Agent skill

Subtitle Translator

by MaKTaiL in MaKTaiL/gemini-srt-translator

Translates SRT and ASS subtitle files, or subtitles embedded in video, into another language using the gst agent CLI and the assistant's own translation.

MITAuto-check passedMedia & Creative

Install Subtitle Translator

skills CLI

$ npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install MaKTaiL/gemini-srt-translator subtitle-translator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/MaKTaiL/gemini-srt-translator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/gemini_srt_translator .claude/skills/subtitle-translator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "subtitle-translator" agent skill from https://github.com/MaKTaiL/gemini-srt-translator/tree/main/gemini_srt_translator into .claude/skills/subtitle-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subtitle-translator", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/MaKTaiL/gemini-srt-translator/tree/main/gemini_srt_translator

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install MaKTaiL/gemini-srt-translator subtitle-translator --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MaKTaiL/gemini-srt-translator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/gemini_srt_translator .agents/skills/subtitle-translator && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "subtitle-translator" agent skill from https://github.com/MaKTaiL/gemini-srt-translator/tree/main/gemini_srt_translator into .agents/skills/subtitle-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subtitle-translator", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install MaKTaiL/gemini-srt-translator subtitle-translator --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MaKTaiL/gemini-srt-translator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/gemini_srt_translator .cursor/skills/subtitle-translator && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "subtitle-translator" agent skill from https://github.com/MaKTaiL/gemini-srt-translator/tree/main/gemini_srt_translator into .cursor/skills/subtitle-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subtitle-translator", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/MaKTaiL/gemini-srt-translator.git --path gemini_srt_translator

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install MaKTaiL/gemini-srt-translator subtitle-translator --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MaKTaiL/gemini-srt-translator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/gemini_srt_translator .gemini/skills/subtitle-translator && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "subtitle-translator" agent skill from https://github.com/MaKTaiL/gemini-srt-translator/tree/main/gemini_srt_translator into .gemini/skills/subtitle-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subtitle-translator", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install MaKTaiL/gemini-srt-translator subtitle-translator

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/MaKTaiL/gemini-srt-translator.git skills-src && mkdir -p .github/skills && cp -r skills-src/gemini_srt_translator .github/skills/subtitle-translator && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "subtitle-translator" agent skill from https://github.com/MaKTaiL/gemini-srt-translator/tree/main/gemini_srt_translator into .github/skills/subtitle-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subtitle-translator", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install MaKTaiL/gemini-srt-translator subtitle-translator --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MaKTaiL/gemini-srt-translator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/gemini_srt_translator .opencode/skills/subtitle-translator && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "subtitle-translator" agent skill from https://github.com/MaKTaiL/gemini-srt-translator/tree/main/gemini_srt_translator into .opencode/skills/subtitle-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "subtitle-translator", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: subtitle-translator
GitHub stars: 357
Token cost: ~1.4k tokens
SKILL.md length: 591 words
Files: 12
Skills in repo: 1
Repo updated: Sep 1, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Translates SRT and ASS subtitle files, or subtitles embedded in video, into another language using the gst agent CLI and the assistant's own translation.

Works in 4 steps: Start a Translation Session → Translate In-Context & Commit Translated… → Repeat Until Complete → …
Translating an .srt or .ass subtitle file into another language
SKILL.md covers 🎯 Role & Agent Protocol…, When to Use, Subtitle Translation Protocol and Translation Rules
Runs Python scripts from its folder; calls uv and poetry

What it does

The agent itself performs the translation inside its own context, and no API key is needed because the `gst agent` protocol runs locally. It opens a session with `gst agent start`, given an input file (.srt, .ass, or a video such as .mp4 or .mkv whose embedded subtitles are extracted automatically) and a target language, then works through the subtitle lines batch by batch.

Options set the batch size (100 lines by default), how many preceding lines go into the context fields, a custom output path, a description with background notes such as a series name or character tone, and whether to resume earlier progress. Context-aware translation keeps tone and gender agreement consistent across multi-part dialogue. If gst is not on the path, the skill points to the project's virtual environment or to uv run and poetry run. External translation scripts are not to be used.

When your agent uses it

Translating an .srt or .ass subtitle file into another language
Translating subtitles embedded in an .mp4 or .mkv video
Keeping character tone and gender agreement consistent across dialogue
Resuming an interrupted subtitle translation

Example prompts

“Translate movie.srt into French.”
“The subtitles in lecture.mkv need to be in Spanish, and it is a university physics lecture.”
“Translate episodes/finale.ass into German, noting that the main character speaks formally.”
“Restart the translation of movie.srt from scratch instead of resuming.”

Requirements

The gst command-line tool, installed globally or in a project virtual environment

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Start a Translation Session
Translate In-Context & Commit Translated Batch
Repeat Until Complete
Cleanup Temporary Files

What it can do on your machine

Read from SKILL.md and the folder at commit f61bbfb. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
- uv
- poetry
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Subtitle Translator loads about 1.4k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 591 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~77
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from MaKTaiL/gemini-srt-translator at commit f61bbfb, republished under its MIT licence (© MaKTaiL). 591 words, ~1,371 tokens.

Download SKILL.mdSave it as .claude/skills/subtitle-translator/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.

name: subtitle-translator
description: Translate subtitle files (SRT, ASS) and video/media with embedded subtitles into any target language with high linguistic quality, sliding context window, timestamp alignment, and formatting preservation. Use when the user asks to translate a subtitle file (.srt, .ass) or video subtitles.

Subtitle Translator Skill

🎯 Role & Agent Protocol (CRITICAL)

When this skill is invoked:

YOU ARE THE TRANSLATOR: You (the AI assistant) perform the translation directly in your context window using your own linguistic intelligence.
NO API KEY REQUIRED: Do NOT ask the user for an API key or external credentials. The gst agent protocol runs completely locally and does not require an API key.
DO NOT RUN EXTERNAL TRANSLATION SCRIPTS: Do NOT look for or execute external Python scripts. Use ONLY the gst agent CLI commands below.
VIRTUAL ENVIRONMENT EXECUTION: gst may be installed in a project virtual environment (.venv or venv) rather than globally. If gst is not recognized:
- Use the virtual environment binary: .venv/bin/gst (Linux/macOS) or .venv\Scripts\gst.exe (Windows)
- Or use environment package runners: uv run gst ... / poetry run gst ...

When to Use

When the user asks to translate a subtitle file (.srt or .ass) into another language.
When translating multi-part dialogue requiring context awareness and consistent character tone/gender agreement.
When working with video files (.mp4, .mkv, etc.) that contain extractable subtitle streams.

Subtitle Translation Protocol

Step 1: Start a Translation Session

Run the start command to initialize the session and receive the first batch of subtitle lines:

bash

gst agent start <INPUT_FILE> -l "<TARGET_LANGUAGE>" [--batch-size N] [--context-size N] [--description "<OPTIONAL_CONTEXT>"] [--pretty]

<INPUT_FILE> can be a subtitle file (.srt, .ass) or a video file (.mp4, .mkv, .avi, etc. — embedded subtitles will be automatically extracted).

CLI Options Reference

Flag	Description	Default
`-l, --target-language`	Target language name (e.g. `"French"`, `"Spanish"`)	Required
`-b, --batch-size`	Number of subtitle lines per batch	`100`
`--context-size`	Preceding lines to include in context fields	`0` (agent retains chat history)
`-o, --output-file`	Custom output subtitle path	`<input>_translated.srt/.ass`
`-d, --description`	Background context notes (e.g. series name, character tone)	None
`--pretty`	Pretty-print JSON responses with indentation	`false` (compact JSON)
`--no-resume`	Start fresh without resuming previous `.progress`	`false`

The CLI outputs a JSON response with next_batch containing:

batch: Array of [{"index": "0", "text": "Original text"}, ...] to translate.
original_context: Previous original source lines (empty by default unless --context-size > 0 is passed).
translated_context: Previous translated lines for continuity (empty by default unless --context-size > 0 is passed).

Optimal Batch Size Guidance (-b / --batch-size is optional, defaults to 100): As an agent, select the batch size you find most optimal for your model capabilities and the file length:

Recommended Default (80–120 lines): Optimal balance between narrative context, translation accuracy, and fast validation.

High-Capacity Models: Feel free to use 100–150 lines to translate full scenes in fewer turns.

Short Files / Anime Episodes (< 300 lines): 60–80 lines provides 3–4 quick, responsive turns.

Constrained Output / Local Models: Use 40–60 lines to guarantee the full JSON array fits comfortably within the model's output generation limits.

Show full SKILL.md (156 more words)Show less

Step 2: Translate In-Context & Commit Translated Batch

Translate each item in batch into the target language, preserving the exact item count and indices.
Save the translated JSON array to a temporary file (e.g. batch_1_translated.json).
Commit the file:

bash

gst agent commit <INPUT_FILE> --data-file batch_1_translated.json

Commit Data Format:

json

[
  { "index": "0", "text": "Bonjour le monde !" },
  { "index": "1", "text": "Comment vas-tu aujourd'hui ?" }
]

Step 3: Repeat Until Complete

Each successful commit automatically saves progress and returns the next_batch. Repeat Step 2 until the response returns "status": "completed".

Step 4: Cleanup Temporary Files

Delete the temporary batch JSON files (e.g. batch_1_translated.json) either progressively as each batch is committed or after the entire translation session finishes, keeping the workspace clean.

Helper Commands

bash

gst agent status <INPUT_FILE> [--pretty]   # Check progress status
gst agent next <INPUT_FILE> -l "<TARGET_LANGUAGE>" [--pretty] # Re-fetch current pending batch
gst agent reset <INPUT_FILE> [--pretty]    # Reset translation progress

Translation Rules

Translation Item Parity: The output JSON array must contain the exact same number of items with identical indices (index).
Formatting Preservation: Preserve all newlines (\n), italic tags (<i>...</i>), and ASS styling tags ({\an8}, {\pos(...)}, etc.).
Punctuation & Tone: Maintain dialogue flow, character voice, and natural target language phrasing without altering structural markers.

Files

SKILL.md and 11 other files in gemini_srt_translator of MaKTaiL/gemini-srt-translator.

SKILL.md
__init__.py
agent_cli.py
cli.py
ffmpeg_utils.py
helpers.py
logger.py
main.py
pricing.json
session.py
skill.py
utils.py

Open the folder on GitHubat commit f61bbfb

Compare with similar skills

Subtitle Translator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Subtitle Translator compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Subtitle Translator this skillMaKTaiL/gemini-srt-translator	357	—	~1.4k	Automated safety check: Pass	MIT	1 mo ago
Adaptationdanjdewhurst/story-skills	283	1 repos	~3.5k	Automated safety check: Notes	MIT	yesterday
Animejsboraoztunc/skills	397	2 repos	~828	Automated safety check: Pass	Apache-2.0	1 mo ago
Youtube PublishAndonywang123/Epost	197	—	~3.4k	Automated safety check: Warn	None	1 mo ago
Vocab Lessonreceptron/mulmocast-cli	475	—	~3.1k	Automated safety check: Notes	None	today
Video Translatecalesthio/OpenMontage	66k	—	~2.7k	Automated safety check: Pass	AGPL-3.0	6 days ago

Similar skills

Adaptation
danjdewhurst/story-skills
This skill should be used when the user asks to "make an audiobook", "narration script", "narrator", "ACX", "Findaway", "pronunciation guide", "how long is the audiobook", "adapt to a screenplay"…
283 GitHub starsUsed in 1 repo~3.5k tokens
Media & CreativeAuto-check: notes
Animejs
boraoztunc/skills
Anime.js adapter patterns for HyperFrames. An agent skill from boraoztunc/skills.
397 GitHub starsUsed in 2 repos~828 tokens
Media & CreativeAuto-check passed
Youtube Publish
Andonywang123/Epost
Prepare an English YouTube release with local Chinese-to-English translation, subtitles and cover localization, then use a deterministic script connected to dedicated Chrome and YouTube Studio to…
197 GitHub stars~3.4k tokensUpdated 1 mo ago
Media & CreativeAuto-check: warnings
Vocab Lesson
receptron/mulmocast-cli
Create a vocabulary learning lesson MulmoScript with multi-section structure (word display, examples with voiceover, explanation, review with translation).
475 GitHub stars~3.1k tokensUpdated today
Media & CreativeAuto-check: notes
Video Translate
calesthio/OpenMontage
Translate and dub existing videos into multiple languages using HeyGen.
66k GitHub stars~2.7k tokensUpdated 6 days ago
Media & CreativeAuto-check passed
Seedance Vocab Es
Emily2040/seedance-2.0
This skill should be used when the user asks for Spanish Seedance 2.0 prompt wording, Spanish cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into…
7.6k GitHub starsUsed in 1 repo~1.1k tokens
Media & CreativeAuto-check passed

Questions about Subtitle Translator

What does Subtitle Translator do?

Translates SRT and ASS subtitle files, or subtitles embedded in video, into another language using the gst agent CLI and the assistant's own translation. The agent itself performs the translation inside its own context, and no API key is needed because the `gst agent` protocol runs locally.mkv whose embedded subtitles are extracted automatically) and a target language, then works through the subtitle lines batch by batch.

When should I use Subtitle Translator?

Subtitle Translator fits situations like: translating an .srt or .ass subtitle file into another language; translating subtitles embedded in an .mp4 or .mkv video; keeping character tone and gender agreement consistent across dialogue; resuming an interrupted subtitle translation.

How do I install Subtitle Translator in Claude Code?

Run `npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a claude-code`. Or copy the skill folder (gemini_srt_translator in MaKTaiL/gemini-srt-translator) into .claude/skills/subtitle-translator in your project. Claude Code loads it when a task matches its description.

How do I install Subtitle Translator in Codex?

Run `npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a codex`. Or copy the skill folder (gemini_srt_translator in MaKTaiL/gemini-srt-translator) into .agents/skills/subtitle-translator in your project. Codex loads it when a task matches its description.

Can I use Subtitle Translator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MaKTaiL/gemini-srt-translator --skill subtitle-translator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/subtitle-translator, .gemini/skills/subtitle-translator, .github/skills/subtitle-translator and .opencode/skills/subtitle-translator in your project.

What does Subtitle Translator need to run?

Going by SKILL.md and its folder, Subtitle Translator needs Python for the scripts in its folder and the command-line tools its instructions call (uv and poetry). Our summary lists: The gst command-line tool, installed globally or in a project virtual environment.

Does Subtitle Translator access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Subtitle Translator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Subtitle Translator use?

Subtitle Translator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Subtitle Translator use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Subtitle Translator?

Skills that share tags, products or a category with Subtitle Translator: Adaptation (danjdewhurst/story-skills, 283 stars), Animejs (boraoztunc/skills, 397 stars), Youtube Publish (Andonywang123/Epost, 197 stars) and Vocab Lesson (receptron/mulmocast-cli, 475 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Subtitle Translator?

MaKTaiL (a GitHub user) maintains it in MaKTaiL/gemini-srt-translator, which has 357 GitHub stars. The repository was last updated on September 1, 2026.

Source: MaKTaiL/gemini-srt-translator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Subtitle Translator

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Subtitle Translator Skill

🎯 Role & Agent Protocol (CRITICAL)

When to Use

Subtitle Translation Protocol

Step 1: Start a Translation Session

CLI Options Reference

Step 2: Translate In-Context & Commit Translated Batch

Step 3: Repeat Until Complete

Step 4: Cleanup Temporary Files

Helper Commands

Translation Rules

Files

Compare with similar skills

Similar skills

Adaptation

Animejs

Youtube Publish

Vocab Lesson

Video Translate

Seedance Vocab Es

Related

Questions about Subtitle Translator