plugins/web/skills/page-langs/SKILL.md
Detect all languages used on a webpage — both declared (html@lang, hreflang alternate links, nested lang= attributes, meta content-language) and actually present in the body text (Google CLD3 via cld3-asm WASM). Reconciles the two signal sets and flags mismatches such as undeclared languages in the body or declared languages absent from the content. Outputs langs.json with detected languages (probability + proportion), all declared language signals, and a reconciliation report. Use for i18n audits, EDS page migrations, hreflang validation, and multilingual content verification. Triggers on: detect languages, page languages, what language, language detection, i18n audit, hreflang, hreflang validation, lang attribute, multilingual page, page-langs, language audit, which language, content language, undeclared language.
npx skillsauth add adobe/skills page-langsInstall 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.
Detect all languages used on a webpage — declared and in the body text.
Node 22+ required. Uses playwright-cli for the browser pass and Google CLD3 (WASM)
for content-based detection.
Install cld3-asm into the skill directory before first use:
if [[ -n "${CLAUDE_SKILL_DIR:-}" ]]; then
SKILL_DIR="${CLAUDE_SKILL_DIR}"
else
SKILL_DIR="$(find ~/.claude -path "*/page-langs" -type d 2>/dev/null | head -1)"
fi
npm install --prefix "$SKILL_DIR"
The WASM model is bundled in the package — no network fetch at runtime.
if [[ -n "${CLAUDE_SKILL_DIR:-}" ]]; then
SKILL_DIR="${CLAUDE_SKILL_DIR}"
else
SKILL_DIR="$(find ~/.claude -path "*/page-langs" -type d 2>/dev/null | head -1)"
fi
COLLECT="$SKILL_DIR/scripts/collect.js"
DETECT="$SKILL_DIR/scripts/detect.mjs"
playwright-cli open "$URL"
If the page has cookie banners or overlays, use the page-prep skill to dismiss
them before continuing.
playwright-cli run-code --filename="$COLLECT" \
| node "$DETECT" --output ./page-langs-output
cat ./page-langs-output/langs.json
Check for common failure modes:
detected is empty → wordCount is very low (page didn't render JS content or is bot-blocked); try --headed or run page-prep firstplaywright-cli lost the session; re-run Step 2 before Step 3declared fields are all null → page has no language markup at all (valid finding, not an error)Output file: ./page-langs-output/langs.json
| Field | Description |
|-------|-------------|
| detected | CLD3 results: language, probability, is_reliable, proportion |
| declared | Structural signals: htmlLang, nestedLangs, hreflang, metaContentLanguage |
| reconciliation | agreement / declaredNotDetected / detectedNotDeclared |
| wordCount | Words in visible body used for CLD3 |
| Field | Meaning |
|-------|---------|
| detectedNotDeclared | Languages in the body not declared in markup — add hreflang or lang= |
| declaredNotDetected | Declared in markup but absent from body — stale hreflang? |
| agreement | Both declared and detected — healthy |
page-prep — invoke before Step 2 to dismiss overlays.wordCount is very low (~< 10 words).en, fr). Structural signals may
be BCP-47 (en-US, x-default). Reconciliation normalises on the primary
subtag; raw values are preserved in declared.references/output-schema.md for the vendoring fallback.tools
Use the run-workflow MCP to discover, compose, execute, publish, and save Adobe Firefly workflows. TRIGGER when: user asks what actions are available, what the MCP can do, how to process images/video/3D via workflow, wants to build/run/save/publish a workflow, OR pastes any workflow/batch/execution ID. BARE ID (UUID/workflowId/batchId) = INSPECT ONLY — call inspect_run, NEVER run_workflow_submit. ALWAYS call list_actions first for capability/discovery questions. DO NOT TRIGGER for direct Firefly API calls without MCP (use firefly-api-specs).
tools
Run predefined featured workflows via run-workflow MCP. TRIGGER when user names a featured workflow (retargeting, banners at scale, localization, packaging, banner advertising, etc.) or asks to run a known marketing/production workflow. Requires run-workflow MCP. ALWAYS call get_featured_workflow before compose_workflow. DO NOT TRIGGER for custom one-off workflows with no named template — use run-workflow skill.
tools
Migrate an Adobe Commerce App Builder project from the Integration Starter Kit or Checkout Starter Kit to the new App Management approach. Run from the root of the App Builder project to be migrated. Pass --auto to skip confirmation prompts (suitable for CI or batch use) — auto mode prints a summary of all Q&A questions answered with their defaults. Pass --doc-scan-only to scan README.md and env.dist for outdated content without modifying any files. Use when the user wants to migrate an App Builder project from the Integration Starter Kit or Checkout Starter Kit to the App Management approach, or mentions upgrading their Adobe Commerce extension architecture.
development
Add or modify webhook interceptors in an Adobe Commerce app. Use when the user wants to intercept Commerce operations to validate input, append data, or modify behavior — before or after execution. Requires a base app initialized with commerce-app-init.