Cloudflare Skill — Anti-Patterns as Code
Organizes guidance around a dedicated Anti-Patterns section — SQL injection, secrets, resource cleanup, missing compatibility_date — each…
- Type
- CLAUDE.md Example
- Repository
- dmmulroy/cloudflare-skill
- GitHub stars
- 727
- License
- MIT
- Repo last updated
- Jan 29, 2026
- Source file
- AGENTS.md
What Cloudflare Skill — Anti-Patterns as Code is
Cloudflare Skill — Anti-Patterns as Code is a claude.md example published in the dmmulroy/cloudflare-skill repository on GitHub, which has about 727 stars.
A CLAUDE.md file holds standing instructions that Claude Code reads at the start of every session in a project, such as conventions, commands, and rules. Examples like Cloudflare Skill — Anti-Patterns as Code show how other teams structure theirs.
In Claude Cowork, the equivalent places for this kind of guidance are your global instructions, project instructions, and folder instructions.
How to install Cloudflare Skill — Anti-Patterns as Code
Claude Code
- Copy the parts that fit your project into CLAUDE.md at the project root, or into ~/.claude/CLAUDE.md for rules that apply everywhere.
- Keep it short and specific; remove anything that doesn't match how your team works.
Claude Cowork
- Put personal rules in Settings → Instructions for Claude (global instructions).
- Put project or folder rules in the project's instructions or the folder instructions for that directory.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from AGENTS.md, shared under the repository's MIT license. Read the full file on GitHub.
Generated: 2026-01-28
OVERVIEW
Documentation/skill repository for Cloudflare platform—structured reference docs for AI/LLM consumption. No executable code.
STRUCTURE
./
├── README.md # Project overview + install instructions
├── LICENSE # MIT license
├── install.sh # Installation script
├── command/
│ └── cloudflare.md # /cloudflare slash command
└── skills/
└── cloudflare/
├── SKILL.md # Main skill manifest + decision trees
└── references/ # Product subdirs
└── <product>/
├── README.md
├── api.md
├── configuration.md
├── patterns.md
└── gotchas.mdWHERE TO LOOK
CONVENTIONS
VCS: jujutsu (NOT git)
# CORRECT
jj status
jj log
jj new
jj commit -m "msg"
# WRONG - do not use
git status # .jj/ present = use jjReference File Structure
Every product follows 5-file pattern:
- README.md — Overview, when to use
- api.md — Runtime API reference
- configuration.md — wrangler.toml + binding setup
- patterns.md — Usage patterns
- gotchas.md — Pitfalls, limitations
YAML Frontmatter
SKILL.md files use frontmatter for machine parsing:
---
name: product-name
description: Brief description
references:
- related-product
---ANTI-PATTERNS
SQL Injection (D1)
// NEVER - string interpolation
const result = await db.prepare(`SELECT * FROM users WHERE id = ${id}`).all();
// ALWAYS - prepared statements with bind()
const result = await db.prepare("SELECT * FROM users WHERE id = ?").bind(id).all();Secrets Management
# NEVER commit .dev.vars (contains secrets)
# NEVER hardcode secrets in codeResource Management
// ALWAYS close browser in finally block (browser-rendering)
const browser = await puppeteer.launch();
try {
// ...
} finally {
await browser.close();
}Configuration
# ALWAYS set compatibility_date for new projects (workers)
compatibility_date = "2026-01-01"NOTES
- No CI/CD configured (docs-only repo)
- No linting/formatting (no code to lint)
- .opencode/ contains plugin config, not project code
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Cloudflare Skill — Anti-Patterns as Code?
Cloudflare Skill — Anti-Patterns as Code is a claude.md example for Claude Code and Claude Cowork from the dmmulroy/cloudflare-skill repository on GitHub. Organizes guidance around a dedicated Anti-Patterns section — SQL injection, secrets, resource cleanup, missing compatibility_date — each…
How do I install Cloudflare Skill — Anti-Patterns as Code in Claude Code?
Copy the parts that fit your project into CLAUDE.md at the project root, or into ~/.claude/CLAUDE.md for rules that apply everywhere. Keep it short and specific; remove anything that doesn't match how your team works.
Can I use Cloudflare Skill — Anti-Patterns as Code in Claude Cowork?
Put personal rules in Settings → Instructions for Claude (global instructions). Put project or folder rules in the project's instructions or the folder instructions for that directory.
Is Cloudflare Skill — Anti-Patterns as Code safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- dbt Agent Skills — Frontmatter Rules & Error Table The most actionable take on SKILL.md frontmatter: the exact allowed fields, the lowercase-hyphen name rule, and a validation-error → fix… CLAUDE.md Example · dbt-labs/dbt-agent-skills
- Claudeclaw — Identity & Voice as Persistent Memory A fully worked example of using CLAUDE.md as the agent's persistent identity and voice spec — Core Truths, Vibe, emoji budget, boundaries… CLAUDE.md Example · moazbuilds/claudeclaw
- Posit Skills — Skill-Repo Conventions & Registration A complete, transferable playbook for a skills repository: the directory contract, the SKILL.md frontmatter, the token/line budget, the… CLAUDE.md Example · posit-dev/skills
- cc-safety-net — TypeScript Style Guide with Good/Bad Pairs The clearest way to express code conventions to an agent: every rule (inline single-use vars, no unnecessary destructuring, early returns… CLAUDE.md Example · kenryu42/cc-safety-net
- Blueprint — Flows, Skills, and Unattended Loops A masterclass in structuring a multi-skill agent system in one file: three named flows (Setup / Decide / Deliver), a skill catalog, and a… CLAUDE.md Example · owainlewis/blueprint
- Callstack Agent Skills — Quick Checklist & 'Good Skill' Rubric Distills skill authoring to a numbered quick checklist plus a 'What Makes a Good Skill' rubric (concise, third-person description… CLAUDE.md Example · callstackincubator/agent-skills
- Turbo — Dual-Edition Skill Monorepo Map A compact, well-annotated map of a monorepo that ships parallel Claude Code and Codex editions from one source tree. Cleanly separates… CLAUDE.md Example · tobihagemann/turbo
- Tiger pg-aiguide — MCP Server Code Style Guide A tight, transferable style guide for a TypeScript MCP server: ESM with .js import extensions, zod for tool-input validation, and the… CLAUDE.md Example · timescale/pg-aiguide