GitHub-Copilot-for-Azure.

    255 GitHub stars~628 tokensUpdated today
    Testing & QAAuto-check passed
  • Deploy To Hosting

    hostinger/api-mcp-server

    Deploy an existing project to a website on Hostinger web hosting (Shared, Cloud or Agency plans) and keep it deployed: picks the right deploy for static sites, Node.js apps (Next.js, Nuxt, Express…

    159 GitHub stars~2.7k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Test Guard

    amElnagdy/guard-skills

    Reviews newly written or edited tests against nine rules that cut test bloat, such as mock-heavy checks and near-duplicate cases, before they are committed.

    1.3k GitHub starsUsed in 2 repos~2.1k tokens
    Testing & QAAuto-check passed
  • Deep-dive diagnosis of a Playwright test failure already isolated to one Quay Prow/OpenShift CI run: downloads its GCS artifacts (results.json, JUnit, build/pod logs, Jaeger traces), classifies real…

    2.8k GitHub stars~2.2k tokensUpdated today
    Testing & QAAuto-check passed
  • Skill Doli Test Phpunit

    Dolibarr/dolibarr

    Creates or modify PHP unit tests for Dolibarr ERP/CRM functions and methods.

    7.7k GitHub starsUsed in 1 repo~1.3k tokens
    Testing & QAAuto-check passed
  • Diagnose any Quay Prow job failure end to end: prowjob.json - top-level build log - JUnit - resolved failing step - Playwright results.json when the failing step is Playwright, continuing through…

    2.8k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed

More from shopware/shopware-cli

  • Shopware CLI Docker

    shopware/shopware-cli

    A skill your agent uses when working on Docker-backed Shopware projects and needing to run Shopware or Symfony CLI commands, interact with project services or databases, start or stop the…

    123 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Shopware CLI Extension Store

    shopware/shopware-cli

    A skill your agent uses for Shopware Store readiness, publication, submission, or compliance questions about an extension.

    123 GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Shopware CLI

What does Shopware CLI do?

Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with…. Shopware CLI is an agent skill from shopware/shopware-cli. Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with --only/--exclude and --format json, junit, github, gitlab for CI), develop, build, upgrade, and troubleshoot.

When should I use Shopware CLI?

Shopware CLI fits situations like: contributing to shopware/shopware-cli and reasoning about the CLIs user-facing behavior; tasks that involve Unit testing.

How do I install Shopware CLI in Claude Code?

Run `npx skills add shopware/shopware-cli --skill shopware-cli -a claude-code`. Or copy the skill folder (skills/shopware-cli in shopware/shopware-cli) into .claude/skills/shopware-cli in your project. Claude Code loads it when a task matches its description.

How do I install Shopware CLI in Codex?

Run `npx skills add shopware/shopware-cli --skill shopware-cli -a codex`. Or copy the skill folder (skills/shopware-cli in shopware/shopware-cli) into .agents/skills/shopware-cli in your project. Codex loads it when a task matches its description.

Can I use Shopware CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shopware/shopware-cli --skill shopware-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shopware-cli, .gemini/skills/shopware-cli, .github/skills/shopware-cli and .opencode/skills/shopware-cli in your project.

What does Shopware CLI need to run?

Going by SKILL.md and its folder, Shopware CLI needs the command-line tools its instructions call (composer). Our summary lists: Docker.

Does Shopware CLI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Shopware CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Shopware CLI use?

Shopware CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Shopware CLI use?

About 4.9k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Shopware CLI?

Skills that share tags, products or a category with Shopware CLI: File Test Bug (microsoft/GitHub-Copilot-for-Azure, 255 stars), Deploy To Hosting (hostinger/api-mcp-server, 159 stars), Test Guard (amElnagdy/guard-skills, 1.3k stars) and Debug Playwright Prow (quay/quay, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Shopware CLI?

shopware (a GitHub organization) maintains it in shopware/shopware-cli, which has 123 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.

Source: shopware/shopware-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.