Home / lattifai / lattifai-skills · GitHub

lai-translate SKILL.md skillA

lai-translate from lattifai/lattifai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add lattifai/lattifai-skills/lai-translate@git:20260513.0a51f69

Pins git:20260513.0a51f69 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: lattifai/lattifai-skills
Path: skills/lai-translate/SKILL.md
Versions recorded: 5
Latest version: git:20260513.0a51f69, committed May 13, 2026
First version recorded: Apr 12, 2026
Size: 12,464 bytes
Repository stars: 32
License: MIT

Translate captions into another language (or produce bilingual captions) while preserving segment count, timing, speaker labels, AND source punctuation density (no inserted em-dashes, parentheses, or bracketed glosses unless the source had them — downstream rendering shows every character). **Primary path uses this session's LLM directly — no API key, no model config.** Trigger on "translate captions", "翻译字幕", "翻译成中文/英文", "make bilingual subtitles", or "translate this" when working with…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Caption Translator

> **Preferred model: Claude Sonnet** (cost-efficient for this agent-driven workload). This skill runs on whatever model is active in the parent session — any Claude model works; no hard switch. If you're deliberately on Opus / Haiku, that's fine.

This skill translates using **the agent's own LLM capability** — the model you are running right now. It does not call out to any external translation service by default. Helper scripts do the mechanical parsing, chunking, and writing so the agent only has to produce translations.

**Primary path** (agent-driven, default): `chunk.py` → agent translates → `merge.py` → `validate.py`.
**Secondary path**: `lai translate run` (CLI with its own LLM backend) — use only when there is no agent in the loop (batch pipelines, CI) or when a transcript is too large to fit in the agent's context.

## Invariants

Any violation is a bug; `validate.py` enforces them.

- Segment count, order, `start` / `end`, `speaker` — preserved verbatim
- Every output segment has non-empty text
- Bilingual mode (JSON): source `text` preserved, `translation` non-empty
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add lattifai/lattifai-skills/lai-translate@sha256:37acbd67807be4f4

The line at the top of this page pins the label git:20260513.0a51f69, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_h5cbcabbail57i3f.svg)](https://markdownregistry.com/a/art_h5cbcabbail57i3f)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Apr 12, 2026 and May 13, 2026, about one every 8 days.

version	committed	commit	size	audit
git:20260513.0a51f69 latest	2026-05-13	0a51f69	12,464 B	A	view · diff
git:20260428.4ab9c84	2026-04-28	4ab9c84	11,024 B	A	view · diff
git:20260416.b0c60d0	2026-04-16	b0c60d0	10,305 B	A	view · diff
git:20260416.83f6907	2026-04-16	83f6907	5,564 B	A	view · diff
git:20260412.85d3d73	2026-04-12	85d3d73	4,875 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (12464 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

lattifai/lattifai-skills · 32 stars · license MIT · pushed 2026-11-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_h5cbcabbail57i3f
GET https://markdownregistry.com/api/v1/resolve?ref=lattifai/lattifai-skills/lai-translate
GET https://markdownregistry.com/api/v1/blob/37acbd67807be4f4710a58ce1b20532fa6523d7398a6ce86478cef659f5d1f48

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.