try-works/role-model / .agents/skills/style-guide-review
style-guide-review
VerifiedReview changed MDX/docs files in a pull request against the Cloudflare docs style guide and return structured findings.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.4 KB |
| reference/always/core-content.md | markdown | 7.3 KB |
| reference/components/anchor-heading.md | markdown | 580 B |
| reference/components/api-request.md | markdown | 709 B |
| reference/components/curl.md | markdown | 457 B |
| reference/components/dash-button.md | markdown | 617 B |
| reference/components/extra-flag-details.md | markdown | 696 B |
| reference/components/file-tree.md | markdown | 368 B |
| reference/components/github-code.md | markdown | 974 B |
| reference/components/markdown.md | markdown | 624 B |
| reference/components/package-managers.md | markdown | 524 B |
| reference/components/steps.md | markdown | 615 B |
| reference/components/subtract-ip-calculator.md | markdown | 508 B |
| reference/components/tabs.md | markdown | 842 B |
| reference/components/typescript-example.md | markdown | 1.1 KB |
| reference/components/wrangler-config.md | markdown | 852 B |
| reference/conditional/code-blocks.md | markdown | 1.9 KB |
| reference/conditional/frontmatter.md | markdown | 1.1 KB |
| reference/conditional/imports.md | markdown | 369 B |
| reference/conditional/links.md | markdown | 1.3 KB |
| reference/manifest.json | config | 3.8 KB |
reference/always/core-content.md
View on GitHub---
title: Core Content Rules
description: Always load for any MDX file with added content lines.
---
## Writing Style
- If prose contains a contraction (`don't`, `can't`, `won't`, `isn't`, `aren't`, `doesn't`, `didn't`, `hasn't`, `haven't`, `couldn't`, `wouldn't`, `shouldn't`, `it's`, `we're`, `you're`, `they're`, `I'm`, `let's`, `there's`, `that's`, `what's`) → **warning**: remove the contraction. Exception: inside code blocks or backtick spans.
- If prose contains `please` → **warning**: remove it.
- If prose contains directional words (`above`, `below`, `as shown above`, `as noted below`) → **warning**: replace with a direct reference by name or link.
- If prose uses `click` → **suggestion**: replace with `select`.
- If prose uses `navigate to` → **suggestion**: replace with `go to`.
- If prose uses `see the [link]` or `see [link]` → **suggestion**: replace with `refer to [link]`.
- If prose uses `e.g.` → **suggestion**: replace with `for example` or restructure.
- If prose uses `i.e.` → **suggestion**: replace with `that is` or restructure.
- If prose uses `etc.` → **suggestion**: replace with a complete list or `and so on`.
- If prose uses LLM-filler phrases (`Note that`, `It is worth noting that`, `It is important to note that`, `Please note that`, `Keep in mind that`) → **suggestion**: remove the filler and state the fact directly.
- If prose uses passive voice where active voice would be clearer → **suggestion**: rewrite in active voice.
- If a list or sentence has three or more items without an Oxford comma before `and` or `or` → **suggestion**: add the serial comma.
- If prose uses a semicolon to join two independent clauses → **suggestion**: break into two sentences.
---
## Terminology and Product Names
**Warning** for any prose line using these terms incorrectly:
| Correct | Incorrect forms |
| ------------------------- | ----------------------------------------------- |
| DDoS | DDOS, ddos, Ddos |
| Zero Trust | zero trust, Zero trust |
| CAPTCHA | Captcha, captcha |
| Internet (as proper noun) | internet (when referring to the global network) |
| SSL | ssl |
| TLS | tls |
| WAF | waf |
| Cloudflare Workers | cloudflare workers, CF Workers |
| Workers AI | workers ai |
**Warning** for any prose line using deprecated jargon:
| Instead of | Use |
| ---------------------------- | --------------------- |
| whitelist | allowlist |
| blacklist | blocklist |
| master / slave | primary / replica |
| man-in-the-middle | on-path attack |
| sanity check | validate / smoke test |
| out-of-the-box | default |
| on-prem | on-premises |
| enable/disable (for toggles) | turn on / turn off |
- If prose uses `click` for a UI element → **suggestion**: use `select`.
- If an example domain is a real-looking but non-reserved domain (`yourdomain.com`, `mysite.com`) → **suggestion**: use `example.com`, `example.org`, or `myappexample.com` instead.
---
## Marketing Language
**Suggestion** when prose contains any of these phrases: `Perfect for`, `Best for`, `Best-in-class`, `Empowers you to`, `Enables you to`, `Essential for`, `Critical for`, or `Modern <noun>` / `Built for <noun>` patterns → replace with direct language that states what the thing actually does. Exception: inside code blocks or backtick spans.
---
## Time-Sensitive Content
These rules fire only on files **outside** `src/content/changelog/` paths. Exceptions: code blocks, backtick spans, frontmatter fields (e.g. `reviewed:`, `compatibility_date:`), URLs, and example data.
- If prose contains `Coming soon`, `recently added`, `newly available`, `now available`, or `just released` → **suggestion**: remove the phrase; docs must read as timeless.
- If prose contains a month name (`January`, `February`, `March`, `April`, `May`, `June`, `July`, `August`, `September`, `October`, `November`, `December`) → **suggestion**: remove or rewrite without a month reference.
- If prose contains a four-digit year (e.g. `2024`, `2025`) → **suggestion**: remove or rewrite without the year.
---
## File Locations
- If an image file is added to `src/content/` → **warning**: images must go in `src/assets/images/{product}/`, not in `src/content/`.
---
## Headings
- If a body heading is a bare `# ` heading (H1) in body content (not frontmatter) → **warning**: the page `title` frontmatter already renders the H1. Change to `##`.
- If a heading skips a level (e.g. H2 directly to H4) → **warning**: heading levels must be sequential.
- If a heading uses title case (multiple capitalized non-proper-noun words) → **suggestion**: use sentence case — capitalize only the first word and proper nouns.
- If a heading ends with `.`, `?`, `!`, or `:` → **warning**: remove trailing punctuation.
- If a heading begins with a verb ending in `-ing` (`Installing`, `Configuring`, `Setting up`) → **warning**: use imperative form instead (`Install`, `Configure`, `Set up`).
- If frontmatter `title:` or `sidebar.label:` contains an emoji → **warning**: remove it.
---
## Formatting
**Bold and Monospace**
- If prose bolds a program or tool name (`**wrangler**`, `**npm**`, `**bun**`) → **warning**: use monospace instead: `` `wrangler` ``, `` `npm` ``, `` `bun` ``.
- If a prose line italicizes `enabled` or `disabled` as toggle states → **warning**: do not italicize toggle states.
- Items that get monospace: IP addresses, port numbers, API commands (`GET`, `POST`), terminal commands, file paths, filenames, config keys, data types, env var names, HTTP headers, HTTP status codes, URLs as input/output, DNS record types.
**Lists**
- If a numbered list is used for non-sequential items → **warning**: use bullet points for unordered items.
- If a bulleted list is used for sequential steps → **warning**: use a numbered list for procedures.
- If a bullet list has fewer than three items → **suggestion**: consider writing as prose instead.
**Tables**
- If a table has no column headers → **warning**: all column headers must be labeled.
- If a table is introduced with a sentence fragment → **warning**: introduce tables with a complete sentence ending in a colon.
**Admonitions**
- Valid types: `:::note`, `:::caution`, `:::tip`.
- If a patch adds more than one admonition of the same type in the same section → **suggestion**: consolidate or integrate the content into prose.
- If an admonition content could be integrated into surrounding prose → **suggestion**: do so rather than using an admonition.
**Numbers**
- If prose uses a single digit (0–9) as a numeral in body text (not a measurement, metric, or UI value) → **suggestion**: spell out: `three options` not `3 options`.
- If prose has a number and unit without a space between them → **warning**: add a space: `128 GB` not `128GB`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |