TypingMindTypingMindThe best frontend for AI
I18n Delivery Pipeline logo

I18n Delivery Pipeline

Community
jerry3413
i18n-delivery-pipeline

Route PRD, spec, and exported localization files into whole-document translation, draft copy extraction, or final localization delivery.

Overview

Publisherjerry3413
Repositoryprd-to-i18n-skill
Skill namei18n-delivery-pipeline
Stars
75
Forks
0
Bundled files
40
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 40 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jerry3413 on GitHub. Read the source before you install it.

Installation

Install the I18n Delivery Pipeline AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jerry3413/prd-to-i18n-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jerry3413/prd-to-i18n-skill.git \
  .claude/skills/i18n-delivery-pipeline
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable I18n Delivery Pipeline in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads I18n Delivery Pipeline on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so I18n Delivery Pipeline is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

I18n Delivery Pipeline

Use When

Use this skill when the request starts from any of these:

  • raw PRD or spec materials such as Markdown, Word, PDF, Confluence export, spreadsheet, screenshot, or Figma export
  • exported locale resources such as iOS .strings, Android strings.xml, JSON, or CSV
  • an ambiguous request that may mean either whole-document translation or localization delivery

First Decision

For raw PRD, PDF, Word, Confluence, or screenshot bundles, ask what outcome the user wants before heavy extraction:

  1. whole-document translation
  2. a draft list of user-facing copy
  3. a final localization package

Critical Guardrails

  • If a PRD or spec translation request is ambiguous, do not default. Ask whether the user wants whole-document translation or localization delivery.
  • If the user already makes delivery intent explicit with phrases such as 多语言, i18n, 本地化, 交付, 导出, handoff, or import, skip the document-vs-localization split.
  • If the user chooses whole-document translation, ask for the target language and stay out of localization-only questions.
  • If the user chooses final delivery, do not start extraction, key creation, translation, or export until the delivery contract is confirmed.
  • A carrier-only answer such as JSON, CSV, or XLSX is not a confirmed handoff shape.
  • If the request is high-risk, context-poor, or ends in human-gate, do not present the result as fully finalized.

Runtime State Map

Use the smallest relevant reference set for the current state:

  1. Intake Read coordinator-core.md. Read coordinator-examples.md only when you need branch-matching follow-up phrasing.
  2. Disambiguation and fallback Read decision-tables.md.
  3. Input and capability handling Read input-contract.md for package shape. Read capability-routing.md for PDFs, screenshots, scans, OCR, or vision paths.
  4. Artifact processing Read artifact-ingestion.md for raw bundles. Read copy-extraction-rules.md for candidate extraction. Read manifest-schema.md before building or editing the canonical manifest.
  5. Review and release gating Read review-policy.md.
  6. Parallel execution after the slice is frozen Read agent-orchestration.md.

Minimal Decision Anchors

  • Ambiguous request example: translate this PRD -> ask whether to translate the whole document or only the product copy for localization.
  • Explicit delivery example: 做多语言交付 -> ask for included scope when the source mixes surfaces, target languages, reusable-history status, and the final handoff shape in one bundled follow-up.

Artifact Flow

  • Raw non-text or mixed bundles: run scripts/route_capabilities.py first when PDFs, screenshots, or scans are present.
  • Raw artifact path: scripts/ingest_artifacts.py -> scripts/extract_copy_candidates.py -> scripts/build_manifest_stub.py
  • Exported resource path: scripts/normalize_snapshot.py -> scripts/build_manifest_stub.py
  • Finalized manifest path: scripts/plan_execution.py -> scripts/qa_manifest.py -> scripts/emit_delivery_bundle.py

Working Rules

  • Prefer one export folder over explicit resource descriptors until auto-discovery is insufficient.
  • Prefer one bundled delivery-contract question over serial one-field turns when several delivery details are missing.
  • If the result is a small draft list, show it inline first unless the user asked for a file.
  • Do not create PRD-specific generator scripts as the official workflow. If a generic capability is missing, improve the shared scripts instead.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the I18n Delivery Pipeline AI skill do?

Route PRD, spec, and exported localization files into whole-document translation, draft copy extraction, or final localization delivery.

Why use I18n Delivery Pipeline on TypingMind?

Because you install it once and use it with any model. I18n Delivery Pipeline is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install I18n Delivery Pipeline in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jerry3413/prd-to-i18n-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use I18n Delivery Pipeline?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with I18n Delivery Pipeline?

As many as you like. As long as a model supports skills, you can use I18n Delivery Pipeline with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the I18n Delivery Pipeline AI skill free?

Yes. It is published on GitHub by jerry3413 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
affaan-m logo

Unified Memory

affaan-m
CommunityPopular

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer…

40.4K
270.2K
1 files
View
NousResearch logo

Draw Your Font

NousResearch
OrganizationPopular

Turn a handwriting photo into an installable TTF font.

53.5K
250.4K
1 files
View
NousResearch logo

Adversarial Ux Test

NousResearch
OrganizationPopular

Roleplay a hostile user to find and triage UX pain points.

53.5K
250.4K
Instructions
View
NousResearch logo

3 Statement Model

NousResearch
OrganizationPopular

Build integrated IS/BS/CF financial workbooks in Excel.

53.5K
250.4K
3 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇