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 jianshuo/claude-skills --skill wjs-translating-subtitlesgit clone --depth 1 https://github.com/jianshuo/claude-skillsWrote 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/jianshuo/claude-skills/wjs-translating-subtitles)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-translating-subtitles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-translating-subtitles/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/jianshuo/claude-skills/wjs-translating-subtitles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-translating-subtitles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 106 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00132 | $0.02659 |
| Opus 5 | $0.00066 | $0.01329 |
| Sonnet 5 | $0.00026 | $0.00532 |
| Haiku 4.5 | $0.00013 | $0.00266 |
Grade A, and why
wjs-translating-subtitles 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 13d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wjs-translating-subtitles
Source-language SRT in → target-language (or bilingual) SRT out. This skill is text-only. Burn-in lives in /wjs-burning-subtitles; voice dub in /wjs-dubbing-video.
When to use
- User has an SRT in language A and wants it in language B.
- User pasted a transcript (with or without timestamps) and wants a translation that becomes an SRT.
- User has an SRT but cues end mid-sentence — this skill's re-segmentation step fixes that.
When NOT to use
- No source-language SRT yet → run
/wjs-transcribing-audiofirst. - User wants burned-in subtitles → finish translation here, then
/wjs-burning-subtitles. - User wants voice dub → finish translation here, then
/wjs-dubbing-video.
Pick the target
Resolve target from the user's phrasing once, don't re-ask:
- "翻成中文 / 中文字幕 / 中文配音" →
zh-CN. - "translate to English / English subs / English dub" →
en. - "bilingual" / "双语" → produce both
.<source>.srtand.<target>.srt(and optionally a combined.<source>-<target>.srt). - Ambiguous → default to whichever the user has historically chosen in the project.
Simplified Chinese and English are fully validated. Other targets (Japanese, Korean, French, etc.) work via the same rules; the bottleneck is TTS-voice availability if dubbing follows — see /wjs-dubbing-video before promising.
Shared translation principles
- Prioritize meaning over literal wording.
- Use concise subtitle-style language — viewers read at ~3 wps for Chinese, ~3–4 wps for English; lines that exceed that go off-screen before they can be read.
- Preserve the tone of the speaker. Casual source → casual target; formal source → formal target.
- Do not over-translate names, brands, cultural references, or technical terms.
- Keep numbers, dates, names, and places accurate.
- If a phrase has no exact equivalent, translate the meaning naturally. No literal/word-for-word constructions.
- Avoid stiff, machine-translated output.
Translating into Simplified Chinese (zh-CN)
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.
- 13d ago First seen · 203 lines · 132 tokens per session scan A 3415a88f9b4e
wjs-translating-subtitles is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 23d ago), licensed MIT. It adds 132 tokens to every session and 2,659 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
baoyu-translate
A translation workflow for converting articles and other text into another language. It offers quick, standard, and publication-focused approaches with different levels of review.
hreflang-international
International / multilingual SEO audit focused on hreflang correctness. Detects and diagnoses the most common (and ranking-damaging) hreflang mistakes: missing or broken return tags, wrong language/region codes, missing x-default, self-referencing errors, conflicts between hreflang and canonical, and inconsistent…
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
i18n-parity
MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, mirrored READMEs, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change…
internationalization
Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled…
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.