mcpbeat Sign in

Coding Standards Agent Skill

Use when writing or reviewing TypeScript in this repo. Covers the no-`any` rule and where to put new types, the uppercase-acronym style guide, and the rules for code comments (no historical context). (project)

834 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1089
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/cloudflare/sandbox-sdk --skill coding-standards

The instruction itself

8 sections, as written by the author

Coding Standards

TypeScript: No any

Never use any unless absolutely necessary — and that should be a final resort.

Process when you reach for any:

  • Look for an existing type that fits. Most domains already have one.
  • If no suitable type exists, define a proper one in the right location:
  • Shared typespackages/shared/src/types.ts or relevant subdirectory
  • SDK-specific typespackages/sandbox/src/clients/types.ts or the appropriate client file
  • Container-specific types → under packages/sandbox-container/src/ with appropriate naming
  • Use the new type everywhere it applies — don't leave one-off shapes scattered around.

This catches errors at compile time instead of runtime and keeps the codebase consistent.

Style: Uppercase Acronyms

When an acronym appears inside a camelCase or PascalCase identifier, keep it fully uppercase:

| ✅ Do | ❌ Don't |

| ----------------- | ----------------- |

| SandboxRPCAPI | SandboxRpcApi |

| containerURL | containerUrl |

| parseHTTPHeader | parseHttpHeader |

| getAPIKey | getApiKey |

Applies to all acronyms: API, URL, HTTP, RPC, SSE, SSH, DNS, ID, etc.

Exception: library-provided names keep their original casing (e.g. capnweb's RpcTarget stays RpcTarget).

Code Comments

Write comments for future readers, not for the current conversation.

Comments should describe the current state of the code. A developer reading the code months later won't have context about bugs that were fixed, conversations that happened, or earlier implementations.

Don't reference historical context

// ❌ Bad: references a bug the reader knows nothing about
// Uses character tracking to avoid the bug where indexOf('') returns wrong position

// ❌ Bad: implies something was wrong before
// Start the server with proper WebSocket typing

// ❌ Bad: "prevent" implies there was a problem to prevent
// Assign synchronously to prevent race conditions

Do describe current behavior and design intent

// ✅ Good: describes what the code does now
// Returns parsed events and any remaining unparsed content

// ✅ Good: explains design rationale without historical context
// Assigned synchronously so concurrent callers share the same connection attempt

// ✅ Good: explains a non-obvious implementation choice
// Uses IIFE to ensure promise exists before any await points

Smell test

If your comment contains "to avoid", "to fix", "to prevent", "instead of", or "properly" — reconsider whether you're describing current behavior or quietly referencing something that no longer exists. Rewrite to describe what the code does now and why this design was chosen.

API Design

When adding or modifying SDK methods:

  • Use clear, descriptive names that indicate what the method does
  • Validate inputs before passing to container APIs
  • Provide helpful error messages with context (use the custom error classes in packages/shared/src/errors/)

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take cloudflare/coding-standards from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.