Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add JamestsaiTW/Taiwanese-Mandarin-Translate-Skill --skill taiwanese-mandarin-translategit clone --depth 1 https://github.com/JamestsaiTW/Taiwanese-Mandarin-Translate-SkillWrote 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/jamestsaitw/taiwanese-mandarin-translate-skill/taiwanese-mandarin-translate)<a href="https://agentmods.dev/skills/jamestsaitw/taiwanese-mandarin-translate-skill/taiwanese-mandarin-translate"><img src="https://agentmods.dev/badge/skills/jamestsaitw/taiwanese-mandarin-translate-skill/taiwanese-mandarin-translate/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/jamestsaitw/taiwanese-mandarin-translate-skill/taiwanese-mandarin-translate"><img src="https://agentmods.dev/badge/skills/jamestsaitw/taiwanese-mandarin-translate-skill/taiwanese-mandarin-translate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.03028 |
| Opus 5 | $0.00019 | $0.01514 |
| Sonnet 5 | $0.00008 | $0.00606 |
| Haiku 4.5 | $0.00004 | $0.00303 |
Grade A, and why
taiwanese-mandarin-translate 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 12d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taiwanese Mandarin Translation and Localization
Use this skill when the task needs English content translated into Traditional Chinese used in Taiwan, or when existing Chinese copy should be rewritten into more natural Taiwanese Mandarin.
Style positioning
- Default to Taiwanese Mandarin / Taiwan Mandarin (台灣華語): natural, contemporary wording that Taiwan readers would comfortably use in products, documentation, and general writing.
- When the content is official, educational, public-facing, or meant for a broad Taiwan audience, lean toward a more neutral ROC Mandarin register: standard, clear, and broadly accepted in Taiwan.
- Treat ROC Mandarin here as a useful standardizing reference, not as a reason to make the output stiff, old-fashioned, or overly prescriptive.
Register decision rules
Use the lightest register that fits the audience:
- Default to natural Taiwanese Mandarin for UI copy, product text, help content, blog posts, marketing copy, developer documentation, and general prose.
- Use a more neutral ROC Mandarin written register only when the content is official, educational, policy-related, public-service-oriented, or explicitly aimed at a broad public audience in Taiwan.
- Do not over-formalize ordinary product or technical content. Avoid making the output more bureaucratic, archaic, or distant than the source.
- Keep project convention first. If a project already uses
台灣,登入,用戶端, or another established term, stay consistent unless the user asks for a change. - Use
臺consistently only when the source, project, or context is official, governmental, educational, or highly formal. Otherwise, follow the existing convention.
What this skill borrows from ROC Mandarin
A widely used definition frames ROC Mandarin as a Taiwan-wide standard variety of Modern Standard Chinese and a common language across different groups in Taiwan. Use those strengths in practice:
- Prefer wording that is widely understandable across Taiwan, not tied to one narrow subculture or imported PRC usage.
- Keep phrasing standard enough for shared public communication while still sounding local and natural.
- Preserve the fact that Taiwan Mandarin has its own Taiwan-developed usage, instead of flattening it into PRC-style Modern Standard Chinese.
- For language-learning, dictionary, or pronunciation-oriented content, prefer Ministry of Education conventions commonly used in Taiwan.
What ships with it
5 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.
- 12d ago First seen · 200 lines · 39 tokens per session scan A 91e5c0d2b3ee
taiwanese-mandarin-translate is a skill published in the GitHub repository JamestsaiTW/Taiwanese-Mandarin-Translate-Skill (4 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 3,028 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
localization
Use when implementing localization (i18n/l10n) — TranslationServer, CSV/PO translation files, locale switching, RTL support, and pluralization in Godot 4.3+.
neo4j-document-import-skill
Ingests unstructured and semi-structured documents into Neo4j as a knowledge graph. Use when chunking PDFs, HTML, plain text, or Markdown; extracting entities and relationships from text with an LLM (SimpleKGPipeline, neo4j-graphrag); loading JSON via apoc.load.json; building Document→Chunk→Entity graph structures; or…
neo4j-driver-dotnet-skill
Neo4j .NET Driver v6 — IDriver lifecycle, DI registration (singleton), ExecutableQuery fluent API, ExecuteReadAsync/ExecuteWriteAsync managed transactions, IResultCursor (FetchAsync/ ToListAsync), record value access (.Get /As ), null safety, UNWIND batching, temporal types, await using, EagerResult, object mapping…
neo4j-getting-started-skill
Orchestrates zero-to-running-app in 8 stages — prerequisites → context → provision → model → load → explore → query → build. Each stage reads its own reference file. Supports HITL and fully autonomous operation. Use when starting a new Neo4j project from scratch, provisioning Aura, generating synthetic data, building…
neo4j-aura-agent-skill
Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance. Use when configuring Aura Agent tools (CypherTemplate, SimilaritySearch, Text2Cypher), setting system prompts, deploying agents to REST or MCP endpoints, or invoking agents with…
neo4j-driver-python-skill
Neo4j Python Driver v6 — driver lifecycle, executequery, managed and explicit transactions, async (AsyncGraphDatabase), result handling, data type mapping, error handling, UNWIND batching, connection pool tuning, and causal consistency. Use when writing Python code that connects to Neo4j via GraphDatabase.driver…