Official agent skill

Language Injection

by microsoft in microsoft/data-formulator

LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（messagecode）时使用。

OfficialMITAuto-check passedFrontend & Design

Install Language Injection

skills CLI

$ npx skills add microsoft/data-formulator --skill language-injection -a claude-code

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

GitHub CLI

$ gh skill install microsoft/data-formulator language-injection --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/microsoft/data-formulator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/language-injection .claude/skills/language-injection && 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 "language-injection" agent skill from https://github.com/microsoft/data-formulator/tree/main/.cursor/skills/language-injection into .claude/skills/language-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-injection", 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/microsoft/data-formulator/tree/main/.cursor/skills/language-injection

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 microsoft/data-formulator --skill language-injection -a codex

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

GitHub CLI

$ gh skill install microsoft/data-formulator language-injection --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/microsoft/data-formulator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/language-injection .agents/skills/language-injection && 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 "language-injection" agent skill from https://github.com/microsoft/data-formulator/tree/main/.cursor/skills/language-injection into .agents/skills/language-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-injection", 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 microsoft/data-formulator --skill language-injection -a cursor

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

GitHub CLI

$ gh skill install microsoft/data-formulator language-injection --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/microsoft/data-formulator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/language-injection .cursor/skills/language-injection && 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 "language-injection" agent skill from https://github.com/microsoft/data-formulator/tree/main/.cursor/skills/language-injection into .cursor/skills/language-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-injection", 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/microsoft/data-formulator.git --path .cursor/skills/language-injection

--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 microsoft/data-formulator --skill language-injection -a gemini-cli

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

GitHub CLI

$ gh skill install microsoft/data-formulator language-injection --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/microsoft/data-formulator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/language-injection .gemini/skills/language-injection && 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 "language-injection" agent skill from https://github.com/microsoft/data-formulator/tree/main/.cursor/skills/language-injection into .gemini/skills/language-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-injection", 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 microsoft/data-formulator language-injection

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 microsoft/data-formulator --skill language-injection -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/microsoft/data-formulator.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/language-injection .github/skills/language-injection && 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 "language-injection" agent skill from https://github.com/microsoft/data-formulator/tree/main/.cursor/skills/language-injection into .github/skills/language-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-injection", 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 microsoft/data-formulator --skill language-injection -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 microsoft/data-formulator language-injection --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/microsoft/data-formulator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/language-injection .opencode/skills/language-injection && 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 "language-injection" agent skill from https://github.com/microsoft/data-formulator/tree/main/.cursor/skills/language-injection into .opencode/skills/language-injection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-injection", 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: language-injection
GitHub stars: 18k
Token cost: ~1.2k tokens
SKILL.md length: 283 words
Files: 1
Skills in repo: 6
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（messagecode）时使用。

Works in 4 steps: Add language code + display name to… → Optionally add extra rules to… → Add frontend translations in… → …
Frontend & Design work in your project
SKILL.md covers Architecture, Code Examples, Anti-Patterns (with… and Adding a New Language
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Language Injection is an agent skill from microsoft/data-formulator, published by the product's own GitHub organization. LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（messagecode）时使用。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design. It works with Python. The repository describes itself as: 🪄 Data Formulator is an interactive AI-powered data analysis system makes it easy to connect, explore and visualize data. The licence is MIT.

When your agent uses it

Frontend & Design work in your project

Example prompts

“/language-injection”

Requirements

Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Add language code + display name to LANGUAGE_DISPLAY_NAMES in agents/agent_language.py.
Optionally add extra rules to LANGUAGE_EXTRA_RULES (e.g. simplified vs traditional Chinese).
Add frontend translations in src/i18n/locales// — copy an existing locale folder as template.
No Agent code changes needed — the existing flow picks up new languages automatically.

What it can do on your machine

Read from SKILL.md and the folder at commit 5477f0e. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and typescript).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Language Injection loads about 1.2k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 283 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~24
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

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 microsoft/data-formulator at commit 5477f0e, republished under its MIT licence (© microsoft). 283 words, ~1,230 tokens.

Download SKILL.mdSave it as .claude/skills/language-injection/SKILL.md (or your agent's skills folder).

name: language-injection
description: LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（message_code）时使用。

Language Injection for Agent Prompts

Authoritative developer guide: docs/dev-guides/6-i18n-language-injection.md.

Prerequisites: Read docs/dev-guides/6-i18n-language-injection.md before changing Agent prompts, Agent routes, backend user-visible messages, or frontend i18n strings. If your work introduces new language injection patterns or conventions, update this file and related dev-guides accordingly.

Architecture

Frontend i18n.language  →  Accept-Language header  →  get_language_instruction()
                                                           │
                                                   build_language_instruction()
                                                   (agents/agent_language.py)
                                                           │
                                              ┌────────────┴────────────┐
                                              ▼                         ▼
                                        mode="full"               mode="compact"
                                    (text-heavy agents)        (code-gen agents)

Core Modules

Module	Role
`agents/agent_language.py`	`build_language_instruction(lang, mode)` — generates prompt fragments; `inject_language_instruction()` — injects into system prompts; supports 20 languages; returns `""` for English
`routes/agents.py` → `get_language_instruction()`	Reads `Accept-Language` header, delegates to `build_language_instruction`
`routes/agents.py` → `_get_ui_lang()`	Extracts primary language code from `Accept-Language` header
`src/app/utils.tsx` → `fetchWithIdentity()`	Sets `Accept-Language` header on every API request from `i18n.language`
`src/app/utils.tsx` → `translateBackend()`	Translates backend `message_code` / `content_code` using frontend i18n

Code Examples

Route handler — inject language

python

# In a Flask route handler:
lang_instruction = get_language_instruction(mode="compact")
lang_suffix = f"\n\n{lang_instruction}" if lang_instruction else ""

messages = [
    {"role": "system", "content": "You are a helpful assistant." + lang_suffix},
    {"role": "user", "content": user_input},
]

Agent constructor — use inject_language_instruction()

python

from data_formulator.agents.agent_language import inject_language_instruction

# Simple append (most agents)
system_prompt = inject_language_instruction(system_prompt, language_instruction)

# Insert before a marker (complex prompts)
system_prompt = inject_language_instruction(
    system_prompt, language_instruction,
    marker="**About the execution environment:**"
)

Python-side user-visible messages — message_code pattern

For fixed strings in Python that appear in the UI, do NOT translate in Python. Return a message_code and let the frontend translate:

python

# In an Agent or route handler:
yield {
    "type": "error",
    "message": "Output DataFrame is empty (0 rows).",  # English fallback
    "message_code": "agent.emptyDataframe",             # frontend i18n key
}

# With parameters:
result = {
    "status": "error",
    "content": f"Fields not found: {missing}",
    "content_code": "agent.fieldsNotFound",
    "content_params": {"missing": missing, "available": available},
}

Frontend consumption:

tsx

import { translateBackend } from '../app/utils';
const msg = translateBackend(event.message, event.message_code, event.message_params);

Translation keys go in src/i18n/locales/{en,zh}/messages.json under messages.agent.*.

Anti-Patterns (with explanations)

Pattern	Why it's wrong
`os.environ.get("DF_DEFAULT_LANGUAGE")`	Process-level — all users get same language; breaks multi-user
Global LLM client interceptor	Hidden behavior; can't distinguish full/compact mode; fragile string detection
New `MessageBuilder` class	Duplicates `agent_language.py`; creates parallel conflicting abstractions
Hardcoded `"回答请使用中文"` in prompts	Not configurable; skips the mode system; breaks for other languages
Backend-side translation dict (`agent_messages.py`)	Forces adding every new language to Python; translations should all live in `src/i18n/locales/`
Hardcoded English UI strings in `.tsx` without `t()`	Not translatable; use `useTranslation` + `t('key')`

Adding a New Language

Add language code + display name to LANGUAGE_DISPLAY_NAMES in agents/agent_language.py.
Optionally add extra rules to LANGUAGE_EXTRA_RULES (e.g. simplified vs traditional Chinese).
Add frontend translations in src/i18n/locales/<lang>/ — copy an existing locale folder as template.
No Agent code changes needed — the existing flow picks up new languages automatically.

Files

Just SKILL.md in .cursor/skills/language-injection of microsoft/data-formulator.

Open the folder on GitHubat commit 5477f0e

Compare with similar skills

Language Injection 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.

Language Injection compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Language Injection this skillmicrosoft/data-formulator	18k	—	~1.2k	Automated safety check: Pass	MIT	today
Claude Desktop Chinese Localizationjavaht/claude-desktop-zh-cn	7.5k	—	~1.6k	Automated safety check: Pass	MIT	2 days ago
DocsPrefectHQ/fastmcp	28k	—	~1k	Automated safety check: Pass	Apache-2.0	today
Oil UIoil-oil/oil-ui	1k	—	~1.7k	Automated safety check: Pass	MIT	today
Jarvis Setupethanplusai/jarvis	838	—	~2.5k	Automated safety check: Notes	Custom licence	27 days ago
Ibm A11y Route Scanlangflow-ai/langflow	156k	—	~1.6k	Automated safety check: Pass	MIT	today

Similar skills

Claude Desktop Chinese Localization
javaht/claude-desktop-zh-cn
Adds missing Simplified and Traditional Chinese translations to the Claude Desktop Chinese patch across three layers, then checks how many mappings actually hit.
7.5k GitHub stars~1.6k tokensUpdated 2 days ago
Frontend & DesignAuto-check passed
Docs
PrefectHQ/fastmcp
Write or revise a page under docs/ for gofastmcp.com. An agent skill from PrefectHQ/fastmcp.
28k GitHub stars~1k tokensUpdated today
Frontend & DesignAuto-check passed
Oil UI
oil-oil/oil-ui
Design, improve, and review interfaces for websites, apps, dashboards, and components: explore distinct design directions, compare styles side by side, and refine visual hierarchy against real…
1k GitHub stars~1.7k tokensUpdated today
Frontend & DesignAuto-check passed
Jarvis Setup
ethanplusai/jarvis
A skill your agent uses when helping someone install, configure, or debug a fresh clone of JARVIS (this repo) — especially "the mic doesn't work", "JARVIS says his language systems are down", any…
838 GitHub stars~2.5k tokensUpdated 27 days ago
Frontend & DesignAuto-check: notes
Ibm A11y Route Scan
langflow-ai/langflow
Batch-scan Langflow frontend routes for accessibility issues using the Python IBM Equal Access scanner (scripts/a11y/a11yscan.py) and produce JSON/Markdown/HTML reports.
156k GitHub stars~1.6k tokensUpdated today
Frontend & DesignAuto-check passed
Build Fluentqt Gui
calvinhxx/Fluent-Qt
Create, integrate, redesign, or fix C++ and PySide6 GUIs using FluentQt, including component and Gallery work.
155 GitHub stars~1.6k tokensUpdated today
Frontend & DesignAuto-check passed

More from microsoft/data-formulator

Error Handling
microsoft/data-formulator
Official
统一错误处理系统。在添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试时使用. An agent skill from microsoft/data-formulator.
18k GitHub stars~3.8k tokensUpdated today
Auto-check passed
Path Safety
microsoft/data-formulator
Official
服务端路径安全与文件访问编码规范。在编写文件下载路由、Agent 工具（文件读取/目录列出）、数据连接器/Loader、Workspace 路径操作、沙箱配置时使用。
18k GitHub stars~1.2k tokensUpdated today
Auto-check passed
Data Loading
microsoft/data-formulator
Official
Discover connected data sources, add new data connectors through a user-confirmed form, inspect table metadata, and run bounded read-only probes when the current workspace data is insufficient.
18k GitHub stars~1.4k tokensUpdated today
Auto-check passed
Report
microsoft/data-formulator
Official
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded…
18k GitHub stars~1.5k tokensUpdated today
Auto-check passed
Core
microsoft/data-formulator
Official
The analyst's built-in capabilities: data-inspection tools and the always-available actions (visualize and askuser).
18k GitHub stars~5.4k tokensUpdated today
Auto-check passed

Works with

Python

Questions about Language Injection

What does Language Injection do?

LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（messagecode）时使用。. Language Injection is an agent skill from microsoft/data-formulator, published by the product's own GitHub organization.

When should I use Language Injection?

Language Injection fits situations like: frontend & Design work in your project.

How do I install Language Injection in Claude Code?

Run `npx skills add microsoft/data-formulator --skill language-injection -a claude-code`. Or copy the skill folder (.cursor/skills/language-injection in microsoft/data-formulator) into .claude/skills/language-injection in your project. Claude Code loads it when a task matches its description.

How do I install Language Injection in Codex?

Run `npx skills add microsoft/data-formulator --skill language-injection -a codex`. Or copy the skill folder (.cursor/skills/language-injection in microsoft/data-formulator) into .agents/skills/language-injection in your project. Codex loads it when a task matches its description.

Can I use Language Injection 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 microsoft/data-formulator --skill language-injection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/language-injection, .gemini/skills/language-injection, .github/skills/language-injection and .opencode/skills/language-injection in your project.

What does Language Injection need to run?

SKILL.md names no scripts, command-line tools or credentials: Language Injection is instructions for the agent only. Our summary lists: Python 3.

Does Language Injection access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Language Injection 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 Language Injection use?

Language Injection 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 Language Injection use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Language Injection?

Skills that share tags, products or a category with Language Injection: Claude Desktop Chinese Localization (javaht/claude-desktop-zh-cn, 7.5k stars), Docs (PrefectHQ/fastmcp, 28k stars), Oil UI (oil-oil/oil-ui, 1k stars) and Jarvis Setup (ethanplusai/jarvis, 838 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Language Injection?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/data-formulator, which has 17,540 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

Source: microsoft/data-formulator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Language Injection

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

Language Injection for Agent Prompts

Architecture

Core Modules

Code Examples

Route handler — inject language

Agent constructor — use inject_language_instruction()

Python-side user-visible messages — message_code pattern

Anti-Patterns (with explanations)

Adding a New Language

Files

Compare with similar skills

Similar skills

More from microsoft/data-formulator

Related

Questions about Language Injection