mcpbeat Sign in

Create Docs Skeleton Agent Skill

Scaffold a new skeleton markdown doc for docs.getdbt.com — standard guide, reference page, feature/product page, or release note entry. Use when asked to create a new doc page, scaffold a doc, start a new page, or add a page to the sidebar.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
205
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/dbt-labs/docs.getdbt.com --skill create-docs-skeleton

The instruction itself

8 sections, as written by the author

Scaffold a new docs.getdbt.com markdown page with correct frontmatter and section

structure, then optionally wire it into sidebars.js. All paths below are relative

to the website/ directory (repo root for this project).

Workflow

  • Ask for the target path if not given, e.g. docs/docs/dbt-ai/new-feature.md.

The user always specifies this — don't infer it.

  • Ask which doc type (see table below) if not obvious from context.
  • Build frontmatter. Always include the full default set:

title, id, description, sidebar_label. Then ask ONLY about the

SEO fields (meta_description / keywords) — don't ask about the rest,

don't skip the defaults.

  • Apply brand rules to all generated prose (title, description, headings,

body): dbt always lowercase, dbt Labs capital L, job titles lowercase,

sentence case headings, "dbt platform" not "dbt Cloud", <Constant> for

product names where one exists in constants.js.

  • Write the file with the skeleton for the chosen doc type.
  • Offer to add a sidebar entry in sidebars.js (see below) — ask where

in the tree it belongs (which category), don't guess.

Doc types

| Type | Frontmatter extras | Body skeleton |

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

| Standard guide | none beyond defaults | ## sections for the task, no special components |

| Reference page | keywords (list) | Property/config table, links to related build docs |

| New feature/product page | tags, availability block | <IntroText>, <Lifecycle status="...">, "Where to access", "Considerations"/FAQ |

| Release note entry | none — appended to existing file, no new frontmatter | Bullet under the current month's ## heading, using New:/Enhancement:/Fix:/Behavior change: prefix |

Verified against real pages in this repo:

docs/docs/dbt-ai/copilot-overview.md (feature page),

docs/reference/semantic-model-properties.md (reference page),

docs/docs/dbt-versions/release-notes.md (release notes).

Standard guide skeleton

---
title: "<Title>"
id: "<slug>"
description: "<One-sentence description of what this page covers.>"
sidebar_label: "<Short nav label>"
---

# <Title>

<One-paragraph intro: what this is, who it's for.>

## <First task heading>

<Steps or explanation.>

## <Next task heading>

<Steps or explanation.>

## Related docs

- [<Related page>](<relative-link>)

Reference page skeleton

---
title: "<Title>"
id: "<slug>"
sidebar_label: "<Short nav label>"
description: "<One-sentence description of what this reference covers.>"
keywords:
  - <keyword one>
  - <keyword two>
---

<One-paragraph intro: what this configures/defines and where it's used, with a
link to the conceptual doc it supports.>

## <Property/section name>

| Field | Type | Required | Description |
|---|---|---|---|
| `field_name` | string | Yes | <what it does> |

## Related docs

- [<Related page>](<relative-link>)

New feature/product page skeleton

---
title: "<Product/feature name>"
id: "<slug>"
description: "<One-sentence description of what this feature does.>"
sidebar_label: "<Short nav label>"
tags: [<Tag>]
availability:
  surface: platform
  access: paid_plan
  minPlan: <plan>
---

# <Product/feature name>

<IntroText>
<One or two sentences: what it is, the core value.>
</IntroText>

<Lifecycle status="preview" />

## Where to access <feature name>

<Bulleted list of surfaces/entry points, each linking to its own doc.>

## Considerations

- <Prerequisite or limitation.>
- <Prerequisite or limitation.>

Drop <Lifecycle> if the feature is already generally available. Drop the

availability frontmatter block if the feature isn't platform/plan-gated.

Release note entry

Don't create a new file — append to the current month's section in

docs/docs/dbt-versions/release-notes.md. If the current month has no ##

heading yet, add one (## <Month> <Year>) above the previous month's.

- **New:** <What shipped and why it matters. Link to the full doc.>

Use Enhancement:, Fix:, or Behavior change: instead of New:

as appropriate — see the categories defined at the top of that file.

sidebars.js at the repo root nests doc IDs (without .md) inside

items: [...] arrays under type: "category" blocks. Example, from the

"dbt Wizard" category (sidebars.js:392-401):

{
  type: "category",
  label: "dbt Wizard",
  collapsed: true,
  link: { type: "doc", id: "docs/platform/wizard-overview" },
  items: [
    "docs/platform/wizard-overview",
    "docs/dbt-ai/wizard-quickstart",
    // ... add the new doc id here, e.g.:
    "docs/dbt-ai/new-feature",
  ],
},

To wire in a new page:

  • Find the category the user wants it under (ask if unclear).
  • Add "<same path as the file, without .md extension>" to that category's

items array, in the position the user specifies (or logically, near

related pages).

  • Don't create new categories or reorder existing entries unless asked.

Gotchas

  • id in frontmatter should match the filename (without .md) — Docusaurus

doesn't require this, but every real example in this repo does it, and

drift confuses cross-references.

  • Release notes are appended to one long file, not created as new pages

— don't scaffold a standalone file for a release note by mistake.

  • pagination_next: null / pagination_prev: null only appears on

standalone/landing-style pages (e.g. release-notes.md) — don't add it by

default to a normal guide or reference page; it suppresses the

next/previous nav links.

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 dbt-labs/create-docs-skeleton 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.