Agent skill

Cloudflare Worker Dev

by curiositech in curiositech/some_claude_skills

Cloudflare Workers, KV, Durable Objects, and edge computing development.

MITAuto-check: notesBackend & APIs

Install Cloudflare Worker Dev

skills CLI
$ npx skills add curiositech/some_claude_skills --skill cloudflare-worker-dev -a claude-code

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

GitHub CLI
$ gh skill install curiositech/some_claude_skills cloudflare-worker-dev --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/curiositech/some_claude_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/cloudflare-worker-dev .claude/skills/cloudflare-worker-dev && 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-worker-dev
GitHub stars
243
Token cost
~3.4k tokens
SKILL.md length
174 words
Files
2
Skills in repo
108
Repo updated
First seen
Licence
MIT

At a glance

Cloudflare Workers, KV, Durable Objects, and edge computing development.

  • Serverless APIs
  • SKILL.md covers Core Architecture, Worker Fundamentals, KV Storage Patterns and Rate Limiting, plus 5 more sections
  • Calls npx; reaches slow-api.com; needs API_KEY
  • Real-time features

What it does

Cloudflare Worker Dev is an agent skill from curiositech/some_claude_skills. Cloudflare Workers, KV, Durable Objects, and edge computing development. Use for serverless APIs, caching, rate limiting, real-time features. Activate on "Workers", "KV", "Durable Objects", "wrangler", "edge function", "Cloudflare". NOT for Cloudflare Pages configuration (use deployment docs), DNS management, or general CDN settings.

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `.claude-plugin/plugin.json`).

It sits in Backend & APIs, covering Rate limiting, Caching and Serverless. It works with Cloudflare Workers, Cloudflare Durable Objects, Cloudflare and Cloudflare Pages. The repository describes itself as: Claude skills that make my life easier. The licence is MIT.

When your agent uses it

  • Serverless APIs
  • Real-time features

Example prompts

  • “Workers”
  • “Durable Objects”
  • “wrangler”
  • “/cloudflare-worker-dev”

Requirements

  • Node.js
  • A credential in API_KEY
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob

What it can do on your machine

Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • slow-api.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cloudflare Worker Dev loads about 3.4k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 174 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Bash, Grep, Glob

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 curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 174 words, ~3,379 tokens.

Download SKILL.mdSave it as .claude/skills/cloudflare-worker-dev/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
cloudflare-worker-dev
description
Cloudflare Workers, KV, Durable Objects, and edge computing development. Use for serverless APIs, caching, rate limiting, real-time features. Activate on "Workers", "KV", "Durable Objects", "wrangler", "edge function", "Cloudflare". NOT for Cloudflare Pages configuration (use deployment docs), DNS management, or general CDN settings.
allowed-tools
Read, Write, Edit, Bash, Grep, Glob
metadata.category
DevOps & Site Reliability
metadata.tags
cloudflare, workers, edge-computing, serverless, kv, caching, rate-limiting

Cloudflare Workers Development

Build high-performance edge APIs with Workers, KV for caching, and Durable Objects for real-time coordination.

Core Architecture

When to Use What
ServiceUse CaseCharacteristics
WorkersRequest handling, API logicStateless, 50ms CPU (free), 30s (paid)
KVCaching, config, sessionsEventually consistent, fast reads
Durable ObjectsReal-time, coordinationStrongly consistent, single-threaded
R2File storageS3-compatible, no egress fees
D1SQLite at edgeServerless SQL, good for reads

Worker Fundamentals

Basic Worker Structure
typescript
// src/index.ts
export interface Env {
  MEETING_CACHE: KVNamespace;
  RATE_LIMIT: KVNamespace;
  API_KEY: string;
}

export default {
  async fetch(request: Request, env: Env, ctx: ExecutionContext): Promise<Response> {
    const url = new URL(request.url);

    // CORS handling
    if (request.method === 'OPTIONS') {
      return handleCORS();
    }

    try {
      // Route handling
      if (url.pathname === '/health') {
        return json({ status: 'ok' });
      }

      if (url.pathname.startsWith('/api/')) {
        return handleAPI(request, env, ctx);
      }

      return new Response('Not Found', { status: 404 });
    } catch (error) {
      console.error('Worker error:', error);
      return json({ error: 'Internal error' }, 500);
    }
  },

  // Cron trigger
  async scheduled(event: ScheduledEvent, env: Env, ctx: ExecutionContext) {
    ctx.waitUntil(runScheduledTask(env));
  }
};
CORS Headers (Essential)
typescript
const CORS_HEADERS = {
  'Access-Control-Allow-Origin': '*', // Or specific origin
  'Access-Control-Allow-Methods': 'GET, POST, PUT, DELETE, OPTIONS',
  'Access-Control-Allow-Headers': 'Content-Type, Authorization',
  'Access-Control-Max-Age': '86400',
};

function handleCORS(): Response {
  return new Response(null, { status: 204, headers: CORS_HEADERS });
}

function json(data: unknown, status = 200): Response {
  return new Response(JSON.stringify(data), {
    status,
    headers: {
      ...CORS_HEADERS,
      'Content-Type': 'application/json',
    },
  });
}
wrangler.toml Configuration
toml
name = "my-worker"
main = "src/index.ts"
compatibility_date = "2024-01-01"

# KV Namespaces
[[kv_namespaces]]
binding = "MEETING_CACHE"
id = "abc123..."  # Production
preview_id = "def456..."  # Dev

[[kv_namespaces]]
binding = "RATE_LIMIT"
id = "ghi789..."

# Environment variables
[vars]
CACHE_TTL = "86400"
RATE_LIMIT_REQUESTS = "100"
RATE_LIMIT_WINDOW = "3600"

# Secrets (set via `wrangler secret put`)
# API_KEY, DATABASE_URL, etc.

# Cron triggers
[triggers]
crons = ["0 */6 * * *"]  # Every 6 hours

# Custom routes
# routes = [{ pattern = "api.example.com/*", zone_name = "example.com" }]

KV Storage Patterns

Basic KV Operations
typescript
// Write with TTL
await env.CACHE.put('key', JSON.stringify(data), {
  expirationTtl: 86400, // 24 hours in seconds
});

// Write with metadata
await env.CACHE.put('key', value, {
  expirationTtl: 3600,
  metadata: { createdAt: Date.now(), source: 'api' },
});

// Read
const value = await env.CACHE.get('key');
const parsed = await env.CACHE.get('key', 'json');

// Read with metadata
const { value, metadata } = await env.CACHE.getWithMetadata('key', 'json');

// Delete
await env.CACHE.delete('key');

// List keys
const { keys, cursor } = await env.CACHE.list({ prefix: 'meetings:' });
Geohash-Based Caching
typescript
import Geohash from 'latlon-geohash';

function getCacheKey(lat: number, lng: number, radius: number): string {
  // 3-char geohash = ~150km cells, good for metro areas
  const geohash = Geohash.encode(lat, lng, 3);
  return `meetings:${geohash}:${radius}`;
}

async function getMeetingsWithCache(
  lat: number,
  lng: number,
  radius: number,
  env: Env
): Promise<{ data: Meeting[]; cached: boolean; geohash: string }> {
  const geohash = Geohash.encode(lat, lng, 3);
  const cacheKey = `meetings:${geohash}:${radius}`;

  // Try cache first
  const cached = await env.MEETING_CACHE.get(cacheKey, 'json');
  if (cached) {
    return { data: cached, cached: true, geohash };
  }

  // Fetch fresh data
  const data = await fetchMeetings(lat, lng, radius);

  // Cache in background (don't await)
  env.ctx.waitUntil(
    env.MEETING_CACHE.put(cacheKey, JSON.stringify(data), {
      expirationTtl: 86400,
      metadata: { cachedAt: Date.now(), geohash },
    })
  );

  return { data, cached: false, geohash };
}
Response Headers for Cache Debugging
typescript
function meetingsResponse(data: Meeting[], cached: boolean, geohash: string): Response {
  return new Response(JSON.stringify(data), {
    headers: {
      ...CORS_HEADERS,
      'Content-Type': 'application/json',
      'X-Cache': cached ? 'HIT' : 'MISS',
      'X-Geohash': geohash,
      'Cache-Control': 'public, max-age=3600',
    },
  });
}

Rate Limiting

IP-Based Rate Limiting
typescript
interface RateLimitConfig {
  maxRequests: number;
  windowSeconds: number;
}

async function checkRateLimit(
  ip: string,
  env: Env,
  config: RateLimitConfig
): Promise<{ allowed: boolean; remaining: number; resetAt: number }> {
  const key = `rate:${ip}`;
  const now = Math.floor(Date.now() / 1000);
  const windowStart = now - config.windowSeconds;

  // Get current state
  const stored = await env.RATE_LIMIT.get(key, 'json') as {
    count: number;
    windowStart: number;
  } | null;

  // New window or expired
  if (!stored || stored.windowStart < windowStart) {
    await env.RATE_LIMIT.put(key, JSON.stringify({
      count: 1,
      windowStart: now,
    }), { expirationTtl: config.windowSeconds });

    return {
      allowed: true,
      remaining: config.maxRequests - 1,
      resetAt: now + config.windowSeconds,
    };
  }

  // Within window
  if (stored.count >= config.maxRequests) {
    return {
      allowed: false,
      remaining: 0,
      resetAt: stored.windowStart + config.windowSeconds,
    };
  }

  // Increment
  await env.RATE_LIMIT.put(key, JSON.stringify({
    count: stored.count + 1,
    windowStart: stored.windowStart,
  }), { expirationTtl: config.windowSeconds });

  return {
    allowed: true,
    remaining: config.maxRequests - stored.count - 1,
    resetAt: stored.windowStart + config.windowSeconds,
  };
}

// Usage in handler
async function handleAPI(request: Request, env: Env): Promise<Response> {
  const ip = request.headers.get('CF-Connecting-IP') || 'unknown';
  const rateLimit = await checkRateLimit(ip, env, {
    maxRequests: parseInt(env.RATE_LIMIT_REQUESTS || '100'),
    windowSeconds: parseInt(env.RATE_LIMIT_WINDOW || '3600'),
  });

  if (!rateLimit.allowed) {
    return json({ error: 'Rate limit exceeded' }, 429, {
      'X-RateLimit-Remaining': '0',
      'X-RateLimit-Reset': rateLimit.resetAt.toString(),
    });
  }

  // ... handle request
}

Durable Objects (Real-Time)

Chat Room Example
typescript
// wrangler.toml
// [[durable_objects.bindings]]
// name = "CHAT_ROOMS"
// class_name = "ChatRoom"
// [[migrations]]
// tag = "v1"
// new_classes = ["ChatRoom"]

export class ChatRoom {
  state: DurableObjectState;
  sessions: WebSocket[] = [];

  constructor(state: DurableObjectState) {
    this.state = state;
  }

  async fetch(request: Request): Promise<Response> {
    const url = new URL(request.url);

    if (url.pathname === '/websocket') {
      if (request.headers.get('Upgrade') !== 'websocket') {
        return new Response('Expected WebSocket', { status: 400 });
      }

      const [client, server] = Object.values(new WebSocketPair());

      server.accept();
      this.sessions.push(server);

      server.addEventListener('message', (event) => {
        this.broadcast(event.data as string, server);
      });

      server.addEventListener('close', () => {
        this.sessions = this.sessions.filter(s => s !== server);
      });

      return new Response(null, { status: 101, webSocket: client });
    }

    return new Response('Not found', { status: 404 });
  }

  broadcast(message: string, exclude?: WebSocket) {
    this.sessions.forEach(session => {
      if (session !== exclude && session.readyState === WebSocket.OPEN) {
        session.send(message);
      }
    });
  }
}

// In main worker
export default {
  async fetch(request: Request, env: Env) {
    const url = new URL(request.url);

    if (url.pathname.startsWith('/room/')) {
      const roomId = url.pathname.split('/')[2];
      const id = env.CHAT_ROOMS.idFromName(roomId);
      const room = env.CHAT_ROOMS.get(id);
      return room.fetch(request);
    }
  }
};

Deployment & Debugging

Commands
bash
# Development
npx wrangler dev                    # Local dev server
npx wrangler dev --remote           # Dev against real KV/DO

# Deployment
npx wrangler deploy                 # Deploy to production
npx wrangler deploy --env staging   # Deploy to staging

# Secrets
npx wrangler secret put API_KEY     # Set secret
npx wrangler secret list            # List secrets

# KV Management
npx wrangler kv:key list --namespace-id=xxx
npx wrangler kv:key get --namespace-id=xxx "key"
npx wrangler kv:key delete --namespace-id=xxx "key"

# Logs
npx wrangler tail                   # Real-time logs
npx wrangler tail --format=pretty   # Formatted output
Error Codes
CodeMeaning
1101Worker threw exception
1102CPU time limit exceeded
1015Rate limited by Cloudflare
524Origin timeout (>100s)

Quick Reference

typescript
// Get client IP
const ip = request.headers.get('CF-Connecting-IP');

// Get country
const country = request.cf?.country;

// Background task (won't block response)
ctx.waitUntil(doBackgroundWork());

// Streaming response
return new Response(readableStream, {
  headers: { 'Content-Type': 'text/event-stream' }
});

// Proxy request
const response = await fetch(upstreamUrl, request);
return new Response(response.body, response);

Anti-Patterns

❌ Awaiting KV writes in hot path
typescript
// ❌ ANTI-PATTERN: Blocks response on cache write
async function handler(request: Request, env: Env) {
  const data = await fetchData();
  await env.CACHE.put('key', data);  // Unnecessary wait!
  return json(data);
}

// ✅ CORRECT: Background write with waitUntil
async function handler(request: Request, env: Env, ctx: ExecutionContext) {
  const data = await fetchData();
  ctx.waitUntil(env.CACHE.put('key', data));  // Non-blocking
  return json(data);
}
❌ Missing CORS handling
typescript
// ❌ ANTI-PATTERN: No preflight handling = broken browser requests
export default {
  async fetch(request: Request) {
    return json({ data: 'hello' });  // OPTIONS requests fail!
  }
}

// ✅ CORRECT: Handle OPTIONS preflight
export default {
  async fetch(request: Request) {
    if (request.method === 'OPTIONS') {
      return new Response(null, { status: 204, headers: CORS_HEADERS });
    }
    return json({ data: 'hello' });
  }
}
❌ Secrets in wrangler.toml
toml
# ❌ ANTI-PATTERN: Secrets in config (committed to git!)
[vars]
API_KEY = "sk-live-xxxxx"

# ✅ CORRECT: Use wrangler secret
# Run: npx wrangler secret put API_KEY
# Access: env.API_KEY
❌ Ignoring KV eventual consistency
typescript
// ❌ ANTI-PATTERN: Read immediately after write
await env.KV.put('count', String(newCount));
const verify = await env.KV.get('count');  // May return old value!

// ✅ CORRECT: Trust write succeeded, or use Durable Objects for consistency
await env.KV.put('count', String(newCount));
return json({ count: newCount });  // Return what you wrote
❌ Blocking on external APIs without timeout
typescript
// ❌ ANTI-PATTERN: External API can hang your worker
const data = await fetch('https://slow-api.com/data');

// ✅ CORRECT: Add timeout with AbortController
const controller = new AbortController();
const timeout = setTimeout(() => controller.abort(), 5000);
try {
  const data = await fetch('https://slow-api.com/data', {
    signal: controller.signal
  });
} finally {
  clearTimeout(timeout);
}

References

See /references/ for detailed guides:

  • kv-patterns.md - Advanced KV usage patterns
  • durable-objects.md - Real-time features with DO
  • debugging.md - Troubleshooting common issues

© curiositech, 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 1 other file in .claude/skills/cloudflare-worker-dev of curiositech/some_claude_skills.

  • SKILL.md
  • .claude-plugin/plugin.json

Open the folder on GitHubat commit 6713fc7

Compare with similar skills

Cloudflare Worker Dev 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 Worker Dev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cloudflare Worker Dev this skillcuriositech/some_claude_skills243—~3.4kAutomated safety check: NotesMIT
Apikerhodgef/apiker127—~1.4kAutomated safety check: PassMIT
Cloudflare WorkersEpicenterHQ/epicenter4.8k—~576Automated safety check: PassCustom licence
Cloudflare Kvsecondsky/claude-skills227—~2.4kAutomated safety check: PassMIT
Cloudflareericrisco/rsc-harness156—~2.6kAutomated safety check: PassMIT
Cloudflarehoodini/ai-agents-skills282—~3kAutomated safety check: PassNone

Similar skills

  • Apiker

    hodgef/apiker

    Develop, review, and extend the Apiker library — a framework for building serverless REST APIs on Cloudflare Workers + Durable Objects.

    127 GitHub stars~1.4k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Cloudflare Workers

    EpicenterHQ/epicenter

    Cloudflare Workers patterns for Worker runtime APIs, Durable Objects, KV, R2, D1, Queues, WebSockets, streaming responses, bindings, wrangler configuration, and deployment limits.

    4.8k GitHub stars~576 tokensUpdated today
    Backend & APIsAuto-check passed
  • Cloudflare Kv

    secondsky/claude-skills

    Cloudflare Workers KV global key-value storage. An agent skill from secondsky/claude-skills.

    227 GitHub stars~2.4k tokensUpdated 9 days ago
    Backend & APIsAuto-check passed
  • Cloudflare

    ericrisco/rsc-harness

    A skill your agent uses when working on Cloudflare's edge platform — wrangler.jsonc bindings, choosing between D1/KV/R2/Durable Objects/Queues, deploying a Worker or SPA via Static Assets, or…

    156 GitHub stars~2.6k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Cloudflare

    hoodini/ai-agents-skills

    Build and deploy on Cloudflare's edge platform. An agent skill from hoodini/ai-agents-skills.

    282 GitHub stars~3k tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed
  • Durable Objects

    cloudflare/skills

    Official

    Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

    3k GitHub starsUsed in 2 repos~1.5k tokens
    Backend & APIsAuto-check passed

More from curiositech/some_claude_skills

All 108 skills in this repo
  • Crisis Detection Intervention AI

    curiositech/some_claude_skills

    Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.

    243 GitHub starsUsed in 3 repos~3.8k tokens
    Auto-check passed
  • Form Validation Architect

    curiositech/some_claude_skills

    End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.

    243 GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Competitive Cartographer

    curiositech/some_claude_skills

    Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations.

    243 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • GitHub Actions Pipeline Builder

    curiositech/some_claude_skills

    Build production CI/CD pipelines with GitHub Actions. An agent skill from curiositech/some_claude_skills.

    243 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check: notes
  • Computer Vision Pipeline

    curiositech/some_claude_skills

    Build production computer vision pipelines for object detection, tracking, and video analysis.

    243 GitHub starsUsed in 1 repo~4k tokens
    Auto-check passed
  • Design Archivist

    curiositech/some_claude_skills

    Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction…

    243 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Categories

Questions about Cloudflare Worker Dev

What does Cloudflare Worker Dev do?

Cloudflare Workers, KV, Durable Objects, and edge computing development. Cloudflare Worker Dev is an agent skill from curiositech/some_claude_skills. Cloudflare Workers, KV, Durable Objects, and edge computing development.

When should I use Cloudflare Worker Dev?

Cloudflare Worker Dev fits situations like: serverless APIs; real-time features.

How do I install Cloudflare Worker Dev in Claude Code?

Run `npx skills add curiositech/some_claude_skills --skill cloudflare-worker-dev -a claude-code`. Or copy the skill folder (.claude/skills/cloudflare-worker-dev in curiositech/some_claude_skills) into .claude/skills/cloudflare-worker-dev in your project. Claude Code loads it when a task matches its description.

How do I install Cloudflare Worker Dev in Codex?

Run `npx skills add curiositech/some_claude_skills --skill cloudflare-worker-dev -a codex`. Or copy the skill folder (.claude/skills/cloudflare-worker-dev in curiositech/some_claude_skills) into .agents/skills/cloudflare-worker-dev in your project. Codex loads it when a task matches its description.

Can I use Cloudflare Worker Dev 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 curiositech/some_claude_skills --skill cloudflare-worker-dev -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-worker-dev, .gemini/skills/cloudflare-worker-dev, .github/skills/cloudflare-worker-dev and .opencode/skills/cloudflare-worker-dev in your project.

What does Cloudflare Worker Dev need to run?

Going by SKILL.md and its folder, Cloudflare Worker Dev needs the command-line tools its instructions call (npx) and credentials named API_KEY. Our summary lists: Node.js; A credential in API_KEY. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Grep, Glob.

Does Cloudflare Worker Dev access the network?

SKILL.md names 1 domain. In commands or code: slow-api.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Cloudflare Worker Dev safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Cloudflare Worker Dev use?

Cloudflare Worker Dev 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 Cloudflare Worker Dev use?

About 3.4k tokens (SKILL.md is roughly 14k 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 Cloudflare Worker Dev?

Skills that share tags, products or a category with Cloudflare Worker Dev: Apiker (hodgef/apiker, 127 stars), Cloudflare Workers (EpicenterHQ/epicenter, 4.8k stars), Cloudflare Kv (secondsky/claude-skills, 227 stars) and Cloudflare (ericrisco/rsc-harness, 156 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cloudflare Worker Dev?

curiositech (a GitHub organization) maintains it in curiositech/some_claude_skills, which has 243 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on September 6, 2026.

Source: curiositech/some_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.