How do I install the Validate Strings skill?

Run npx skillmds@latest add jason0404/validate-strings in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Validate Strings skill do?

Validate Android strings.xml locale resources for missing keys, placeholders, XML safety and scoped brand text risks It is listed under Coding & Dev Tools on SkillMD.

Is Validate Strings safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Validate Strings?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Validate Strings free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Validate Strings?

jason0404 (@jason0404) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Validate Strings by jason0404 — Agent Skill

Name: Validate Strings
Author: jason0404

File contents

Audit Android localization resources for the selected module, source set or flavour.

Workflow

Find src/**/res/values*/strings.xml files within the requested scope.
Use the selected base locale or default values/strings.xml as the source of truth.
Keep separate source sets/flavours clearly separated; do not silently merge unrelated resource scopes.
Invoke android-strings-auditor.
When the user requests a deliverable, invoke android-localization-report-generator.

Validate

Missing and extra string keys.
Duplicate keys and malformed XML.
Placeholder signatures such as %s, %1$s, %d, %f, escaped %, newlines and formatted content.
XML escaping, CDATA/HTML markup and Android build-safety risks.
translatable="false" handling when applicable.
Brand-keyword contamination only when the user provides intended/forbidden brand rules.
Potential overflow or RTL risks only when matching UI layouts/composables can be inspected.

Output

Provide locale folders inspected, issue counts, exact file/key findings, severity, recommended correction and any limits of the analysis.

Do not change translations unless explicitly asked.

Frequently asked questions

Validate Strings