Agent skill

Shopware CLI Extension Store

by shopware in shopware/shopware-cli

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

MITAuto-check passed

Install Shopware CLI Extension Store

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

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

GitHub CLI
$ gh skill install shopware/shopware-cli shopware-cli-extension-store --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-extension-store .claude/skills/shopware-cli-extension-store && 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-extension-store
GitHub stars
123
Token cost
~5.1k tokens
SKILL.md length
2,616 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 6 steps: Collect evidence → Classification table — the only place… → Emit rules → …
  • Shopware Store readiness
  • SKILL.md covers 1. Collect evidence, 2. Classification table — the…, 3. Emit rules and 4. Store doc map, plus 2 more sections
  • Reaches developer.shopware.com

What it does

Shopware CLI Extension Store is an agent skill from shopware/shopware-cli. Use for Shopware Store readiness, publication, submission, or compliance questions about an extension. Inspects read-only using the installed shopware-cli, classifies every finding by table lookup, and cites a re-checkable source for each one so local file state is never reported as remote Store listing state.

Its SKILL.md is about 5.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Go and PHP. The repository describes itself as: CLI for Shopware Account and Shopware 6. The licence is MIT.

When your agent uses it

  • Shopware Store readiness
  • Compliance questions about an extension

Example prompts

  • “/shopware-cli-extension-store”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Collect evidence
  2. Classification table — the only place classification is decided
  3. Emit rules
  4. Store doc map
  5. Response format
  6. Self-check

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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • developer.shopware.com

    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 Extension Store loads about 5.1k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 2,616 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~5.1k

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). 2,616 words, ~5,079 tokens.

Download SKILL.mdSave it as .claude/skills/shopware-cli-extension-store/SKILL.md (or your agent's skills folder).
name
shopware-cli-extension-store
description
Use for Shopware Store readiness, publication, submission, or compliance questions about an extension. Inspects read-only using the installed shopware-cli, classifies every finding by table lookup, and cites a re-checkable source for each one so local file state is never reported as remote Store listing state.

Shopware Store readiness

Assess the current extension for Store publication. Start immediately. Never modify files. Never ask a preflight question the workspace can answer.

Every claim in the answer carries a source. A finding without a source is not a finding.

1. Collect evidence

Gather evidence in two steps: run shopware-cli directly — exactly as a developer would — then read a few of the extension's own files (listed below) for the specific values the classification table needs. Do not wrap this in a bespoke script: calling the CLI directly keeps the output and the config-file discovery identical to what a human gets, and avoids re-implementing logic (e.g. config-path lookup) the CLI already owns.

Run both validations from the extension root and capture the full output and the exit code:

bash
shopware-cli --version
shopware-cli extension validate . --only builtin --format markdown
shopware-cli extension validate . --only builtin --store-compliance --format markdown
  • The exit code is the pass/fail signal (0 = pass, non-zero = findings). The report goes to stdout; a usage block or error goes to stderr — do not read a validation failure as a usage error.
  • --format markdown gives a stable, quotable form. --reporter is a deprecated alias that prints a warning — use --format.
  • Treat the store-compliance run as a delta over the normal run: report only the lines it adds.
  • extension validate now runs all checkers by default. The two commands above explicitly select only the built-in builtin checker, not PHPStan/ESLint/Stylelint. (sw-cli remains accepted as a legacy alias. It is that checker's deprecated name, not shorthand for the binary.) Report "the builtin checks passed", not "full validation passed". Source: cmd/extension/extension_validate.go, selectExtensionValidationTools.
  • The Markdown report includes a checker table. invoked means the checker was called; it does not prove that files were analyzed or that a check passed. skipped means it was not selected or was excluded. Classify only finding lines, not checker-status lines.
  • Use one shopware-cli binary throughout, and state its version. Never mix binaries mid-answer.
  • Each error line ends with its result identifier — that identifier is the row's Source, and L0 catches any line the table does not name explicitly. The CLI currently prints a missing icon twice; count a repeated line once.

Then read these files yourself for the measured values and precondition triggers the classification table below uses — read only these, and do not re-derive CLI findings:

  • composer.json — license, extra.label, authors, and per-locale extra.description / extra.manufacturerLink / extra.supportLink (L1–L3, L5, A1, and the R9 trigger).
  • src/Resources/config/plugin.png — presence, dimensions, and size (the L4 gate; a missing icon is the CLI's metadata.icon line under L0).
  • src/Resources/config/config.xml — presence, and whether fields carry an English fallback (the R10 trigger).
  • extension type (plugin / theme / app) and whether it ships CMS elements (G3 / G4 triggers).

Run shopware-cli extension config-schema only if the extension already uses Store sync config, or the user asks where Store metadata is configured. Schema fields are never readiness requirements.

Do not answer before both validations have run.

2. Classification table — the only place classification is decided

Copy Level, Target, and Source from this table verbatim. Do not re-derive them from doc prose, CLI output, or reasoning. If a source has changed, report the drift as a separate note; do not silently reclassify.

Doc baseline: https://developer.shopware.com/docs/guides/development/testing/store/content-and-translations.html Code baseline: the shopware-cli source. The result identifiers below are printed at the end of every CLI result line and are stable across releases.

CLI rules are cited by their result identifier, not a file or line number: identifiers appear in the CLI's own output and survive refactors. If a shopware-cli source checkout is at hand, a row can be re-checked with:

bash
grep -rn '"metadata.icon.size"' --include=*.go internal/ | grep -v _test
#ConditionLevelTargetSourceEmit only if
L0Any other error line printed by extension validateCLI-enforcedLocal filethe result identifier printed in that line, for example metadata.label, metadata.icon, metadata.icon.size, assets.*always
L1extra.description per locale is 150–185 charsCLI-enforcedLocal filemetadata.descriptionalways
L2extra.manufacturerLink per locale presentCLI-enforcedLocal filemetadata.manufactureralways
L3extra.supportLink per locale presentCLI-enforcedLocal filemetadata.supportalways
L4src/Resources/config/plugin.png is 84–256 px in both dimensionsStore-doc-requiredLocal artifactdocs #images-and-screenshotsicon present (a missing icon is the CLI's metadata.icon line, L0)
L5authors key present in composer.jsonCLI-enforcedLocal filemetadata.authoralways
R1Published in the international StoreStore-doc-requiredRemote listingdocs #store-listingalways
R2Short description 150–185 charsStore-doc-requiredRemote listingdocs #store-listingalways
R3Long description ≥200 charsStore-doc-requiredRemote listingdocs #store-listingalways
R4Descriptions and use cases are meaningful and accurateStore-doc-requiredRemote listingdocs #store-listingalways
R5Display name avoids "plugin" and "shopware"Store-doc-requiredRemote listingdocs #store-listingalways
R6Clear, complete setup/configuration instructionsStore-doc-requiredRemote listingdocs #store-listingalways
R7Clean HTML, allowed tags only, no ads/contact info/backlinksStore-doc-requiredRemote listingdocs #store-listingalways
R8No blank-space filler textStore-doc-requiredRemote listingdocs #store-listingalways
R9German/English 1:1 parityStore-doc-requiredRemote listingdocs #store-listinguser states German Store intent, or de-DE values exist in composer.json (state which triggered it)
R10English fallback for settings and error messagesStore-doc-requiredExtension behaviordocs #admin-translationsextension has user-facing settings or error messages
A1Shopware Account license matches the composer.json license valueStore-doc-requiredRemote Accountdocs #extension-master-data-and-licensealways
G1≥1 storefront and ≥1 admin screenshot showing main featuresStore-doc-guidanceRemote listingdocs #images-and-screenshots (should)always
G2Mobile and desktop screenshotsStore-doc-guidanceRemote listingdocs #images-and-screenshots (prefer)always
G3Theme preview image in Theme ManagerStore-doc-requiredRemote listingdocs #images-and-screenshotsextension is a theme
G4CMS element iconStore-doc-requiredLocal artifactdocs #images-and-screenshotsextension ships CMS elements

Nothing outside this table is a finding, because nothing outside it has a source. Every CLI error line has one, its identifier, which is what L0 is for. In particular, never emit: store.type, demo shops, API credential checks, install/uninstall hooks, logging or JS rules for absent features, README/CHANGELOG/LICENSE-file pseudo-requirements, or generic compatibility-date advice.

CLI-vs-docs conflicts — defer to docs

When CLI and docs disagree on a requirement:

  • Follow the docs reading (canonical Store review standard).
  • Flag the CLI gap or mismatch as a note only if useful for understanding why local validation passed but Store review may differ.
  • Do not report the CLI reading as correct if docs have been updated.
  • CLI error lines stay under Required local changes regardless: they set the exit code. Put the docs reading next to them as a note.

Known differences:

  • Icon: the CLI's metadata.icon.size check rejects icons below 112 px and files above 30 kB, stricter than L4. When it fires, add that the Store standard is 84–256 px.
  • German metadata: the CLI requires de-DE label, description, manufacturerLink and supportLink unless .shopware-extension.yml sets store.availabilities without German. When those lines fire for an extension meant for the international Store only, name that setting.

3. Emit rules

Eight invariants. Check each finding against all eight before writing it.

  1. Lookup, not inference. Level, Target, and Source come from the table verbatim.
  2. Emit every ungated row, not a selection. Before writing the remote section, walk rows R1–R10, A1, G1–G4 in order and emit each whose precondition holds. Dropping a row because it feels obvious or hard to check is a silent failure. Count them: an extension with no theme, no CMS elements, no settings UI, no German Store intent and no de-DE values yields R1–R8 plus A1; either German trigger adds R9.
  3. Remote rows can never become local changes. Any row with Target = Remote listing / Remote Account / Extension behavior may appear only under "Remote conditions not verified". It can never be a required local change, and it can never be called missing, present, passing, failing, satisfied, or compliant unless the Shopware Account listing was actually inspected.
  4. Preconditions gate emission. A row whose Emit only if is not proven true by evidence from §1 emits nothing at all. Not as "N/A", not as "not applicable", not as a struck-through line. It is absent. R9 and R10 are omitted entirely for an extension with no German Store intent and no settings UI.
  5. Local values are candidates, not proof. Name the row and the specific rule the value bumps against, not generic advice: a label containing "Plugin" is incompatible with R5's prohibited-words rule, which is a different statement from "rename it to something better".
    • A candidate entry requires a measured deficiency — a value you read that conflicts with a named rule. A precondition firing is not a deficiency. If config.xml exists and its fields carry unqualified defaults plus lang="…" variants, the English fallback is present; say so or say nothing. Never write "verify that…" or "this may not…" about a file you have read: you either found a conflict and can quote it, or you did not.
    • Never propose a change that would delete existing content (translations, locales, fields) to satisfy a rule that content already satisfies. A composer.json label or description is a sync candidate. It may be described as compatible or incompatible with a remote rule. It never satisfies or fails one. R5 with a local label of "Acme Plugin" yields: remote display name unverified, plus a separate note that the local label candidate looks incompatible.
  6. Every local finding needs a quoted artifact. A required local change must cite either a verbatim CLI output line or a measured value from §1. No line and no measurement means it is not a required local change.
    • A row may be marked CLI-enforced only if the CLI output contains a matching error line. If validation printed No problems found, the Required local changes section is empty. Write "none". Never infer a CLI finding from reading composer.json yourself.
    • Every error line the CLI printed appears under Required local changes exactly once: under L1–L5 when the identifier matches, otherwise under L0.
    • Placeholder or example values (example.com, TODO, lorem text) are not CLI findings: L2 and L3 check presence, not plausibility. Mention them under Local candidates if useful, never as a required local change.
  7. Rows are the only vocabulary. Every finding names a row ID from §2 and must match that row's actual subject. Do not attach a finding to the nearest-looking row; a CLI line with no dedicated row is L0. A1 is the license-value comparison and nothing else — an author homepage is not "A1 candidate", it is not in the table, so it is not a finding.
  8. Every emitted row carries its provenance. For a CLI row: the result identifier. For a doc row: the doc URL with its section anchor. Never paraphrase a requirement without naming where it came from.
Show full SKILL.md (901 more words)Show less

4. Store doc map

https://developer.shopware.com/docs/guides/development/testing/store/ is the index of all Store review pages. Always link it in Sources so the user can navigate the set.

content-and-translations is the baseline: read it every run, it backs the table in §2. Read any other page only when its trigger fires, and add its rows to the answer as sourced findings. Never audit the whole set unprompted.

PageCoversRead when
quality-guidelinesNon-negotiable quality, security, compliance rules for every extensionuser asks for a full compliance audit or pre-submission review
content-and-translationsListing text, translations, images, icon, licensealways
store-review-errorsCommon reasons reviewers reject a submissionuser asks why a submission failed, or wants rejection risks
not-allowed-store-behaviorsProhibited patternsextension touches core internals, filesystem, or DB directly
functionality-integrationCorrect integration with core, persistence, public APIsextension has subscribers, entities, or API endpoints
code-qualityCode standards reviewers applyuser asks about code quality, or code-quality checkers were invoked
installation-and-cleanupInstall/update/uninstall and data removalextension implements lifecycle methods or creates tables
cookies-and-privacyCookie registration, GDPR, subprocessorsextension sets cookies, tracks, or sends data to third parties
seo-and-structured-dataSEO output and structured dataextension changes storefront markup, URLs, or meta tags
storefront-performance-and-errorsStorefront performance and error handlingextension ships storefront JS/CSS or template overrides
faqPreview requirements and misc answersuser asks about previews or something the other pages miss

Preconditions here work like §2's: a page you had no trigger to read produces no findings, and you say so rather than guessing at its contents.

5. Response format

Validation status

  • CLI binary and version
  • inspection timestamp
    • builtin checks: pass/fail + exit code (state that --only builtin was used)
  • store-compliance checks: pass/fail + exit code
  • remote Store listing: inspected / not inspected
  • files modified: no

Required local changes — one entry per CLI error line (L1–L5 by identifier, otherwise L0), plus any other Local file / Local artifact row that failed. Empty section if none; write "none".

FindingEvidenceLevelRowSource

Evidence is the verbatim CLI line or the measured value. Source is the identifier and file, or the doc anchor link.

Remote conditions not verified — every emitted row with a remote target, each with its doc anchor link. Then, verbatim:

Store publication readiness cannot be confirmed from local validation alone because the remote Store listing was not inspected.

Local candidates — measured local values and whether each looks compatible with its remote rule, with the rule's source. Explicitly not a pass.

Guidance — only Store-doc-guidance rows (G1, G2), each with its link and the exact modal verb the docs use. Guidance rows appear here only. They are not remote conditions and must not be repeated in that table.

Sources checked — a flat list the user can re-verify independently:

  • CLI path and version
  • the two extension validate commands run (normal and --store-compliance), so the user can re-run them and see the same output
  • the result identifiers relied on; source file paths and grep commands only if a shopware-cli checkout was actually read
  • the Store docs index, as a clickable link, so the user can reach the whole set
  • every doc page actually read, as a clickable full URL with the date read
  • the pages not read, listed by name with the trigger that would have required them, so the user can see what was out of scope rather than assuming it passed
  • anything else not consulted, stated plainly (e.g. "Shopware Account: not accessed")

The response ends here. Do not append a summary, a recap, a next-steps list, or an offer to fix anything: the sections above already say what is wrong and what is unverified, and a summary reintroduces the collapsed local/remote framing the format exists to prevent.

Every documentation source must be a clickable URL, in every section including table rows. content-and-translations § store-listing is not a link. CLI identifiers, local paths and commands are quoted as they are.

Repeating a 100-character URL across eleven rows is tedious, so a table may instead declare its base once directly above itself and carry only anchors in the rows:

Sources below are anchors on https://developer.shopware.com/docs/guides/development/testing/store/content-and-translations.html

with rows reading #store-listing. Use one form or the other. Bare anchors with no declared base are not acceptable — that is the failure this replaces.

6. Self-check

Answer only after all are true:

  • every Level/Target/Source was copied from §2, not reasoned out;
  • every finding names a source the user can open (doc URL) or re-run (CLI identifier, command);
  • the Sources section links the docs index and names the pages not read;
  • no remote-target row appears as a required local change;
  • no ungated precondition row was emitted;
  • every CLI error line appears under Required local changes, as L1–L5 or L0;
  • no CLI-enforced row emitted when the CLI printed No problems found;
  • no row emitted as "N/A";
  • every ungated row emitted, counted against §2 rather than eyeballed;
  • every doc source is a clickable URL, or an anchor under a base declared directly above its table;
  • G rows appear in Guidance only, not in the remote table;
  • the response ends at Sources checked;
  • every finding's row ID matches that row's actual subject;
  • every candidate entry quotes a value that conflicts with a rule, rather than speculating about one;
  • every required local change quotes a CLI line or a measured value;
  • Account-license comparison uses the license value, not the package name;
  • one CLI binary used throughout, and its version is stated;
  • the "Sources checked" section lists what was not inspected as well as what was.

© 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-extension-store of shopware/shopware-cli.

Open the folder on GitHubat commit f20f5ba

Compare with similar skills

Shopware CLI Extension Store 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 Extension Store compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Shopware CLI Extension Store this skillshopware/shopware-cli123—~5.1kAutomated safety check: PassMIT
Configuring Horizoncoollabsio/coolify63k4 repos~898Automated safety check: PassMIT
Tailwindcss Developmentanonaddy/anonaddy4.9k10 repos~865Automated safety check: PassMIT
Fortify Developmentcoollabsio/coolify63k4 repos~1.9kAutomated safety check: PassMIT
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
WooCommerce Code Reviewwoocommerce/woocommerce11k3 repos~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Configuring Horizon

    coollabsio/coolify

    A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.

    63k GitHub starsUsed in 4 repos~898 tokens
    Backend & APIsAuto-check passed
  • Tailwindcss Development

    anonaddy/anonaddy

    Always invoke when the user's message includes 'tailwind' in any form.

    4.9k GitHub starsUsed in 10 repos~865 tokens
    Frontend & DesignAuto-check passed
  • Fortify Development

    coollabsio/coolify

    ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 4 repos~1.9k tokens
    Backend & APIsAuto-check passed
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Sync Translations

    symfony/symfony

    Synchronize translation catalogs across maintained Symfony branches: find messages that newer branches added to the English catalogs but that are still missing from the oldest maintained branch…

    31k GitHub stars~1.9k tokensUpdated today
    Writing & ContentAuto-check passed

More from shopware/shopware-cli

  • Shopware CLI

    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…

    123 GitHub stars~4.9k tokensUpdated today
    Auto-check passed
  • 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 today
    Auto-check passed

Works with

Questions about Shopware CLI Extension Store

What does Shopware CLI Extension Store do?

A skill your agent uses for Shopware Store readiness, publication, submission, or compliance questions about an extension. Shopware CLI Extension Store is an agent skill from shopware/shopware-cli. Use for Shopware Store readiness, publication, submission, or compliance questions about an extension.

When should I use Shopware CLI Extension Store?

Shopware CLI Extension Store fits situations like: shopware Store readiness; compliance questions about an extension.

How do I install Shopware CLI Extension Store in Claude Code?

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

How do I install Shopware CLI Extension Store in Codex?

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

Can I use Shopware CLI Extension Store 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-extension-store -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-extension-store, .gemini/skills/shopware-cli-extension-store, .github/skills/shopware-cli-extension-store and .opencode/skills/shopware-cli-extension-store in your project.

What does Shopware CLI Extension Store need to run?

SKILL.md names no scripts, command-line tools or credentials: Shopware CLI Extension Store is instructions for the agent only.

Does Shopware CLI Extension Store access the network?

SKILL.md names 1 domain. In commands or code: developer.shopware.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Shopware CLI Extension Store 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 Extension Store use?

Shopware CLI Extension Store 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 Extension Store use?

About 5.1k tokens (SKILL.md is roughly 20k 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 Extension Store?

Skills that share tags, products or a category with Shopware CLI Extension Store: Configuring Horizon (coollabsio/coolify, 63k stars), Tailwindcss Development (anonaddy/anonaddy, 4.9k stars), Fortify Development (coollabsio/coolify, 63k stars) and MCP Development (coollabsio/coolify, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Shopware CLI Extension Store?

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 7, 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.