localization
Skill3 starsChanged 2 months agoMITView on GitHub
Add new locale keys with real Russian translations instead of English placeholders — spawns a lightweight Haiku subagent to translate new en.asset entries into proper ru.asset entries. Load whenever adding, renaming, or changing user-facing text keys in Assets/Localization/en.asset and ru.asset.
21 other projects use a version of this.
Adopted by
Most recently taken up by
- parker-brown-family/agent-skillstheir own version, first seen Nov 8, 2026
- AnyOrgName/php-skillstheir own version, first seen Nov 8, 2026
- ghuntley/loomtheir own version, first seen Nov 1, 2026
- jame581/GodotPromptertheir own version, first seen Oct 21, 2026
- PhoenixNest/AGENT-GLOBAL-BASEtheir own version, first seen Oct 20, 2026
- glrodasz/dotfilestheir own version, first seen Oct 17, 2026
Used with
Projects with it also use ab-test-store-listing, app-analytics and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
appeekySkillab-test-store-listing
When the user wants to A/B test App Store product page elements to improve conversion rate. Also use when the user mentions "A/B test", "product page optimization", "test my screenshots", "test my icon", "conversion rate optimization", "CPP", or "custom product pages". For screenshot design, see screenshot-optimization. For metadata optimization, see metadata-optimization.
Also in 3 projects that use this
- appeekySkill
app-analytics
When the user wants to set up, interpret, or improve their app analytics and tracking. Also use when the user mentions "analytics", "tracking", "metrics", "KPIs", "App Store Connect analytics", "install tracking", "funnel", "attribution", or "how is my app performing". For A/B testing, see ab-test-store-listing. For retention metrics, see retention-optimization.
Also in 3 projects that use this
- +10 more from appeeky
Other versions21 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 21
- chen08209/FlClash★ 62ksame name
- appeeky/aso-skills★ 2.2ksame name
- Eronred/aso-skills★ 2.2ksame name
- ghuntley/loom★ 1.7ksame name
- igorescodro/alkaa★ 1.6ksame name
- jame581/GodotPrompter★ 870same name
- bagofwords1/bagofwords★ 463same name
- CamilleScholtz/swmpc★ 239same name
- everpcpc/KMReader★ 118same name
- glrodasz/dotfiles★ 20same name
11 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/issue-clarification-questions.mdcCursor rule
- .cursor/rules/reset-font-assets.mdcCursor rule
- .cursor/rules/src-dotnet-build-release.mdcCursor rule
- .cursor/rules/unity-plugins-before-work.mdcCursor rule
- codex-issueSkill
- commitSkill
- complete-prdSkill
- dependency-docsSkill
- dotnet-buildSkill
- dotnet-testSkill
- generate-imageSkill
- implementSkill
- meeting-joinSkill
- meeting-scheduleSkill
- meeting-startSkill
- plan-reviewSkill
- planSkill
- prSkill
- specifySkill
- unity-e2e-runSkill
- unity-pluginsSkill
- add-terminal-commandSkill
- dependency-docsSkill
- dotnet-benchmarkSkill
- dotnet-buildSkill
- dotnet-testSkill
- end-game-score-calibrationSkill
- flag-assetsSkill
- github-issue-automationSkill
- image-generationSkill
- meeting-joinSkill
- meeting-scheduleSkill
- meeting-startSkill
- milestone-completeSkill
- province-config-generatorSkill
- unity-e2e-runSkill
- unity-pluginsSkill
- unity-prefabsSkill
- unity-scenesSkill
- update-branchSkill
- cursor-meeting-joinSkill
- cursor-meeting-startSkill
- unity-pluginsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
Add the returned Russian values to Assets/Localization/ru.asset under the matching keys, keeping the same key order as en.asset where …
- Very specific: line 56
Don't proactively hunt down and fix old keys where ru.asset still equals en.asset — that's separate cleanup work, not something this skill …
“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
localization
The old pattern (deprecated)
Older specs (e.g. Docs/Specs/26_06_20_00_country-action-cards/plan.md) added new
keys to ru.asset with the same English text as a "placeholder Russian
translation," deferring the real translation to later. Do not do this
anymore. Every new key gets a real Russian translation in the same change
that adds it.
Workflow
- Decide the new key(s) and their English text; add them to
Assets/Localization/en.assetasKey/Valuepairs underEntries(see.claude/rules/unity/localization.mdfor the namespacing convention —menu.*,hud.*,country_name.*, etc.). - Collect the full list of new
Key: Valuepairs (English) just added. - Spawn a translation subagent —
Agenttool,model: "haiku"— with a self-contained prompt that:- Includes every new key and its English value.
- Asks for natural, game-appropriate Russian translations (not
literal/machine-style), preserving any
string.Formatplaceholders ({0},{1}, …) and any markup/formatting tokens unchanged, positioned wherever they'd naturally fall in Russian phrasing. - Asks it to return only the
Key: Valuepairs (Russian value) in the same order, no commentary, so the output can be pasted straight intoru.asset.
- Add the returned Russian values to
Assets/Localization/ru.assetunder the matching keys, keeping the same key order asen.assetwhere practical (not load-bearing, just keeps the two files diffable). - Refresh Unity and check the console for errors from the
LocaleConfigassets.
Why Haiku
Translating short UI strings is a low-reasoning, high-volume task — a
full-capability model is overkill. Route it to a model: "haiku" subagent
to keep cost and latency down; the parent conversation stays on the main
model and should not delegate anything else through this call.
Batching
Batch all new keys from a single feature into one subagent call rather than one call per key — the subagent has no memory between calls, so a single prompt with the full list is both cheaper and gives the translator surrounding context (sibling strings in the same feature) for consistent tone and terminology.
Existing placeholder debt
Don't proactively hunt down and fix old keys where ru.asset still equals
en.asset — that's separate cleanup work, not something this skill
triggers automatically. This skill only applies going forward, whenever a
spec/plan step or ad-hoc change adds new locale keys.
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.