Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/starcat-app/Starcatnpx agentmods add skills/starcat-app/starcat/starcat-localization-syncWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/starcat-app/starcat/starcat-localization-sync)<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-localization-sync"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-localization-sync/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-localization-sync"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-localization-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.01998 |
| Opus 5.5 | $0.00042 | $0.00799 |
| Sonnet 5.5 | $0.00021 | $0.00400 |
| Haiku 4.5 | $0.00011 | $0.00200 |
Grade A, and why
starcat-localization-sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Starcat 本地化同步
处理 Starcat 运行时 String Catalog 与公开本地化仓库之间的完整生命周期。先读
references/localization-map.md，再按本文件选择执行路径。
硬闸（2026-08-18）：日常功能开发往 Starcat/Resources/Localizable.xcstrings 加 key / 改文案，禁止走本 skill，禁止 scripts/xcstrings_patch.py --apply，禁止 Python/jq 读入全文再写回。只允许按 docs/5-规范/i18n-军规.md 铁律 #6 做相邻 key 关键词局部匹配。本 skill 仅在 dong4j 明确要求本地化同步 / 导入导出 / 审计时使用。
核心模型
始终区分四个阶段，不得用后一个阶段的状态掩盖前一个阶段缺失的证据：
| 阶段 | 含义 | 允许结果 |
|---|---|---|
| AI 初稿 | 机器翻译完成，尚未批准 | needs-review-translation |
| 翻译批准 | 人工审核，或维护者明确接受 AI 风险 | translated / final / signed-off |
| 导入 Catalog | 已批准 target 写回 App | locale 仍可保持 draft |
| 正式发布 | 编译、AppLocale、UI 和 RTL 门禁通过 | releaseStatus=released |
“翻译批准”不等于“正式发布”。维护者跳过母语审核时，也不能自动跳过 UI、编译和 Arabic RTL 验收。
硬性规则
- 所有说明使用中文；命令、路径、locale、key、JSON 字段保持原文。
- 写入前先给出范围、状态变化和验证方案，等用户确认。
- 运行时单一来源是
Starcat/Resources/Localizable.xcstrings；公开协作单一来源是supports/starcat-localization/Translation Packages/。 supports/starcat-localization是独立 Git 仓库；分别检查、提交和回滚，不混入 Starcat 主仓库 commit。- 新增或修改用户可见文案时，同时维护
en和zh-Hans。 - 新增 key 使用
{section}.{subsection}.{component}，禁止_。 - AI 生成只能写
needs-review-translation。 - 默认只导入
translated、final、signed-off；禁止普通流程使用--allow-unreviewed。 - 可执行代码块、行内代码、URL 和占位符必须逐字保留。
.xcstrings只做局部编辑；用jq empty校验，禁止用 formatter 重写全文。- 不使用
String(localized:)或NSLocalizedString；Swift 代码任务先读 i18n 规范。 - 未观察到的母语质量、UI 或 RTL 验收不得写成已完成。
任务路由
| 用户目标 | 入口 |
|---|---|
| 同步最新 key/source | python3 supports/scripts/starcat-localization.py export |
| 查看完成度 | python3 supports/scripts/starcat-localization.py report --format json |
| 审计包和发布门禁 | python3 supports/scripts/starcat-localization.py audit |
| 生成/续跑 AI 初稿 | python3 supports/starcat-localization/scripts/translate_draft.py |
| 定向重译 | translate_draft.py --key <key> --apply |
| 恢复技术字面量 | translate_draft.py --repair-protected-literals --apply |
| 人工审核后导入 | starcat-localization.py import / import-all |
| 维护者接受 AI 初稿 | python3 supports/starcat-localization/scripts/promote_drafts.py |
| 正式开放语言 | 先导入，再扩展 AppLocale，最后提升 releaseStatus |
修补已有 .xcstrings |
scripts/xcstrings_patch.py show/set/set-batch |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 143 lines · 105 tokens per session scan A 8e875dfb33f1
starcat-localization-sync is a skill published in the GitHub repository starcat-app/Starcat (211 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 1,998 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
my-wiki
A skill for managing a local Markdown knowledge vault that stores captured webpages, PDFs, Office files, notes, images, folders, and ZIP files. It links preserved source material, called References, to durable topic pages, called Concepts.
memobase
A Russian-language skill for searching a local knowledge base built from documents and other sources such as web pages, YouTube, audio, and Obsidian notes.
cet-skill
CET-4 and CET-6 exam preparation coach for original CET-style practice, diagnostic feedback, writing and translation correction, reading/listening drills, and study planning.
operating-system-visualization
Use this skill whenever the user wants visual learning for operating systems, process states, CPU scheduling, Gantt charts, synchronization, semaphore/PV problems, deadlock, Banker's algorithm, memory management, paging, address translation, page replacement, file systems, disk scheduling, or 408 OS review.
chromadb-manager
Query the ChromaDB Manager document base over MCP.
llm-wiki
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture, schema, or organization decisions; operational ingest/query/lint work uses dedicated skills.