More room for your next idea. Membership from $9.99/month.Take a look

Localization QA Studiov1.0.0

Make multilingual app copy reviewable and reusable. Check real catalog keys and named placeholders, inspect labeled source fallback, preview four screens in LTR/RTL, apply browser edits and rebuild exact locale JSON, XLIFF and quality evidence from the edited project.

See what you can make

Jump to a momentExplore the workflow
Made with this SkillAn editable multilingual review and translation handoff

Four locales · four screens · actual edit and rebuild

Open full example

What you get

An editable multilingual review and translation handoff

What you can make

  • Find missing copy, named-argument mismatches and unsupported catalog formats.
  • Preview authored locales and RTL screens, apply edits and download the current project.
  • Rebuild exact locale JSON, XLIFF handoffs, pseudo copy and structural evidence.
Explore delivered files6 groups
  • index.html + project.json
  • messages/<locale>.json
  • xliff/<target>.xlf
  • pseudo/en-XA.json
  • report.json + findings.csv
  • handoff.md + delivery-manifest.json

Good fit

Product teams preparing multilingual app copy and a reviewable translator handoff.

Know the limits

Supports nested strings and simple named placeholders; linguistic quality and actual framework behavior need review.

About this skill

Capabilities: missing/empty/extra keys, named argument mismatches, unsupported-format review, unchanged-copy review, Unicode character-budget warnings, thirteen source messages, four authored locale fixtures, four screen previews, actual RTL direction, expanded copy, message search and current edited JSON downloads.

Deliverables: the original fictional Atlas language room, editable project JSON, nested messages per locale, target XLIFF 2.0 files, source pseudo-catalog, structural report, findings CSV, integration handoff and SHA-256 manifest. Missing translations remain missing in the exported files.

Read the full workflow

First run: Python 3.10+ standard library, offline. Run scripts/build-localization.py --input examples/project.json --output ./language-room. Apply a reviewed translation in the browser, download edited-project.json and rebuild into a fresh directory to refresh JSON, XLIFF and findings.

Validation: actual missing Chinese CTA and German argument mismatch detection, real browser edit/download/rebuild, zero Chinese findings after the reviewed edit, parsed XLIFF units and missing targets, placeholder-preserving pseudo copy, RTL preview, inert text, unsafe-key/duplicate-locale rejection, desktop/mobile layout and exact archive re-execution.

Version 1.0.0: original MIT workflow, validator and interface. Supports nested string catalogs and simple {name} placeholders, not plural objects or universal ICU parsing. Linguistic meaning, actual fonts/layout and framework runtime behavior need separate review. No automatic translation or remote TMS call. $4.99 one-time; eligible active Premium membership includes this package.

FROM PACKAGE TO FIRST RESULT

Your first complete localization review.

Build the fictional Atlas travel product with thirteen source messages, four authored locales and four screen previews. Inspect a missing Chinese CTA and a mismatched German argument, then edit reviewed copy and regenerate the implementation files.

View example result
US$4.99 · MIT licensePython 3.10+ · offlineNo API key or paid provider
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/localization-qa-studio

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.

  3. 03

    Run the included sample

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/localization-qa-studio
    python3 scripts/build-localization.py --input examples/project.json --output ./language-room
    Your first result

    Select Chinese and repair the missing hero CTA; apply the edit, download the full edited project and rebuild to refresh JSON/XLIFF/reports. Explore all four screens, Arabic RTL, expanded copy and search. Inspect source fallback labels instead of treating them as completed translation.

    Python 3.10+ standard library, offline. Supports nested string catalogs and simple {name} placeholders. Plural objects, ICU/literal brace formats and real framework/runtime checks need an adapter. Authored translations require language review; character counts do not prove rendered fit. No translation service or TMS is called.

    If language-room already exists, change the output to ./language-room-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use Localization QA Studio at .agents/skills/localization-qa-studio. Read SKILL.md and review scripts/build-localization.py. Run examples/project.json into a new output folder and show me all generated files. Keep fictional sample content clearly labeled.

Ready to use your own facts?

Copy examples/project.json to a new input file, replace all fictional facts, and generate into a new folder. Review the content before using or publishing it; the generator does not independently verify claims.

Reviews0

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get Localization QA Studio?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

What files can this workflow generate?

The documented 1.0.0 workflow lists: index.html + project.json; messages/<locale>.json; xliff/<target>.xlf; pseudo/en-XA.json; report.json + findings.csv; handoff.md + delivery-manifest.json. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

What should I check before using the result?

Python 3.10+ standard library, offline. Supports nested string catalogs and simple {name} placeholders. Plural objects, ICU/literal brace formats and real framework/runtime checks need an adapter. Authored translations require language review; character counts do not prove rendered fit. No translation service or TMS is called.

$4.99One-time purchase