docs: Skill for Claude Code

.agents/skills/docs-review/SKILL.md

docs-review is a skill for Claude Code, Codex from mintlify/docs. It costs 65 tokens per session (828 once invoked), scanned A, original, MIT.

A review workflow for Mintlify documentation, using a project style guide and the product's code or interface to check proposed changes. Mintlify is a documentation publishing platform.

In plain words
What is it for?
It is for reviewing documentation changes, checking facts and user-interface steps, applying house style, and reporting anything that cannot be verified.
Why use it?
It helps catch inaccurate product descriptions, outdated interface instructions, and style problems before documentation is handed back or published.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is mintlify/docs's own configuration. It tells Claude Code and Codex how to work on docs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything docs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mintlify/docs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mintlify/docs/main/.agents/skills/docs-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mintlify/docs

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for docs-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/mintlify/docs/docs-review/github.svg)](https://agentmods.dev/skills/mintlify/docs/docs-review)
Your own site
<a href="https://agentmods.dev/skills/mintlify/docs/docs-review"><img src="https://agentmods.dev/badge/skills/mintlify/docs/docs-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for docs-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/mintlify/docs/docs-review"><img src="https://agentmods.dev/badge/skills/mintlify/docs/docs-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 828 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00828
Opus 5.5 $0.00026 $0.00331
Sonnet 5.5 $0.00013 $0.00166
Haiku 4.5 $0.00006 $0.00083

Measured 3d ago against content hash d4445947943f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/docs-review/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs review

style-guide/ holds the rules for this repo's docs. This skill doesn't repeat them. It describes the order to apply them in.

Before you review anything, read style-guide/README.md and every file it lists. Don't work from memory of the guide or a summary of it. If you don't have a local checkout, read the files from the mintlify project with the Mintlify Admin MCP read tool.

Check facts against the product

Check every fact against the product, not against other docs pages, because other pages can be out of date:

  • UI steps: Take button, tab, and field names and the order of screens from the product or its frontend source.
  • Behavior claims: Read the code path before you describe what the product does. If another docs page contradicts the code, find out why before you edit either page.

If you can't verify a fact, list it under areas of uncertainty in your report. Never guess.

Review order

Review your own drafts the same way you review anyone else's. Cut first, then check the structure, then the sentences. Rewriting a sentence is wasted work if the sentence shouldn't be on the page.

  1. Lint. If you have a shell, run vale on the changed files, mint broken-links, and mint a11y. If you don't, fix any validation errors your edits return. Either way, a clean run doesn't mean the page follows the guide.
  2. Cut what the reader won't act on. Read the page one paragraph at a time and apply "Leave out what the reader won't act on" in style-guide/content-strategy.md. Apply it to existing content, other people's content, and your own draft. No other step catches this, and restructuring a sentence that should be cut makes the page longer.
  3. Check the structure against style-guide/content-strategy.md: page structure, prerequisites, where content goes, and duplication.
  4. Check every sentence against style-guide/voice-and-tone.md. Take the "Clear sentences" rules one heading at a time, and check every sentence on the page against that rule before you move to the next one. Then check "Phrases to cut" and "AI-writing tells."
  5. Check formatting and components against style-guide/formatting-and-components.md and terms against style-guide/word-list.md.
  6. Apply the findings. If the person you're working with wrote or edited prose in this conversation, don't change their sentences. Report those findings and ask once whether to apply them.
  7. Review the edited page again from the top, steps 1 to 5. Your edits create new problems. For example, turning a paragraph into a list can leave several short paragraphs in a row.

Read the full file on GitHub · 48 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 48 lines · 65 tokens per session scan A d4445947943f

Subscribe to this mod's changes

docs-review is a skill published in the GitHub repository mintlify/docs (461 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 828 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-04.

Related

docs-review compared with skills from other repositories

docs-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docs-reviewmintlify/docsSkill461yesterdayMITA65Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code