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 lattifai/omni-captions-skills --skill omnicaptions-translategit clone --depth 1 https://github.com/lattifai/omni-captions-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/lattifai/omni-captions-skills/omnicaptions-translate)<a href="https://agentmods.dev/skills/lattifai/omni-captions-skills/omnicaptions-translate"><img src="https://agentmods.dev/badge/skills/lattifai/omni-captions-skills/omnicaptions-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/lattifai/omni-captions-skills/omnicaptions-translate"><img src="https://agentmods.dev/badge/skills/lattifai/omni-captions-skills/omnicaptions-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 | $0.00035 | $0.02208 |
| Opus 5 | $0.00017 | $0.01104 |
| Sonnet 5 | $0.00007 | $0.00442 |
| Haiku 4.5 | $0.00003 | $0.00221 |
Grade A, and why
omnicaptions-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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caption Translation
Default: Claude native translation (no API key needed)
Use Gemini API only when user explicitly requests it.
Default Workflow (Claude)
- Read the caption file
- Translate using Claude's native ability
- Write output with
_Claude_{lang}suffix
Gemini API (Optional)
Use CLI when user requests Gemini:
omnicaptions translate input.srt -l zh --bilingual
Output: input_Gemini_zh.srt
When to Use
- Translate SRT/VTT/ASS to another language
- Generate bilingual captions (original + translation)
- Translate YouTube video transcripts
- Need context-aware translation (not line-by-line)
When NOT to Use
- Need transcription (use
/omnicaptions:transcribe) - Just format conversion without translation (use
/omnicaptions:convert)
Setup
pip install omni-captions-skills --extra-index-url https://lattifai.github.io/pypi/simple/
API Key
Priority: GEMINI_API_KEY env → .env file → ~/.config/omnicaptions/config.json
If not set, ask user: Please enter your Gemini API key (get from https://aistudio.google.com/apikey):
Then run with -k <key>. Key will be saved to config file automatically.
Context-Aware Translation
LLM-based translation is superior to traditional machine translation because it understands context across multiple lines:
Why Context Matters
| Approach | Problem | Result |
|---|---|---|
| Line-by-line | No context | Robotic, disconnected translations |
| Batch + Context | Sees surrounding lines | Natural, coherent dialogue |
How It Works
┌─────────────────────────────────────────┐
│ Batch size: 30 lines │
│ Context: 5 lines before/after │
├─────────────────────────────────────────┤
│ [5 previous lines] → context │
│ [30 current lines] → translate │
│ [5 next lines] → preview │
└─────────────────────────────────────────┘
Benefits:
- Speaker continuity - maintains character voice
- Split sentences - handles dialogue spanning multiple lines
- Idioms & culture - adapts cultural references naturally
- Pronoun resolution - correct he/she/they based on context
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 · 290 lines · 35 tokens per session scan A cf6227e1241e
omnicaptions-translate is a skill published in the GitHub repository lattifai/omni-captions-skills (22 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 2,208 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 2026-08-30.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
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.