Agent skill

Cloudflare Workers Multi Lang

by secondsky in secondsky/claude-skills

Multi-language Workers development with Rust, Python, and WebAssembly.

MITAuto-check passed

Install Cloudflare Workers Multi Lang

skills CLI
$ npx skills add secondsky/claude-skills --skill cloudflare-workers-multi-lang -a claude-code

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

GitHub CLI
$ gh skill install secondsky/claude-skills cloudflare-workers-multi-lang --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/secondsky/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/cloudflare-workers/skills/cloudflare-workers-multi-lang .claude/skills/cloudflare-workers-multi-lang && 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/

Facts

Skill name
cloudflare-workers-multi-lang
GitHub stars
227
Token cost
~1.3k tokens
SKILL.md length
246 words
Files
9 (incl. scripts, references)
Skills in repo
169
Repo updated
First seen
Licence
MIT

At a glance

Multi-language Workers development with Rust, Python, and WebAssembly.

  • Works in 5 steps: WASM Initialization: Cache instance, use… → Memory: Use typed arrays for data transfer → Bundle Size: Enable LTO, strip debug info → …
  • Building Workers in languages other than JavaScript/TypeScript
  • SKILL.md covers Language Comparison, Quick Decision, Top 10 Multi-Lang Errors and Rust Quick Start, plus 5 more sections
  • Runs Shell, Python, Rust and TypeScript scripts from its folder; calls cargo and python

What it does

Cloudflare Workers Multi Lang is an agent skill from secondsky/claude-skills. Multi-language Workers development with Rust, Python, and WebAssembly. Use when building Workers in languages other than JavaScript/TypeScript, or when integrating WASM modules for performance-critical code.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `references/python-workers.md`, `references/rust-workers.md` and `references/wasm-integration.md`).

It works with WebAssembly, Rust, Python and Cloudflare Workers. The repository describes itself as: Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations. The licence is MIT.

When your agent uses it

  • Building Workers in languages other than JavaScript/TypeScript
  • Integrating WASM modules for performance-critical code

Example prompts

  • “/cloudflare-workers-multi-lang”

Requirements

  • Python 3
  • Node.js
  • A Bash shell

Workflow steps

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

  1. WASM Initialization: Cache instance, use streaming
  2. Memory: Use typed arrays for data transfer
  3. Bundle Size: Enable LTO, strip debug info
  4. Cold Starts: Keep WASM modules small
  5. Data Transfer: Minimize JS/WASM boundary crossings

What it can do on your machine

Read from SKILL.md and the folder at commit 8837836. 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 2 files in scripts/ (Shell, Python, Rust and TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • cargo
    • python

    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

Cloudflare Workers Multi Lang loads about 1.3k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 246 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~10k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from secondsky/claude-skills at commit 8837836, republished under its MIT licence (© secondsky). 246 words, ~1,280 tokens.

Download SKILL.mdSave it as .claude/skills/cloudflare-workers-multi-lang/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
cloudflare-workers-multi-lang
description
Multi-language Workers development with Rust, Python, and WebAssembly. Use when building Workers in languages other than JavaScript/TypeScript, or when integrating WASM modules for performance-critical code.
metadata.version
1.0.0
license
MIT

Multi-Language Workers Development

Build Cloudflare Workers using Rust, Python, or WebAssembly for performance-critical operations.

Language Comparison

FeatureJavaScript/TSRustPython
StartupFastFastest (WASM)Moderate
CPU PerfGoodExcellentGood
MemoryHigherLowerHigher
Bundle SizeSmallerMediumLarger
Type SafetyOptional (TS)StrictOptional
Best ForGeneral appsCPU-intensiveData/ML

Quick Decision

Need maximum performance? → Rust/WASM
Heavy computation (crypto, image processing)? → Rust/WASM
Data processing, ML inference? → Python
General web apps? → JavaScript/TypeScript

Top 10 Multi-Lang Errors

ErrorLanguageCauseSolution
WebAssembly.instantiate() failedRustInvalid WASMCheck wasm-pack build output
Module parse failed: Unexpected tokenRustESM/CJS mismatchUse --target bundler
Cannot find modulePythonMissing depAdd to pyproject.toml
Out of memoryAllLarge WASMEnable streaming instantiation
Exceeded CPU time limitAllLong computationChunk processing
wasm-bindgen version mismatchRustDep conflictAlign versions in Cargo.toml
RuntimeError: unreachableRustPanic in WASMAdd proper error handling
TypeError: not a functionRustMissing exportAdd #[wasm_bindgen] attribute
Python worker startup timeoutPythonSlow initMinimize imports
SharedArrayBuffer not supportedAllSecurityAdd COOP/COEP headers

Rust Quick Start

bash
# Install tools
cargo install wasm-pack

# Create project
cargo new --lib my-worker
cd my-worker

# Add to Cargo.toml
cat >> Cargo.toml << 'EOF'
[lib]
crate-type = ["cdylib"]

[dependencies]
wasm-bindgen = "0.2"
worker = "0.3"
console_error_panic_hook = "0.1"

[profile.release]
opt-level = "s"
lto = true
EOF
rust
// src/lib.rs
use worker::*;

#[event(fetch)]
async fn fetch(req: Request, env: Env, _ctx: Context) -> Result<Response> {
    console_error_panic_hook::set_once();

    Router::new()
        .get("/", |_, _| Response::ok("Hello from Rust!"))
        .get("/compute", |_, _| {
            // CPU-intensive computation
            let result = heavy_computation();
            Response::ok(format!("Result: {}", result))
        })
        .run(req, env)
        .await
}

fn heavy_computation() -> u64 {
    (1..1_000_000).filter(|n| is_prime(*n)).count() as u64
}

fn is_prime(n: u64) -> bool {
    if n < 2 { return false; }
    (2..=(n as f64).sqrt() as u64).all(|i| n % i != 0)
}

Python Quick Start (Workers for Platforms)

toml
# pyproject.toml
[project]
name = "my-worker"
version = "0.1.0"
requires-python = ">=3.12"
dependencies = []

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
python
# src/entry.py
from js import Response, Headers

async def on_fetch(request, env):
    url = request.url

    if "/compute" in url:
        result = heavy_computation()
        return Response.new(f"Result: {result}")

    return Response.new("Hello from Python!")

def heavy_computation():
    """CPU-intensive computation"""
    return sum(1 for n in range(2, 100000) if is_prime(n))

def is_prime(n):
    if n < 2:
        return False
    return all(n % i != 0 for i in range(2, int(n**0.5) + 1))

WASM Module Integration

typescript
// Load and use WASM module in TypeScript Worker
import wasmModule from './pkg/my_lib_bg.wasm';
import { init, process_data } from './pkg/my_lib';

let wasmInstance: WebAssembly.Instance;

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    // Initialize WASM once
    if (!wasmInstance) {
      wasmInstance = await WebAssembly.instantiate(wasmModule);
      init();
    }

    // Use WASM function
    const result = process_data(inputData);

    return Response.json({ result });
  },
};

When to Load References

ReferenceLoad When
references/rust-workers.mdBuilding Workers with Rust/WASM
references/python-workers.mdUsing Python on Workers for Platforms
references/wasm-integration.mdIntegrating WASM modules in any Worker

Performance Tips

  1. WASM Initialization: Cache instance, use streaming
  2. Memory: Use typed arrays for data transfer
  3. Bundle Size: Enable LTO, strip debug info
  4. Cold Starts: Keep WASM modules small
  5. Data Transfer: Minimize JS/WASM boundary crossings

See Also

  • workers-performance - General optimization techniques
  • workers-testing - Testing multi-language Workers
  • cloudflare-worker-base - Basic Workers setup

© secondsky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in plugins/cloudflare-workers/skills/cloudflare-workers-multi-lang of secondsky/claude-skills.

  • SKILL.md
  • references/python-workers.md
  • references/rust-workers.md
  • references/wasm-integration.md
  • scripts/build-rust.sh
  • scripts/build-wasm.sh
  • templates/python-worker.py
  • templates/rust-worker.rs
  • templates/wasm-worker.ts

Open the folder on GitHubat commit 8837836

Compare with similar skills

Cloudflare Workers Multi Lang 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.

Cloudflare Workers Multi Lang compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cloudflare Workers Multi Lang this skillsecondsky/claude-skills227—~1.3kAutomated safety check: PassMIT
Cloudflare Workerseinverne/dotfiles121—~8.4kAutomated safety check: PassMIT
jscpd Code Migration Trackerkucherenko/jscpd6.3k—~5kAutomated safety check: PassMIT
Cross-Language Coding Standardszereight/gitlab-mcp2k1 repos~1.4kAutomated safety check: PassMIT
Crossbindcrossbind/crossbind148—~1.1kAutomated safety check: PassMIT
Language Supportlive-codes/livecodes1.5k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Cloudflare Workers

    einverne/dotfiles

    Comprehensive guide for building serverless applications with Cloudflare Workers.

    121 GitHub stars~8.4k tokensUpdated 28 days ago
    Backend & APIsAuto-check passed
  • Measures a code port between languages or frameworks with jscpd's function-level comparison, porting tests before code and tracking what is left unmatched.

    6.3k GitHub stars~5k tokensUpdated today
    DevelopmentAuto-check passed
  • Shared reference for naming, function size, complexity and error handling rules that reviewer agents apply across TypeScript, Python, Go, Rust, Java, C# and Swift.

    2k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • Crossbind

    crossbind/crossbind

    A skill your agent uses when a user wants to call C++ or Rust from JavaScript or TypeScript; add a native library such as GDAL, SQLite, OpenSSL, GEOS or PROJ to a browser, Node.js, Cloudflare Worker…

    148 GitHub stars~1.1k tokensUpdated today
    MobileAuto-check passed
  • Language Support

    live-codes/livecodes

    Work with 90+ supported languages, compilers, CSS processors, and WASM-compiled languages for markup, style, and script editors.

    1.5k GitHub stars~1.6k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Coding Agent

    mastra-ai/mastra

    Authoring playbook for building agents that write, edit, review, or refactor code.

    29k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed

More from secondsky/claude-skills

All 169 skills in this repo
  • Tanstack AI

    secondsky/claude-skills

    TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama.

    227 GitHub starsUsed in 1 repo~3.6k tokens
    Auto-check: notes
  • Auto Animate

    secondsky/claude-skills

    AutoAnimate (@formkit/auto-animate) zero-config animations for React.

    227 GitHub stars~2.9k tokensUpdated 9 days ago
    Auto-check passed
  • Base UI React

    secondsky/claude-skills

    MUI Base UI unstyled React components with Floating UI. An agent skill from secondsky/claude-skills.

    227 GitHub stars~1.9k tokensUpdated 9 days ago
    Auto-check passed
  • Cloudflare Images

    secondsky/claude-skills

    This skill should be used when the user asks to "upload images to Cloudflare", "implement direct creator upload", "configure image transformations", "optimize WebP/AVIF", "create image variants"…

    227 GitHub stars~3.6k tokensUpdated 9 days ago
    Auto-check: notes
  • Cloudflare Nextjs

    secondsky/claude-skills

    Deploy Next.js to Cloudflare Workers via the OpenNext adapter (@opennextjs/cloudflare).

    227 GitHub stars~5.3k tokensUpdated 9 days ago
    Auto-check: notes
  • Cloudflare Sandbox

    secondsky/claude-skills

    Cloudflare Sandboxes SDK for secure code execution in Linux containers at edge.

    227 GitHub stars~4.5k tokensUpdated 9 days ago
    Auto-check passed

Questions about Cloudflare Workers Multi Lang

What does Cloudflare Workers Multi Lang do?

Multi-language Workers development with Rust, Python, and WebAssembly. Cloudflare Workers Multi Lang is an agent skill from secondsky/claude-skills. Multi-language Workers development with Rust, Python, and WebAssembly.

When should I use Cloudflare Workers Multi Lang?

Cloudflare Workers Multi Lang fits situations like: building Workers in languages other than JavaScript/TypeScript; integrating WASM modules for performance-critical code.

How do I install Cloudflare Workers Multi Lang in Claude Code?

Run `npx skills add secondsky/claude-skills --skill cloudflare-workers-multi-lang -a claude-code`. Or copy the skill folder (plugins/cloudflare-workers/skills/cloudflare-workers-multi-lang in secondsky/claude-skills) into .claude/skills/cloudflare-workers-multi-lang in your project. Claude Code loads it when a task matches its description.

How do I install Cloudflare Workers Multi Lang in Codex?

Run `npx skills add secondsky/claude-skills --skill cloudflare-workers-multi-lang -a codex`. Or copy the skill folder (plugins/cloudflare-workers/skills/cloudflare-workers-multi-lang in secondsky/claude-skills) into .agents/skills/cloudflare-workers-multi-lang in your project. Codex loads it when a task matches its description.

Can I use Cloudflare Workers Multi Lang 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 secondsky/claude-skills --skill cloudflare-workers-multi-lang -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cloudflare-workers-multi-lang, .gemini/skills/cloudflare-workers-multi-lang, .github/skills/cloudflare-workers-multi-lang and .opencode/skills/cloudflare-workers-multi-lang in your project.

What does Cloudflare Workers Multi Lang need to run?

Going by SKILL.md and its folder, Cloudflare Workers Multi Lang needs a shell, Python, Rust and TypeScript for the scripts in its folder and the command-line tools its instructions call (cargo and python). Our summary lists: Python 3; Node.js; A Bash shell.

Does Cloudflare Workers Multi Lang 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 Cloudflare Workers Multi Lang 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cloudflare Workers Multi Lang use?

Cloudflare Workers Multi Lang is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cloudflare Workers Multi Lang use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9k tokens, read only when the agent opens those files.

What are the alternatives to Cloudflare Workers Multi Lang?

Skills that share tags, products or a category with Cloudflare Workers Multi Lang: Cloudflare Workers (einverne/dotfiles, 121 stars), jscpd Code Migration Tracker (kucherenko/jscpd, 6.3k stars), Cross-Language Coding Standards (zereight/gitlab-mcp, 2k stars) and Crossbind (crossbind/crossbind, 148 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cloudflare Workers Multi Lang?

secondsky (a GitHub user) maintains it in secondsky/claude-skills, which has 227 GitHub stars. The repository holds 169 skills in this directory. The repository was last updated on September 28, 2026.

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