translate-android-locale
Skill432 starsChanged 4 months agoMITView on GitHub
Generate, critique, install, and validate AI-assisted Android string-resource translations for Hermes-Relay. Use when adding a locale, refreshing a locale after English changes, or applying canonical translation corrections.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- website/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- relay-serverSkill
- androidSkill
- hermes-relay-desktop-setupSkill
- hermes-relay-doctorSkill
- hermes-relay-pairSkill
- hermes-relay-self-setupSkill
- hermes-relay-statusSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read docs/translation-playbook.md and docs/localization.md completely.
- Distinctive: line 17
Use a fresh model context to critique meaning, naturalness, glossary consistency, and sensitive strings.
- Very specific: line 25
Add the locale to AppLanguage, the Appearance label map, picker-label resources, locales_config.xml, and AppLanguageTest.
- Very specific: line 27
Keep the registry at ai-translated until a fluent review PR is recorded.
- Very specific: line 28
Run the locale validator, both flavor compilations, and Android lint as documented in docs/localization.md.
- Distinctive: line 31
Keep one locale per commit.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Translate Android locale
- Read
docs/translation-playbook.mdanddocs/localization.mdcompletely. Prepare a non-shipping draft:
python scripts/android-locale-harness.py prepare <bcp47-tag> "<native name>"- Translate both draft catalogs under
build/i18n/<tag>/in semantic batches. Protect resource identifiers, XML, markup, escapes, and placeholders. - Use a fresh model context to critique meaning, naturalness, glossary consistency, and sensitive strings. Apply justified corrections.
Install only after the draft is complete:
python scripts/android-locale-harness.py install <bcp47-tag>- Add the locale to
AppLanguage, the Appearance label map, picker-label resources,locales_config.xml, andAppLanguageTest. - Keep the registry at
ai-translateduntil a fluent review PR is recorded. - Run the locale validator, both flavor compilations, and Android lint as
documented in
docs/localization.md.
Keep one locale per commit. Do not mix signing, version, or release changes into translation commits. Apply later corrections to the canonical locale catalog and preserve contributor credit.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

